Retry in case where the JSON deserialization fails

5041: Update version for the next release (v1.11.1) in Cargo.toml r=dureuill a=meili-bot

⚠️ This PR is automatically generated. Check the new version is the expected one and Cargo.lock has been updated before merging.

Co-authored-by: dureuill <dureuill@users.noreply.github.com>

Cargo.lock

@@ -386,15 +386,16 @@ checksum = "96d30a06541fbafbc7f82ed10c06164cfbd2c401138f6addd8404629c4b16711"
 
 [[package]]
 name = "arroy"
-version = "0.4.0"
+version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2ece9e5347e7fdaaea3181dec7f916677ad5f3fcbac183648ce1924eb4aeef9a"
+checksum = "dfc5f272f38fa063bbff0a7ab5219404e221493de005e2b4078c62d626ef567e"
 dependencies = [
  "bytemuck",
  "byteorder",
  "heed",
  "log",
  "memmap2",
+ "nohash",
  "ordered-float",
  "rand",
  "rayon",
@@ -471,7 +472,7 @@ checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
 [[package]]
 name = "benchmarks"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "anyhow",
  "bytes",
@@ -527,7 +528,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "regex",
- "rustc-hash",
+ "rustc-hash 1.1.0",
  "shlex",
  "syn 2.0.60",
 ]
@@ -652,7 +653,7 @@ dependencies = [
 
 [[package]]
 name = "build-info"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "anyhow",
  "time",
@@ -933,9 +934,9 @@ dependencies = [
 
 [[package]]
 name = "charabia"
-version = "0.9.0"
+version = "0.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03cd8f290cae94934cdd0103c14c2de9faf2d7d85be0d24d511af2bf1b14119d"
+checksum = "55ff52497324e7d168505a16949ae836c14595606fab94687238d2f6c8d4c798"
 dependencies = [
  "aho-corasick",
  "csv",
@@ -1622,7 +1623,7 @@ dependencies = [
 
 [[package]]
 name = "dump"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "anyhow",
  "big_s",
@@ -1834,7 +1835,7 @@ checksum = "9fc0510504f03c51ada170672ac806f1f105a88aa97a5281117e1ddc3368e51a"
 
 [[package]]
 name = "file-store"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "tempfile",
  "thiserror",
@@ -1856,7 +1857,7 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "insta",
  "nom",
@@ -1876,7 +1877,7 @@ dependencies = [
 
 [[package]]
 name = "flatten-serde-json"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "criterion",
  "serde_json",
@@ -2000,7 +2001,7 @@ dependencies = [
 
 [[package]]
 name = "fuzzers"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "arbitrary",
  "clap",
@@ -2552,7 +2553,7 @@ checksum = "206ca75c9c03ba3d4ace2460e57b189f39f43de612c2f85836e65c929701bb2d"
 
 [[package]]
 name = "index-scheduler"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "anyhow",
  "arroy",
@@ -2746,7 +2747,7 @@ dependencies = [
 
 [[package]]
 name = "json-depth-checker"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "criterion",
  "serde_json",
@@ -3365,7 +3366,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
 
 [[package]]
 name = "meili-snap"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "insta",
  "md5",
@@ -3374,7 +3375,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "actix-cors",
  "actix-http",
@@ -3414,6 +3415,7 @@ dependencies = [
  "meilisearch-types",
  "mimalloc",
  "mime",
+ "mopa-maintained",
  "num_cpus",
  "obkv",
  "once_cell",
@@ -3463,7 +3465,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-auth"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "base64 0.22.1",
  "enum-iterator",
@@ -3482,7 +3484,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-types"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "actix-web",
  "anyhow",
@@ -3512,7 +3514,7 @@ dependencies = [
 
 [[package]]
 name = "meilitool"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "anyhow",
  "clap",
@@ -3520,6 +3522,7 @@ dependencies = [
  "file-store",
  "meilisearch-auth",
  "meilisearch-types",
+ "serde",
  "time",
  "uuid",
 ]
@@ -3542,7 +3545,7 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "arroy",
  "big_s",
@@ -3679,12 +3682,24 @@ dependencies = [
  "syn 2.0.60",
 ]
 
+[[package]]
+name = "mopa-maintained"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "79b7f3e22167862cc7c95b21a6f326c22e4bf40da59cbf000b368a310173ba11"
+
 [[package]]
 name = "mutually_exclusive_features"
 version = "0.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6d02c0b00610773bb7fc61d85e13d86c7858cbdf00e1a120bfc41bc055dbaa0e"
 
+[[package]]
+name = "nohash"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a0f889fb66f7acdf83442c35775764b51fed3c606ab9cee51500dbde2cf528ca"
+
 [[package]]
 name = "nom"
 version = "7.1.3"
@@ -3976,7 +3991,7 @@ checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
 
 [[package]]
 name = "permissive-json-pointer"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "big_s",
  "serde_json",
@@ -4307,7 +4322,7 @@ dependencies = [
  "pin-project-lite",
  "quinn-proto",
  "quinn-udp",
- "rustc-hash",
+ "rustc-hash 1.1.0",
  "rustls",
  "thiserror",
  "tokio",
@@ -4316,14 +4331,14 @@ dependencies = [
 
 [[package]]
 name = "quinn-proto"
-version = "0.11.3"
+version = "0.11.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ddf517c03a109db8100448a4be38d498df8a210a99fe0e1b9eaf39e78c640efe"
+checksum = "fadfaed2cd7f389d0161bb73eeb07b7b78f8691047a6f3e73caaeae55310a4a6"
 dependencies = [
  "bytes",
  "rand",
  "ring",
- "rustc-hash",
+ "rustc-hash 2.0.0",
  "rustls",
  "slab",
  "thiserror",
@@ -4574,9 +4589,8 @@ dependencies = [
 
 [[package]]
 name = "rhai"
-version = "1.19.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "61797318be89b1a268a018a92a7657096d83f3ecb31418b9e9c16dcbb043b702"
+version = "1.20.0"
+source = "git+https://github.com/rhaiscript/rhai?rev=ef3df63121d27aacd838f366f2b83fd65f20a1e4#ef3df63121d27aacd838f366f2b83fd65f20a1e4"
 dependencies = [
  "ahash 0.8.11",
  "bitflags 2.6.0",
@@ -4593,8 +4607,7 @@ dependencies = [
 [[package]]
 name = "rhai_codegen"
 version = "2.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a5a11a05ee1ce44058fa3d5961d05194fdbe3ad6b40f904af764d81b86450e6b"
+source = "git+https://github.com/rhaiscript/rhai?rev=ef3df63121d27aacd838f366f2b83fd65f20a1e4#ef3df63121d27aacd838f366f2b83fd65f20a1e4"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -4696,6 +4709,12 @@ version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
 
+[[package]]
+name = "rustc-hash"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "583034fd73374156e66797ed8e5b0d5690409c9226b22d87cb7f19821c05d152"
+
 [[package]]
 name = "rustc_version"
 version = "0.4.0"
@@ -4834,9 +4853,9 @@ checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
 
 [[package]]
 name = "serde"
-version = "1.0.204"
+version = "1.0.209"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bc76f558e0cbb2a839d37354c575f1dc3fdc6546b5be373ba43d95f231bf7c12"
+checksum = "99fce0ffe7310761ca6bf9faf5115afbc19688edd00171d81b1bb1b116c63e09"
 dependencies = [
  "serde_derive",
 ]
@@ -4852,9 +4871,9 @@ dependencies = [
 
 [[package]]
 name = "serde_derive"
-version = "1.0.204"
+version = "1.0.209"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e0cd7e117be63d3c3678776753929474f3b04a43a080c744d6b0ae2a8c28e222"
+checksum = "a5831b979fd7b5439637af1752d535ff49f4860c0f341d1baeb6faf0f4242170"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -5347,7 +5366,7 @@ dependencies = [
  "fancy-regex 0.12.0",
  "lazy_static",
  "parking_lot",
- "rustc-hash",
+ "rustc-hash 1.1.0",
 ]
 
 [[package]]
@@ -6361,7 +6380,7 @@ dependencies = [
 
 [[package]]
 name = "xtask"
-version = "1.10.0"
+version = "1.11.1"
 dependencies = [
  "anyhow",
  "build-info",

Cargo.toml

@@ -22,7 +22,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.10.0"
+version = "1.11.1"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",

README.md

@@ -45,14 +45,14 @@ See the list of all our example apps in our [demos repository](https://github.co
 ## ✨ Features
 - **Hybrid search:** Combine the best of both [semantic](https://www.meilisearch.com/docs/learn/experimental/vector_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) & full-text search to get the most relevant results
 - **Search-as-you-type:** Find & display results in less than 50 milliseconds to provide an intuitive experience
-- **[Typo tolerance](https://www.meilisearch.com/docs/learn/configuration/typo_tolerance?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** get relevant matches even when queries contain typos and misspellings
+- **[Typo tolerance](https://www.meilisearch.com/docs/learn/relevancy/typo_tolerance_settings?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** get relevant matches even when queries contain typos and misspellings
 - **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your users' search experience with custom filters and build a faceted search interface in a few lines of code
 - **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** sort results based on price, date, or pretty much anything else your users need
-- **[Synonym support](https://www.meilisearch.com/docs/learn/configuration/synonyms?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** configure synonyms to include more relevant content in your search results
+- **[Synonym support](https://www.meilisearch.com/docs/learn/relevancy/synonyms?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** configure synonyms to include more relevant content in your search results
 - **[Geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** filter and sort documents based on geographic data
 - **[Extensive language support](https://www.meilisearch.com/docs/learn/what_is_meilisearch/language?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
 - **[Security management](https://www.meilisearch.com/docs/learn/security/master_api_keys?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** control which users can access what data with API keys that allow fine-grained permissions handling
-- **[Multi-Tenancy](https://www.meilisearch.com/docs/learn/security/tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** personalize search results for any number of application tenants
+- **[Multi-Tenancy](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** personalize search results for any number of application tenants
 - **Highly Customizable:** customize Meilisearch to your specific needs or use our out-of-the-box and hassle-free presets
 - **[RESTful API](https://www.meilisearch.com/docs/reference/api/overview?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** integrate Meilisearch in your technical stack with our plugins and SDKs
 - **Easy to install, deploy, and maintain**

dump/src/reader/mod.rs

@@ -255,6 +255,8 @@ pub(crate) mod test {
         }
         "###);
 
+        insta::assert_json_snapshot!(vector_index.settings().unwrap());
+
         {
             let documents: Result<Vec<_>> = vector_index.documents().unwrap().collect();
             let mut documents = documents.unwrap();

dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-5.snap

@@ -1,783 +1,56 @@
 ---
 source: dump/src/reader/mod.rs
-expression: document
+expression: vector_index.settings().unwrap()
 ---
 {
-  "id": "e3",
-  "desc": "overriden vector + map",
-  "_vectors": {
-    "default": [
-      0.2,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1
-    ],
-    "toto": [
-      0.1
-    ]
-  }
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "sort",
+    "exactness"
+  ],
+  "stopWords": [],
+  "nonSeparatorTokens": [],
+  "separatorTokens": [],
+  "dictionary": [],
+  "synonyms": {},
+  "distinctAttribute": null,
+  "proximityPrecision": "byWord",
+  "typoTolerance": {
+    "enabled": true,
+    "minWordSizeForTypos": {
+      "oneTypo": 5,
+      "twoTypos": 9
+    },
+    "disableOnWords": [],
+    "disableOnAttributes": []
+  },
+  "faceting": {
+    "maxValuesPerFacet": 100,
+    "sortFacetValuesBy": {
+      "*": "alpha"
+    }
+  },
+  "pagination": {
+    "maxTotalHits": 1000
+  },
+  "embedders": {
+    "default": {
+      "source": "huggingFace",
+      "model": "BAAI/bge-base-en-v1.5",
+      "revision": "617ca489d9e86b49b8167676d8220688b99db36e",
+      "documentTemplate": "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}"
+    }
+  },
+  "searchCutoffMs": null
 }

dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-9.snap

@@ -0,0 +1,780 @@
+---
+source: dump/src/reader/mod.rs
+expression: document
+---
+{
+  "id": "e0",
+  "desc": "overriden vector",
+  "_vectors": {
+    "default": [
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1
+    ]
+  }
+}

filter-parser/src/condition.rs

@@ -27,6 +27,7 @@ pub enum Condition<'a> {
     LowerThanOrEqual(Token<'a>),
     Between { from: Token<'a>, to: Token<'a> },
     Contains { keyword: Token<'a>, word: Token<'a> },
+    StartsWith { keyword: Token<'a>, word: Token<'a> },
 }
 
 /// condition      = value ("==" | ">" ...) value
@@ -121,6 +122,34 @@ pub fn parse_not_contains(input: Span) -> IResult<FilterCondition> {
     ))
 }
 
+/// starts with        = value "CONTAINS" value
+pub fn parse_starts_with(input: Span) -> IResult<FilterCondition> {
+    let (input, (fid, starts_with, value)) =
+        tuple((parse_value, tag("STARTS WITH"), cut(parse_value)))(input)?;
+    Ok((
+        input,
+        FilterCondition::Condition {
+            fid,
+            op: StartsWith { keyword: Token { span: starts_with, value: None }, word: value },
+        },
+    ))
+}
+
+/// starts with        = value "NOT" WS+ "CONTAINS" value
+pub fn parse_not_starts_with(input: Span) -> IResult<FilterCondition> {
+    let keyword = tuple((tag("NOT"), multispace1, tag("STARTS WITH")));
+    let (input, (fid, (_not, _spaces, starts_with), value)) =
+        tuple((parse_value, keyword, cut(parse_value)))(input)?;
+
+    Ok((
+        input,
+        FilterCondition::Not(Box::new(FilterCondition::Condition {
+            fid,
+            op: StartsWith { keyword: Token { span: starts_with, value: None }, word: value },
+        })),
+    ))
+}
+
 /// to             = value value "TO" WS+ value
 pub fn parse_to(input: Span) -> IResult<FilterCondition> {
     let (input, (key, from, _, _, to)) =

filter-parser/src/error.rs

@@ -146,7 +146,7 @@ impl<'a> Display for Error<'a> {
             }
             ErrorKind::InvalidPrimary => {
                 let text = if input.trim().is_empty() { "but instead got nothing.".to_string() } else { format!("at `{}`.", escaped_input) };
-                writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` {}", text)?
+                writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` {}", text)?
             }
             ErrorKind::InvalidEscapedNumber => {
                 writeln!(f, "Found an invalid escaped sequence number: `{}`.", escaped_input)?

filter-parser/src/lib.rs

@@ -49,7 +49,7 @@ use std::fmt::Debug;
 pub use condition::{parse_condition, parse_to, Condition};
 use condition::{
     parse_contains, parse_exists, parse_is_empty, parse_is_not_empty, parse_is_not_null,
-    parse_is_null, parse_not_contains, parse_not_exists,
+    parse_is_null, parse_not_contains, parse_not_exists, parse_not_starts_with, parse_starts_with,
 };
 use error::{cut_with_err, ExpectedValueKind, NomErrorExt};
 pub use error::{Error, ErrorKind};
@@ -166,7 +166,8 @@ impl<'a> FilterCondition<'a> {
                 | Condition::LowerThan(_)
                 | Condition::LowerThanOrEqual(_)
                 | Condition::Between { .. } => None,
-                Condition::Contains { keyword, word: _ } => Some(keyword),
+                Condition::Contains { keyword, word: _ }
+                | Condition::StartsWith { keyword, word: _ } => Some(keyword),
             },
             FilterCondition::Not(this) => this.use_contains_operator(),
             FilterCondition::Or(seq) | FilterCondition::And(seq) => {
@@ -484,6 +485,8 @@ fn parse_primary(input: Span, depth: usize) -> IResult<FilterCondition> {
         parse_to,
         parse_contains,
         parse_not_contains,
+        parse_starts_with,
+        parse_not_starts_with,
         // the next lines are only for error handling and are written at the end to have the less possible performance impact
         parse_geo,
         parse_geo_distance,
@@ -567,6 +570,7 @@ impl<'a> std::fmt::Display for Condition<'a> {
             Condition::LowerThanOrEqual(token) => write!(f, "<= {token}"),
             Condition::Between { from, to } => write!(f, "{from} TO {to}"),
             Condition::Contains { word, keyword: _ } => write!(f, "CONTAINS {word}"),
+            Condition::StartsWith { word, keyword: _ } => write!(f, "STARTS WITH {word}"),
         }
     }
 }
@@ -680,6 +684,13 @@ pub mod tests {
         insta::assert_snapshot!(p("NOT subscribers NOT CONTAINS 'hello'"), @"{subscribers} CONTAINS {hello}");
         insta::assert_snapshot!(p("subscribers NOT   CONTAINS 'hello'"), @"NOT ({subscribers} CONTAINS {hello})");
 
+        // Test STARTS WITH + NOT STARTS WITH
+        insta::assert_snapshot!(p("subscribers STARTS WITH 'hel'"), @"{subscribers} STARTS WITH {hel}");
+        insta::assert_snapshot!(p("NOT subscribers STARTS WITH 'hel'"), @"NOT ({subscribers} STARTS WITH {hel})");
+        insta::assert_snapshot!(p("subscribers NOT STARTS WITH hel"), @"NOT ({subscribers} STARTS WITH {hel})");
+        insta::assert_snapshot!(p("NOT subscribers NOT STARTS WITH 'hel'"), @"{subscribers} STARTS WITH {hel}");
+        insta::assert_snapshot!(p("subscribers NOT   STARTS WITH 'hel'"), @"NOT ({subscribers} STARTS WITH {hel})");
+
         // Test nested NOT
         insta::assert_snapshot!(p("NOT NOT NOT NOT x = 5"), @"{x} = {5}");
         insta::assert_snapshot!(p("NOT NOT (NOT NOT x = 5)"), @"{x} = {5}");
@@ -751,7 +762,7 @@ pub mod tests {
         "###);
 
         insta::assert_snapshot!(p("'OR'"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `\'OR\'`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `\'OR\'`.
         1:5 'OR'
         "###);
 
@@ -761,12 +772,12 @@ pub mod tests {
         "###);
 
         insta::assert_snapshot!(p("channel Ponce"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `channel Ponce`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `channel Ponce`.
         1:14 channel Ponce
         "###);
 
         insta::assert_snapshot!(p("channel = Ponce OR"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` but instead got nothing.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` but instead got nothing.
         19:19 channel = Ponce OR
         "###);
 
@@ -851,12 +862,12 @@ pub mod tests {
         "###);
 
         insta::assert_snapshot!(p("colour NOT EXIST"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `colour NOT EXIST`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `colour NOT EXIST`.
         1:17 colour NOT EXIST
         "###);
 
         insta::assert_snapshot!(p("subscribers 100 TO1000"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `subscribers 100 TO1000`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `subscribers 100 TO1000`.
         1:23 subscribers 100 TO1000
         "###);
 
@@ -919,35 +930,35 @@ pub mod tests {
         "###);
 
         insta::assert_snapshot!(p(r#"value NULL"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value NULL`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value NULL`.
         1:11 value NULL
         "###);
         insta::assert_snapshot!(p(r#"value NOT NULL"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value NOT NULL`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value NOT NULL`.
         1:15 value NOT NULL
         "###);
         insta::assert_snapshot!(p(r#"value EMPTY"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value EMPTY`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value EMPTY`.
         1:12 value EMPTY
         "###);
         insta::assert_snapshot!(p(r#"value NOT EMPTY"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value NOT EMPTY`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value NOT EMPTY`.
         1:16 value NOT EMPTY
         "###);
         insta::assert_snapshot!(p(r#"value IS"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value IS`.
         1:9 value IS
         "###);
         insta::assert_snapshot!(p(r#"value IS NOT"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT`.
         1:13 value IS NOT
         "###);
         insta::assert_snapshot!(p(r#"value IS EXISTS"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS EXISTS`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value IS EXISTS`.
         1:16 value IS EXISTS
         "###);
         insta::assert_snapshot!(p(r#"value IS NOT EXISTS"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT EXISTS`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT EXISTS`.
         1:20 value IS NOT EXISTS
         "###);
     }

filter-parser/src/value.rs

@@ -212,6 +212,8 @@ fn is_keyword(s: &str) -> bool {
             | "NULL"
             | "EMPTY"
             | "CONTAINS"
+            | "STARTS"
+            | "WITH"
             | "_geoRadius"
             | "_geoBoundingBox"
     )

index-scheduler/Cargo.toml

@@ -40,7 +40,7 @@ ureq = "2.10.0"
 uuid = { version = "1.10.0", features = ["serde", "v4"] }
 
 [dev-dependencies]
-arroy = "0.4.0"
+arroy = "0.5.0"
 big_s = "1.0.2"
 crossbeam = "0.8.4"
 insta = { version = "1.39.0", features = ["json", "redactions"] }

index-scheduler/src/autobatcher.rs

@@ -25,8 +25,9 @@ enum AutobatchKind {
         primary_key: Option<String>,
     },
     DocumentEdition,
-    DocumentDeletion,
-    DocumentDeletionByFilter,
+    DocumentDeletion {
+        by_filter: bool,
+    },
     DocumentClear,
     Settings {
         allow_index_creation: bool,
@@ -65,10 +66,12 @@ impl From<KindWithContent> for AutobatchKind {
                 ..
             } => AutobatchKind::DocumentImport { method, allow_index_creation, primary_key },
             KindWithContent::DocumentEdition { .. } => AutobatchKind::DocumentEdition,
-            KindWithContent::DocumentDeletion { .. } => AutobatchKind::DocumentDeletion,
+            KindWithContent::DocumentDeletion { .. } => {
+                AutobatchKind::DocumentDeletion { by_filter: false }
+            }
             KindWithContent::DocumentClear { .. } => AutobatchKind::DocumentClear,
             KindWithContent::DocumentDeletionByFilter { .. } => {
-                AutobatchKind::DocumentDeletionByFilter
+                AutobatchKind::DocumentDeletion { by_filter: true }
             }
             KindWithContent::SettingsUpdate { allow_index_creation, is_deletion, .. } => {
                 AutobatchKind::Settings {
@@ -105,9 +108,7 @@ pub enum BatchKind {
     },
     DocumentDeletion {
         deletion_ids: Vec<TaskId>,
-    },
-    DocumentDeletionByFilter {
-        id: TaskId,
+        includes_by_filter: bool,
     },
     ClearAndSettings {
         other: Vec<TaskId>,
@@ -205,12 +206,13 @@ impl BatchKind {
                 allow_index_creation,
             ),
             K::DocumentEdition => (Break(BatchKind::DocumentEdition { id: task_id }), false),
-            K::DocumentDeletion => {
-                (Continue(BatchKind::DocumentDeletion { deletion_ids: vec![task_id] }), false)
-            }
-            K::DocumentDeletionByFilter => {
-                (Break(BatchKind::DocumentDeletionByFilter { id: task_id }), false)
-            }
+            K::DocumentDeletion { by_filter: includes_by_filter } => (
+                Continue(BatchKind::DocumentDeletion {
+                    deletion_ids: vec![task_id],
+                    includes_by_filter,
+                }),
+                false,
+            ),
             K::Settings { allow_index_creation } => (
                 Continue(BatchKind::Settings { allow_index_creation, settings_ids: vec![task_id] }),
                 allow_index_creation,
@@ -228,7 +230,7 @@ impl BatchKind {
 
         match (self, kind) {
             // We don't batch any of these operations
-            (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentEdition | K::DocumentDeletionByFilter) => Break(this),
+            (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentEdition) => Break(this),
             // We must not batch tasks that don't have the same index creation rights if the index doesn't already exists.
             (this, kind) if !index_already_exists && this.allow_index_creation() == Some(false) && kind.allow_index_creation() == Some(true) => {
                 Break(this)
@@ -264,7 +266,7 @@ impl BatchKind {
             // The index deletion can batch with everything but must stop after
             (
                 BatchKind::DocumentClear { mut ids }
-                | BatchKind::DocumentDeletion { deletion_ids: mut ids }
+                | BatchKind::DocumentDeletion { deletion_ids: mut ids, includes_by_filter: _ }
                 | BatchKind::DocumentOperation { method: _, allow_index_creation: _, primary_key: _, operation_ids: mut ids }
                 | BatchKind::Settings { allow_index_creation: _, settings_ids: mut ids },
                 K::IndexDeletion,
@@ -284,7 +286,7 @@ impl BatchKind {
 
             (
                 BatchKind::DocumentClear { mut ids },
-                K::DocumentClear | K::DocumentDeletion,
+                K::DocumentClear | K::DocumentDeletion { by_filter: _ },
             ) => {
                 ids.push(id);
                 Continue(BatchKind::DocumentClear { ids })
@@ -328,7 +330,7 @@ impl BatchKind {
             }
             (
                 BatchKind::DocumentOperation { method, allow_index_creation, primary_key, mut operation_ids },
-                K::DocumentDeletion,
+                K::DocumentDeletion { by_filter: false },
             ) => {
                 operation_ids.push(id);
 
@@ -339,6 +341,13 @@ impl BatchKind {
                     operation_ids,
                 })
             }
+            // We can't batch a document operation with a delete by filter
+            (
+                this @ BatchKind::DocumentOperation { .. },
+                K::DocumentDeletion { by_filter: true },
+            ) => {
+                Break(this)
+            }
             // but we can't autobatch documents if it's not the same kind
             // this match branch MUST be AFTER the previous one
             (
@@ -357,13 +366,18 @@ impl BatchKind {
                 operation_ids,
             }),
 
-            (BatchKind::DocumentDeletion { mut deletion_ids }, K::DocumentClear) => {
+            (BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: _ }, K::DocumentClear) => {
                 deletion_ids.push(id);
                 Continue(BatchKind::DocumentClear { ids: deletion_ids })
             }
+            // we can't autobatch the deletion and import if the document deletion contained a filter
+            (
+                this @ BatchKind::DocumentDeletion { deletion_ids: _, includes_by_filter: true },
+                K::DocumentImport { .. }
+            ) => Break(this),
             // we can autobatch the deletion and import if the index already exists
             (
-                BatchKind::DocumentDeletion { mut deletion_ids },
+                BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: false },
                 K::DocumentImport { method, allow_index_creation, primary_key }
             ) if index_already_exists => {
                 deletion_ids.push(id);
@@ -377,7 +391,7 @@ impl BatchKind {
             }
             // we can autobatch the deletion and import if both can't create an index
             (
-                BatchKind::DocumentDeletion { mut deletion_ids },
+                BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: false },
                 K::DocumentImport { method, allow_index_creation, primary_key }
             ) if !allow_index_creation => {
                 deletion_ids.push(id);
@@ -396,9 +410,9 @@ impl BatchKind {
             ) => {
                 Break(this)
             }
-            (BatchKind::DocumentDeletion { mut deletion_ids }, K::DocumentDeletion) => {
+            (BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter }, K::DocumentDeletion { by_filter }) => {
                 deletion_ids.push(id);
-                Continue(BatchKind::DocumentDeletion { deletion_ids })
+                Continue(BatchKind::DocumentDeletion { deletion_ids, includes_by_filter: includes_by_filter | by_filter })
             }
             (this @ BatchKind::DocumentDeletion { .. }, K::Settings { .. }) => Break(this),
 
@@ -412,7 +426,7 @@ impl BatchKind {
             }),
             (
                 this @ BatchKind::Settings { .. },
-                K::DocumentImport { .. } | K::DocumentDeletion,
+                K::DocumentImport { .. } | K::DocumentDeletion { .. },
             ) => Break(this),
             (
                 BatchKind::Settings { mut settings_ids, allow_index_creation },
@@ -443,7 +457,7 @@ impl BatchKind {
                     settings_ids,
                     allow_index_creation,
                 },
-                K::DocumentDeletion,
+                K::DocumentDeletion { .. },
             ) => {
                 other.push(id);
                 Continue(BatchKind::ClearAndSettings {
@@ -505,7 +519,7 @@ impl BatchKind {
             // this MUST be AFTER the two previous branch
             (
                 this @ BatchKind::SettingsAndDocumentOperation { .. },
-                K::DocumentDeletion | K::DocumentImport { .. },
+                K::DocumentDeletion { .. } | K::DocumentImport { .. },
             ) => Break(this),
             (
                 BatchKind::SettingsAndDocumentOperation { mut settings_ids, method, allow_index_creation,primary_key, operation_ids },
@@ -525,8 +539,7 @@ impl BatchKind {
                 | BatchKind::IndexDeletion { .. }
                 | BatchKind::IndexUpdate { .. }
                 | BatchKind::IndexSwap { .. }
-                | BatchKind::DocumentEdition { .. }
-                | BatchKind::DocumentDeletionByFilter { .. },
+                | BatchKind::DocumentEdition { .. },
                 _,
             ) => {
                 unreachable!()
@@ -616,6 +629,13 @@ mod tests {
         }
     }
 
+    fn doc_del_fil() -> KindWithContent {
+        KindWithContent::DocumentDeletionByFilter {
+            index_uid: String::from("doggo"),
+            filter_expr: serde_json::json!("cuteness > 100"),
+        }
+    }
+
     fn doc_clr() -> KindWithContent {
         KindWithContent::DocumentClear { index_uid: String::from("doggo") }
     }
@@ -676,10 +696,16 @@ mod tests {
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false))");
 
         // we can autobatch one or multiple DocumentDeletion together
-        debug_snapshot!(autobatch_from(true, None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2] }, false))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, false))");
+
+        // we can autobatch one or multiple DocumentDeletionByFilter together
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_del_fil(), doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_del_fil(), doc_del_fil(), doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: true }, false))");
 
         // we can autobatch one or multiple Settings together
         debug_snapshot!(autobatch_from(true, None, [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true))");
@@ -722,25 +748,63 @@ mod tests {
         debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
         debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
         debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
+
+        // But we can't autobatch document addition with document deletion by filter
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        // And the other way around
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
     }
 
     #[test]
     fn simple_document_operation_dont_autobatch_with_other() {
-        // addition, updates and deletion can't batch together
+        // addition, updates and deletion by filter can't batch together
         debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
         debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
 
         debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_create()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
         debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_create()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
 
         debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
         debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
 
         debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
         debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
     }
 
     #[test]
@@ -807,6 +871,7 @@ mod tests {
         debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
         debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
         debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_del_fil()]), @"Some((IndexDeletion { ids: [0] }, false))");
         debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))");
         debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
         debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
@@ -816,6 +881,7 @@ mod tests {
         debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_del_fil()]), @"Some((IndexDeletion { ids: [0] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
@@ -827,6 +893,7 @@ mod tests {
         debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
         debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
         debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
         debug_snapshot!(autobatch_from(true, None, [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
         debug_snapshot!(autobatch_from(true, None, [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
         debug_snapshot!(autobatch_from(true, None, [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
@@ -836,6 +903,7 @@ mod tests {
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_del_fil(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
         debug_snapshot!(autobatch_from(false,None,  [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
@@ -901,10 +969,10 @@ mod tests {
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
 
         // batch deletion and addition
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
     }
 
     #[test]

index-scheduler/src/batch.rs

@@ -110,9 +110,9 @@ pub(crate) enum IndexOperation {
         index_uid: String,
         task: Task,
     },
-    IndexDocumentDeletionByFilter {
+    DocumentDeletion {
         index_uid: String,
-        task: Task,
+        tasks: Vec<Task>,
     },
     DocumentClear {
         index_uid: String,
@@ -165,11 +165,11 @@ impl Batch {
             Batch::IndexOperation { op, .. } => match op {
                 IndexOperation::DocumentOperation { tasks, .. }
                 | IndexOperation::Settings { tasks, .. }
+                | IndexOperation::DocumentDeletion { tasks, .. }
                 | IndexOperation::DocumentClear { tasks, .. } => {
                     RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
                 }
-                IndexOperation::DocumentEdition { task, .. }
-                | IndexOperation::IndexDocumentDeletionByFilter { task, .. } => {
+                IndexOperation::DocumentEdition { task, .. } => {
                     RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
                 }
                 IndexOperation::SettingsAndDocumentOperation {
@@ -234,7 +234,7 @@ impl IndexOperation {
         match self {
             IndexOperation::DocumentOperation { index_uid, .. }
             | IndexOperation::DocumentEdition { index_uid, .. }
-            | IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
+            | IndexOperation::DocumentDeletion { index_uid, .. }
             | IndexOperation::DocumentClear { index_uid, .. }
             | IndexOperation::Settings { index_uid, .. }
             | IndexOperation::DocumentClearAndSetting { index_uid, .. }
@@ -252,8 +252,8 @@ impl fmt::Display for IndexOperation {
             IndexOperation::DocumentEdition { .. } => {
                 f.write_str("IndexOperation::DocumentEdition")
             }
-            IndexOperation::IndexDocumentDeletionByFilter { .. } => {
-                f.write_str("IndexOperation::IndexDocumentDeletionByFilter")
+            IndexOperation::DocumentDeletion { .. } => {
+                f.write_str("IndexOperation::DocumentDeletion")
             }
             IndexOperation::DocumentClear { .. } => f.write_str("IndexOperation::DocumentClear"),
             IndexOperation::Settings { .. } => f.write_str("IndexOperation::Settings"),
@@ -289,21 +289,6 @@ impl IndexScheduler {
                 },
                 must_create_index,
             })),
-            BatchKind::DocumentDeletionByFilter { id } => {
-                let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
-                match &task.kind {
-                    KindWithContent::DocumentDeletionByFilter { index_uid, .. } => {
-                        Ok(Some(Batch::IndexOperation {
-                            op: IndexOperation::IndexDocumentDeletionByFilter {
-                                index_uid: index_uid.clone(),
-                                task,
-                            },
-                            must_create_index: false,
-                        }))
-                    }
-                    _ => unreachable!(),
-                }
-            }
             BatchKind::DocumentEdition { id } => {
                 let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
                 match &task.kind {
@@ -366,30 +351,11 @@ impl IndexScheduler {
                     must_create_index,
                 }))
             }
-            BatchKind::DocumentDeletion { deletion_ids } => {
+            BatchKind::DocumentDeletion { deletion_ids, includes_by_filter: _ } => {
                 let tasks = self.get_existing_tasks(rtxn, deletion_ids)?;
 
-                let mut operations = Vec::with_capacity(tasks.len());
-                let mut documents_counts = Vec::with_capacity(tasks.len());
-                for task in &tasks {
-                    match task.kind {
-                        KindWithContent::DocumentDeletion { ref documents_ids, .. } => {
-                            operations.push(DocumentOperation::Delete(documents_ids.clone()));
-                            documents_counts.push(documents_ids.len() as u64);
-                        }
-                        _ => unreachable!(),
-                    }
-                }
-
                 Ok(Some(Batch::IndexOperation {
-                    op: IndexOperation::DocumentOperation {
-                        index_uid,
-                        primary_key: None,
-                        method: IndexDocumentsMethod::ReplaceDocuments,
-                        documents_counts,
-                        operations,
-                        tasks,
-                    },
+                    op: IndexOperation::DocumentDeletion { index_uid, tasks },
                     must_create_index,
                 }))
             }
@@ -1439,7 +1405,7 @@ impl IndexScheduler {
                 {
                     (original_filter, context, function)
                 } else {
-                    // In the case of a `documentDeleteByFilter` the details MUST be set
+                    // In the case of a `documentEdition` the details MUST be set
                     unreachable!();
                 };
 
@@ -1469,52 +1435,102 @@ impl IndexScheduler {
 
                 Ok(vec![task])
             }
-            IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
-                let filter =
-                    if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
-                        &task.kind
-                    {
-                        filter_expr
-                    } else {
-                        unreachable!()
-                    };
-                let deleted_documents = delete_document_by_filter(
-                    index_wtxn,
-                    filter,
-                    self.index_mapper.indexer_config(),
-                    self.must_stop_processing.clone(),
-                    index,
-                );
-                let original_filter = if let Some(Details::DocumentDeletionByFilter {
-                    original_filter,
-                    deleted_documents: _,
-                }) = task.details
-                {
-                    original_filter
-                } else {
-                    // In the case of a `documentDeleteByFilter` the details MUST be set
-                    unreachable!();
-                };
+            IndexOperation::DocumentDeletion { mut tasks, index_uid: _ } => {
+                let mut to_delete = RoaringBitmap::new();
+                let external_documents_ids = index.external_documents_ids();
 
-                match deleted_documents {
-                    Ok(deleted_documents) => {
-                        task.status = Status::Succeeded;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(deleted_documents),
-                        });
-                    }
-                    Err(e) => {
-                        task.status = Status::Failed;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(0),
-                        });
-                        task.error = Some(e.into());
+                for task in tasks.iter_mut() {
+                    let before = to_delete.len();
+                    task.status = Status::Succeeded;
+
+                    match &task.kind {
+                        KindWithContent::DocumentDeletion { index_uid: _, documents_ids } => {
+                            for id in documents_ids {
+                                if let Some(id) = external_documents_ids.get(index_wtxn, id)? {
+                                    to_delete.insert(id);
+                                }
+                            }
+                            let will_be_removed = to_delete.len() - before;
+                            task.details = Some(Details::DocumentDeletion {
+                                provided_ids: documents_ids.len(),
+                                deleted_documents: Some(will_be_removed),
+                            });
+                        }
+                        KindWithContent::DocumentDeletionByFilter { index_uid: _, filter_expr } => {
+                            let before = to_delete.len();
+                            let filter = match Filter::from_json(filter_expr) {
+                                Ok(filter) => filter,
+                                Err(err) => {
+                                    // theorically, this should be catched by deserr before reaching the index-scheduler and cannot happens
+                                    task.status = Status::Failed;
+                                    task.error = match err {
+                                        milli::Error::UserError(
+                                            milli::UserError::InvalidFilterExpression { .. },
+                                        ) => Some(
+                                            Error::from(err)
+                                                .with_custom_error_code(Code::InvalidDocumentFilter)
+                                                .into(),
+                                        ),
+                                        e => Some(e.into()),
+                                    };
+                                    None
+                                }
+                            };
+                            if let Some(filter) = filter {
+                                let candidates =
+                                    filter.evaluate(index_wtxn, index).map_err(|err| match err {
+                                        milli::Error::UserError(
+                                            milli::UserError::InvalidFilter(_),
+                                        ) => Error::from(err)
+                                            .with_custom_error_code(Code::InvalidDocumentFilter),
+                                        e => e.into(),
+                                    });
+                                match candidates {
+                                    Ok(candidates) => to_delete |= candidates,
+                                    Err(err) => {
+                                        task.status = Status::Failed;
+                                        task.error = Some(err.into());
+                                    }
+                                };
+                            }
+                            let will_be_removed = to_delete.len() - before;
+                            if let Some(Details::DocumentDeletionByFilter {
+                                original_filter: _,
+                                deleted_documents,
+                            }) = &mut task.details
+                            {
+                                *deleted_documents = Some(will_be_removed);
+                            } else {
+                                // In the case of a `documentDeleteByFilter` the details MUST be set
+                                unreachable!()
+                            }
+                        }
+                        _ => unreachable!(),
                     }
                 }
 
-                Ok(vec![task])
+                let config = IndexDocumentsConfig {
+                    update_method: IndexDocumentsMethod::ReplaceDocuments,
+                    ..Default::default()
+                };
+
+                let must_stop_processing = self.must_stop_processing.clone();
+                let mut builder = milli::update::IndexDocuments::new(
+                    index_wtxn,
+                    index,
+                    self.index_mapper.indexer_config(),
+                    config,
+                    |indexing_step| tracing::debug!(update = ?indexing_step),
+                    || must_stop_processing.get(),
+                )?;
+
+                let (new_builder, _count) =
+                    builder.remove_documents_from_db_no_batch(&to_delete)?;
+                builder = new_builder;
+
+                let _ = builder.execute()?;
+
+                Ok(tasks)
             }
             IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
                 let indexer_config = self.index_mapper.indexer_config();
@@ -1718,46 +1734,6 @@ impl IndexScheduler {
     }
 }
 
-fn delete_document_by_filter<'a>(
-    wtxn: &mut RwTxn<'a>,
-    filter: &serde_json::Value,
-    indexer_config: &IndexerConfig,
-    must_stop_processing: MustStopProcessing,
-    index: &'a Index,
-) -> Result<u64> {
-    let filter = Filter::from_json(filter)?;
-    Ok(if let Some(filter) = filter {
-        let candidates = filter.evaluate(wtxn, index).map_err(|err| match err {
-            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
-                Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
-            }
-            e => e.into(),
-        })?;
-
-        let config = IndexDocumentsConfig {
-            update_method: IndexDocumentsMethod::ReplaceDocuments,
-            ..Default::default()
-        };
-
-        let mut builder = milli::update::IndexDocuments::new(
-            wtxn,
-            index,
-            indexer_config,
-            config,
-            |indexing_step| tracing::debug!(update = ?indexing_step),
-            || must_stop_processing.get(),
-        )?;
-
-        let (new_builder, count) = builder.remove_documents_from_db_no_batch(&candidates)?;
-        builder = new_builder;
-
-        let _ = builder.execute()?;
-        count
-    } else {
-        0
-    })
-}
-
 fn edit_documents_by_function<'a>(
     wtxn: &mut RwTxn<'a>,
     filter: &Option<serde_json::Value>,

index-scheduler/src/features.rs

@@ -87,7 +87,7 @@ impl RoFeatures {
             Ok(())
         } else {
             Err(FeatureNotEnabledError {
-                disabled_action: "Using `CONTAINS` in a filter",
+                disabled_action: "Using `CONTAINS` or `STARTS WITH` in a filter",
                 feature: "contains filter",
                 issue_link: "https://github.com/orgs/meilisearch/discussions/763",
             }

index-scheduler/src/index_mapper/mod.rs

@@ -108,8 +108,10 @@ pub struct IndexStats {
     /// Association of every field name with the number of times it occurs in the documents.
     pub field_distribution: FieldDistribution,
     /// Creation date of the index.
+    #[serde(with = "time::serde::rfc3339")]
     pub created_at: OffsetDateTime,
     /// Date of the last update of the index.
+    #[serde(with = "time::serde::rfc3339")]
     pub updated_at: OffsetDateTime,
 }
 

index-scheduler/src/insta_snapshot.rs

@@ -11,6 +11,9 @@ use crate::index_mapper::IndexMapper;
 use crate::{IndexScheduler, Kind, Status, BEI128};
 
 pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
+    // Since we'll snapshot the index right afterward, we don't need to ensure it's internally consistent for every run.
+    // We can only do it for the release run, where the function runs way faster.
+    #[cfg(not(debug_assertions))]
     scheduler.assert_internally_consistent();
 
     let IndexScheduler {

index-scheduler/src/lib.rs

@@ -35,6 +35,7 @@ pub type TaskId = u32;
 use std::collections::{BTreeMap, HashMap};
 use std::io::{self, BufReader, Read};
 use std::ops::{Bound, RangeBounds};
+use std::panic::{catch_unwind, AssertUnwindSafe};
 use std::path::{Path, PathBuf};
 use std::sync::atomic::Ordering::{self, Relaxed};
 use std::sync::atomic::{AtomicBool, AtomicU32};
@@ -612,19 +613,24 @@ impl IndexScheduler {
                 #[cfg(test)]
                 run.breakpoint(Breakpoint::Init);
 
-                run.wake_up.wait();
+                run.wake_up.wait_timeout(std::time::Duration::from_secs(60));
 
                 loop {
-                    match run.tick() {
-                        Ok(TickOutcome::TickAgain(_)) => (),
-                        Ok(TickOutcome::WaitForSignal) => run.wake_up.wait(),
-                        Err(e) => {
+                    let ret = catch_unwind(AssertUnwindSafe(|| run.tick()));
+                    match ret {
+                        Ok(Ok(TickOutcome::TickAgain(_))) => (),
+                        Ok(Ok(TickOutcome::WaitForSignal)) => run.wake_up.wait(),
+                        Ok(Err(e)) => {
                             tracing::error!("{e}");
                             // Wait one second when an irrecoverable error occurs.
                             if !e.is_recoverable() {
                                 std::thread::sleep(Duration::from_secs(1));
                             }
                         }
+                        Err(_panic) => {
+                            tracing::error!("Internal error: Unexpected panic in the `IndexScheduler::run` method.");
+
+                        }
                     }
                 }
             })
@@ -1257,7 +1263,7 @@ impl IndexScheduler {
                     #[cfg(test)]
                     self.maybe_fail(tests::FailureLocation::UpdatingTaskAfterProcessBatchFailure)?;
 
-                    tracing::info!("Batch failed {}", error);
+                    tracing::error!("Batch failed {}", error);
 
                     self.update_task(&mut wtxn, &task)
                         .map_err(|e| Error::TaskDatabaseUpdate(Box::new(e)))?;
@@ -1471,7 +1477,7 @@ impl IndexScheduler {
             .map(
                 |IndexEmbeddingConfig {
                      name,
-                     config: milli::vector::EmbeddingConfig { embedder_options, prompt },
+                     config: milli::vector::EmbeddingConfig { embedder_options, prompt, quantized },
                      ..
                  }| {
                     let prompt =
@@ -1480,7 +1486,10 @@ impl IndexScheduler {
                     {
                         let embedders = self.embedders.read().unwrap();
                         if let Some(embedder) = embedders.get(&embedder_options) {
-                            return Ok((name, (embedder.clone(), prompt)));
+                            return Ok((
+                                name,
+                                (embedder.clone(), prompt, quantized.unwrap_or_default()),
+                            ));
                         }
                     }
 
@@ -1494,7 +1503,7 @@ impl IndexScheduler {
                         let mut embedders = self.embedders.write().unwrap();
                         embedders.insert(embedder_options, embedder.clone());
                     }
-                    Ok((name, (embedder, prompt)))
+                    Ok((name, (embedder, prompt, quantized.unwrap_or_default())))
                 },
             )
             .collect();
@@ -1758,6 +1767,7 @@ mod tests {
     use crossbeam::channel::RecvTimeoutError;
     use file_store::File;
     use insta::assert_json_snapshot;
+    use maplit::btreeset;
     use meili_snap::{json_string, snapshot};
     use meilisearch_auth::AuthFilter;
     use meilisearch_types::document_formats::DocumentFormatError;
@@ -2000,11 +2010,13 @@ mod tests {
         fn advance_till(&mut self, breakpoints: impl IntoIterator<Item = Breakpoint>) {
             for breakpoint in breakpoints {
                 let b = self.advance();
-                let state = snapshot_index_scheduler(&self.index_scheduler);
                 assert_eq!(
-                    b, breakpoint,
-                    "Was expecting the breakpoint `{:?}` but instead got `{:?}`.\n{state}",
-                    breakpoint, b
+                    b,
+                    breakpoint,
+                    "Was expecting the breakpoint `{:?}` but instead got `{:?}`.\n{}",
+                    breakpoint,
+                    b,
+                    snapshot_index_scheduler(&self.index_scheduler)
                 );
             }
         }
@@ -2028,7 +2040,6 @@ mod tests {
         // Wait for one successful batch.
         #[track_caller]
         fn advance_one_successful_batch(&mut self) {
-            self.index_scheduler.assert_internally_consistent();
             self.advance_till([Start, BatchCreated]);
             loop {
                 match self.advance() {
@@ -2047,7 +2058,6 @@ mod tests {
             }
 
             self.advance_till([AfterProcessing]);
-            self.index_scheduler.assert_internally_consistent();
         }
 
         // Wait for one failed batch.
@@ -2547,6 +2557,117 @@ mod tests {
         snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents");
     }
 
+    #[test]
+    fn fail_in_process_batch_for_document_deletion() {
+        let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
+
+        use meilisearch_types::settings::{Settings, Unchecked};
+        let mut new_settings: Box<Settings<Unchecked>> = Box::default();
+        new_settings.filterable_attributes = Setting::Set(btreeset!(S("catto")));
+
+        index_scheduler
+            .register(
+                KindWithContent::SettingsUpdate {
+                    index_uid: S("doggos"),
+                    new_settings,
+                    is_deletion: false,
+                    allow_index_creation: true,
+                },
+                None,
+                false,
+            )
+            .unwrap();
+
+        let content = r#"[
+            { "id": 1, "doggo": "jean bob" },
+            { "id": 2, "catto": "jorts" },
+            { "id": 3, "doggo": "bork" }
+        ]"#;
+
+        let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap();
+        let documents_count = read_json(content.as_bytes(), &mut file).unwrap();
+        file.persist().unwrap();
+        index_scheduler
+            .register(
+                KindWithContent::DocumentAdditionOrUpdate {
+                    index_uid: S("doggos"),
+                    primary_key: Some(S("id")),
+                    method: ReplaceDocuments,
+                    content_file: uuid,
+                    documents_count,
+                    allow_index_creation: true,
+                },
+                None,
+                false,
+            )
+            .unwrap();
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_setting_and_document_addition");
+
+        handle.advance_one_successful_batch();
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_adding_the_settings");
+        handle.advance_one_successful_batch();
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_adding_the_documents");
+
+        index_scheduler
+            .register(
+                KindWithContent::DocumentDeletion {
+                    index_uid: S("doggos"),
+                    documents_ids: vec![S("1")],
+                },
+                None,
+                false,
+            )
+            .unwrap();
+        // This one should not be catched by Meilisearch but it's still nice to handle it because if one day we break the filters it could happens
+        index_scheduler
+            .register(
+                KindWithContent::DocumentDeletionByFilter {
+                    index_uid: S("doggos"),
+                    filter_expr: serde_json::json!(true),
+                },
+                None,
+                false,
+            )
+            .unwrap();
+        // Should fail because the ids are not filterable
+        index_scheduler
+            .register(
+                KindWithContent::DocumentDeletionByFilter {
+                    index_uid: S("doggos"),
+                    filter_expr: serde_json::json!("id = 2"),
+                },
+                None,
+                false,
+            )
+            .unwrap();
+        index_scheduler
+            .register(
+                KindWithContent::DocumentDeletionByFilter {
+                    index_uid: S("doggos"),
+                    filter_expr: serde_json::json!("catto EXISTS"),
+                },
+                None,
+                false,
+            )
+            .unwrap();
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_document_deletions");
+
+        // Everything should be batched together
+        handle.advance_one_successful_batch();
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_removing_the_documents");
+
+        let index = index_scheduler.index("doggos").unwrap();
+        let rtxn = index.read_txn().unwrap();
+        let field_ids_map = index.fields_ids_map(&rtxn).unwrap();
+        let field_ids = field_ids_map.ids().collect::<Vec<_>>();
+        let documents = index
+            .all_documents(&rtxn)
+            .unwrap()
+            .map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap())
+            .collect::<Vec<_>>();
+        snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents_remaining_should_only_be_bork");
+    }
+
     #[test]
     fn do_not_batch_task_of_different_indexes() {
         let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
@@ -5079,10 +5200,11 @@ mod tests {
             let simple_hf_name = name.clone();
 
             let configs = index_scheduler.embedders(configs).unwrap();
-            let (hf_embedder, _) = configs.get(&simple_hf_name).unwrap();
-            let beagle_embed = hf_embedder.embed_one(S("Intel the beagle best doggo")).unwrap();
-            let lab_embed = hf_embedder.embed_one(S("Max the lab best doggo")).unwrap();
-            let patou_embed = hf_embedder.embed_one(S("kefir the patou best doggo")).unwrap();
+            let (hf_embedder, _, _) = configs.get(&simple_hf_name).unwrap();
+            let beagle_embed =
+                hf_embedder.embed_one(S("Intel the beagle best doggo"), None).unwrap();
+            let lab_embed = hf_embedder.embed_one(S("Max the lab best doggo"), None).unwrap();
+            let patou_embed = hf_embedder.embed_one(S("kefir the patou best doggo"), None).unwrap();
             (fakerest_name, simple_hf_name, beagle_embed, lab_embed, patou_embed)
         };
 
@@ -5397,7 +5519,11 @@ mod tests {
                     ),
                     prompt: PromptData {
                         template: "{{doc.doggo}}",
+                        max_bytes: Some(
+                            400,
+                        ),
                     },
+                    quantized: None,
                 },
                 user_provided: RoaringBitmap<[1, 2]>,
             },
@@ -5410,28 +5536,8 @@ mod tests {
 
         // the document with the id 3 should keep its original embedding
         let docid = index.external_documents_ids.get(&rtxn, "3").unwrap().unwrap();
-        let mut embeddings = Vec::new();
-
-        'vectors: for i in 0..=u8::MAX {
-            let reader = arroy::Reader::open(&rtxn, i as u16, index.vector_arroy)
-                .map(Some)
-                .or_else(|e| match e {
-                    arroy::Error::MissingMetadata(_) => Ok(None),
-                    e => Err(e),
-                })
-                .transpose();
-
-            let Some(reader) = reader else {
-                break 'vectors;
-            };
-
-            let embedding = reader.unwrap().item_vector(&rtxn, docid).unwrap();
-            if let Some(embedding) = embedding {
-                embeddings.push(embedding)
-            } else {
-                break 'vectors;
-            }
-        }
+        let embeddings = index.embeddings(&rtxn, docid).unwrap();
+        let embeddings = &embeddings["my_doggo_embedder"];
 
         snapshot!(embeddings.len(), @"1");
         assert!(embeddings[0].iter().all(|i| *i == 3.0), "{:?}", embeddings[0]);
@@ -5611,8 +5717,12 @@ mod tests {
                         },
                     ),
                     prompt: PromptData {
-                        template: "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}",
+                        template: "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
+                        max_bytes: Some(
+                            400,
+                        ),
                     },
+                    quantized: None,
                 },
                 user_provided: RoaringBitmap<[0]>,
             },
@@ -5651,8 +5761,12 @@ mod tests {
                         },
                     ),
                     prompt: PromptData {
-                        template: "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}",
+                        template: "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
+                        max_bytes: Some(
+                            400,
+                        ),
                     },
+                    quantized: None,
                 },
                 user_provided: RoaringBitmap<[]>,
             },

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_adding_the_documents.snap

@@ -0,0 +1,44 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued []
+succeeded [0,1,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 3, field_distribution: {"catto": 1, "doggo": 2, "id": 3} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_adding_the_settings.snap

@@ -0,0 +1,43 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued [1,]
+succeeded [0,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 0, field_distribution: {} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### File Store:
+00000000-0000-0000-0000-000000000000
+
+----------------------------------------------------------------------

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_adding_the_settings_and_documents.snap

@@ -0,0 +1,43 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued [1,]
+succeeded [0,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 0, field_distribution: {} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### File Store:
+00000000-0000-0000-0000-000000000000
+
+----------------------------------------------------------------------

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_removing_the_documents.snap

@@ -0,0 +1,56 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+2 {uid: 2, status: succeeded, details: { received_document_ids: 1, deleted_documents: Some(1) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
+3 {uid: 3, status: failed, error: ResponseError { code: 200, message: "Invalid type for filter subexpression: expected: String, Array, found: true.", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: true, deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
+4 {uid: 4, status: failed, error: ResponseError { code: 200, message: "Attribute `id` is not filterable. Available filterable attributes are: `catto`.\n1:3 id = 2", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: "id = 2", deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
+5 {uid: 5, status: succeeded, details: { original_filter: "catto EXISTS", deleted_documents: Some(1) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
+----------------------------------------------------------------------
+### Status:
+enqueued []
+succeeded [0,1,2,5,]
+failed [3,4,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"documentDeletion" [2,3,4,5,]
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,2,3,4,5,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+[timestamp] [2,]
+[timestamp] [3,]
+[timestamp] [4,]
+[timestamp] [5,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+[timestamp] [1,]
+[timestamp] [2,3,4,5,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+[timestamp] [1,]
+[timestamp] [2,3,4,5,]
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/documents_remaining_should_only_be_bork.snap

@@ -0,0 +1,9 @@
+---
+source: index-scheduler/src/lib.rs
+---
+[
+  {
+    "id": 3,
+    "doggo": "bork"
+  }
+]

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/registered_the_document_deletions.snap

@@ -0,0 +1,53 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+2 {uid: 2, status: enqueued, details: { received_document_ids: 1, deleted_documents: None }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
+3 {uid: 3, status: enqueued, details: { original_filter: true, deleted_documents: None }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
+4 {uid: 4, status: enqueued, details: { original_filter: "id = 2", deleted_documents: None }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
+5 {uid: 5, status: enqueued, details: { original_filter: "catto EXISTS", deleted_documents: None }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
+----------------------------------------------------------------------
+### Status:
+enqueued [2,3,4,5,]
+succeeded [0,1,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"documentDeletion" [2,3,4,5,]
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,2,3,4,5,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 3, field_distribution: {"catto": 1, "doggo": 2, "id": 3} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+[timestamp] [2,]
+[timestamp] [3,]
+[timestamp] [4,]
+[timestamp] [5,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/registered_the_setting_and_document_addition.snap

@@ -0,0 +1,39 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued [0,1,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+----------------------------------------------------------------------
+### Finished At:
+----------------------------------------------------------------------
+### File Store:
+00000000-0000-0000-0000-000000000000
+
+----------------------------------------------------------------------

index-scheduler/src/snapshots/lib.rs/import_vectors/Intel to kefir succeeds.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------

index-scheduler/src/snapshots/lib.rs/import_vectors/Intel to kefir.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------

index-scheduler/src/snapshots/lib.rs/import_vectors/adding Intel succeeds.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:

index-scheduler/src/snapshots/lib.rs/import_vectors/after adding Intel.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:

index-scheduler/src/snapshots/lib.rs/import_vectors/after_registering_settings_task_vectors.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

index-scheduler/src/snapshots/lib.rs/import_vectors/settings_update_processed_vectors.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

index-scheduler/src/snapshots/lib.rs/test_settings_update/after_registering_settings_task.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

index-scheduler/src/snapshots/lib.rs/test_settings_update/settings_update_processed.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

meilisearch-types/Cargo.toml

@@ -66,3 +66,8 @@ khmer = ["milli/khmer"]
 vietnamese = ["milli/vietnamese"]
 # force swedish character recomposition
 swedish-recomposition = ["milli/swedish-recomposition"]
+# allow german tokenization
+german = ["milli/german"]
+# allow turkish normalization
+turkish = ["milli/turkish"]
+

meilisearch-types/src/error.rs

@@ -238,8 +238,14 @@ InvalidIndexLimit                     , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexOffset                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexPrimaryKey                , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexUid                       , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchFacets              , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchFacetsByIndex       , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchFacetOrder          , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchFederated           , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchFederationOptions   , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchMaxValuesPerFacet   , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchMergeFacets         , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchQueryFacets         , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchQueryPagination     , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchQueryRankingRules   , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchWeight              , InvalidRequest       , BAD_REQUEST ;
@@ -388,7 +394,11 @@ impl ErrorCode for milli::Error {
                     | UserError::InvalidOpenAiModelDimensionsMax { .. }
                     | UserError::InvalidSettingsDimensions { .. }
                     | UserError::InvalidUrl { .. }
-                    | UserError::InvalidPrompt(_) => Code::InvalidSettingsEmbedders,
+                    | UserError::InvalidSettingsDocumentTemplateMaxBytes { .. }
+                    | UserError::InvalidPrompt(_)
+                    | UserError::InvalidDisableBinaryQuantization { .. } => {
+                        Code::InvalidSettingsEmbedders
+                    }
                     UserError::TooManyEmbedders(_) => Code::InvalidSettingsEmbedders,
                     UserError::InvalidPromptForEmbeddings(..) => Code::InvalidSettingsEmbedders,
                     UserError::NoPrimaryKeyCandidateFound => Code::IndexPrimaryKeyNoCandidateFound,

meilisearch-types/src/index_uid.rs

@@ -1,3 +1,4 @@
+use std::borrow::Borrow;
 use std::error::Error;
 use std::fmt;
 use std::str::FromStr;
@@ -8,7 +9,7 @@ use crate::error::{Code, ErrorCode};
 
 /// An index uid is composed of only ascii alphanumeric characters, - and _, between 1 and 400
 /// bytes long
-#[derive(Debug, Clone, PartialEq, Eq, Deserr)]
+#[derive(Debug, Clone, PartialEq, Eq, Deserr, PartialOrd, Ord)]
 #[deserr(try_from(String) = IndexUid::try_from -> IndexUidFormatError)]
 pub struct IndexUid(String);
 
@@ -70,6 +71,12 @@ impl From<IndexUid> for String {
     }
 }
 
+impl Borrow<String> for IndexUid {
+    fn borrow(&self) -> &String {
+        &self.0
+    }
+}
+
 #[derive(Debug)]
 pub struct IndexUidFormatError {
     pub invalid_uid: String,

meilisearch-types/src/locales.rs

@@ -1,134 +1,6 @@
 use deserr::Deserr;
 use milli::LocalizedAttributesRule;
 use serde::{Deserialize, Serialize};
-use serde_json::json;
-
-/// Generate a Locale enum and its From and Into implementations for milli::tokenizer::Language.
-///
-/// this enum implements `Deserr` in order to be used in the API.
-macro_rules! make_locale {
-
-    ($($language:tt), +) => {
-        #[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize, Ord, PartialOrd)]
-        #[deserr(rename_all = camelCase)]
-        #[serde(rename_all = "camelCase")]
-        pub enum Locale {
-            $($language),+,
-        }
-
-        impl From<milli::tokenizer::Language> for Locale {
-            fn from(other: milli::tokenizer::Language) -> Locale {
-                match other {
-                    $(milli::tokenizer::Language::$language => Locale::$language), +
-                }
-            }
-        }
-
-        impl From<Locale> for milli::tokenizer::Language {
-            fn from(other: Locale) -> milli::tokenizer::Language {
-                match other {
-                    $(Locale::$language => milli::tokenizer::Language::$language), +,
-                }
-            }
-        }
-
-        #[derive(Debug)]
-        pub struct LocaleFormatError {
-            pub invalid_locale: String,
-        }
-
-        impl std::fmt::Display for LocaleFormatError {
-            fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-                let valid_locales = [$(Locale::$language),+].iter().map(|l| format!("`{}`", json!(l).as_str().unwrap())).collect::<Vec<_>>().join(", ");
-                write!(f, "Unsupported locale `{}`, expected one of {}", self.invalid_locale, valid_locales)
-            }
-        }
-    };
-}
-
-make_locale! {
-    Epo,
-    Eng,
-    Rus,
-    Cmn,
-    Spa,
-    Por,
-    Ita,
-    Ben,
-    Fra,
-    Deu,
-    Ukr,
-    Kat,
-    Ara,
-    Hin,
-    Jpn,
-    Heb,
-    Yid,
-    Pol,
-    Amh,
-    Jav,
-    Kor,
-    Nob,
-    Dan,
-    Swe,
-    Fin,
-    Tur,
-    Nld,
-    Hun,
-    Ces,
-    Ell,
-    Bul,
-    Bel,
-    Mar,
-    Kan,
-    Ron,
-    Slv,
-    Hrv,
-    Srp,
-    Mkd,
-    Lit,
-    Lav,
-    Est,
-    Tam,
-    Vie,
-    Urd,
-    Tha,
-    Guj,
-    Uzb,
-    Pan,
-    Aze,
-    Ind,
-    Tel,
-    Pes,
-    Mal,
-    Ori,
-    Mya,
-    Nep,
-    Sin,
-    Khm,
-    Tuk,
-    Aka,
-    Zul,
-    Sna,
-    Afr,
-    Lat,
-    Slk,
-    Cat,
-    Tgl,
-    Hye
-}
-
-impl std::error::Error for LocaleFormatError {}
-
-impl std::str::FromStr for Locale {
-    type Err = LocaleFormatError;
-
-    fn from_str(s: &str) -> Result<Self, Self::Err> {
-        milli::tokenizer::Language::from_code(s)
-            .map(Self::from)
-            .ok_or(LocaleFormatError { invalid_locale: s.to_string() })
-    }
-}
 
 #[derive(Debug, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize)]
 #[deserr(rename_all = camelCase)]
@@ -155,3 +27,140 @@ impl From<LocalizedAttributesRuleView> for LocalizedAttributesRule {
         }
     }
 }
+
+/// Generate a Locale enum and its From and Into implementations for milli::tokenizer::Language.
+///
+/// this enum implements `Deserr` in order to be used in the API.
+macro_rules! make_locale {
+    ($(($iso_639_1:ident, $iso_639_1_str:expr) => ($iso_639_3:ident, $iso_639_3_str:expr),)+) => {
+        #[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize, Ord, PartialOrd)]
+        #[deserr(rename_all = camelCase)]
+        #[serde(rename_all = "camelCase")]
+        pub enum Locale {
+            $($iso_639_1,)+
+            $($iso_639_3,)+
+            Cmn,
+        }
+
+        impl From<milli::tokenizer::Language> for Locale {
+            fn from(other: milli::tokenizer::Language) -> Locale {
+                match other {
+                    $(milli::tokenizer::Language::$iso_639_3 => Locale::$iso_639_3,)+
+                    milli::tokenizer::Language::Cmn => Locale::Cmn,
+                }
+            }
+        }
+
+        impl From<Locale> for milli::tokenizer::Language {
+            fn from(other: Locale) -> milli::tokenizer::Language {
+                match other {
+                    $(Locale::$iso_639_1 => milli::tokenizer::Language::$iso_639_3,)+
+                    $(Locale::$iso_639_3 => milli::tokenizer::Language::$iso_639_3,)+
+                    Locale::Cmn => milli::tokenizer::Language::Cmn,
+                }
+            }
+        }
+
+        impl std::str::FromStr for Locale {
+            type Err = LocaleFormatError;
+
+            fn from_str(s: &str) -> Result<Self, Self::Err> {
+                let locale = match s {
+                    $($iso_639_1_str => Locale::$iso_639_1,)+
+                    $($iso_639_3_str => Locale::$iso_639_3,)+
+                    "cmn" => Locale::Cmn,
+                    _ => return Err(LocaleFormatError { invalid_locale: s.to_string() }),
+                };
+
+                Ok(locale)
+            }
+        }
+
+        #[derive(Debug)]
+        pub struct LocaleFormatError {
+            pub invalid_locale: String,
+        }
+
+        impl std::fmt::Display for LocaleFormatError {
+            fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+                let mut valid_locales = [$($iso_639_1_str),+,$($iso_639_3_str),+,"cmn"];
+                valid_locales.sort_by(|left, right| left.len().cmp(&right.len()).then(left.cmp(right)));
+                write!(f, "Unsupported locale `{}`, expected one of {}", self.invalid_locale, valid_locales.join(", "))
+            }
+        }
+
+        impl std::error::Error for LocaleFormatError {}
+    };
+}
+
+make_locale!(
+    (Af, "af") => (Afr, "afr"),
+    (Ak, "ak") => (Aka, "aka"),
+    (Am, "am") => (Amh, "amh"),
+    (Ar, "ar") => (Ara, "ara"),
+    (Az, "az") => (Aze, "aze"),
+    (Be, "be") => (Bel, "bel"),
+    (Bn, "bn") => (Ben, "ben"),
+    (Bg, "bg") => (Bul, "bul"),
+    (Ca, "ca") => (Cat, "cat"),
+    (Cs, "cs") => (Ces, "ces"),
+    (Da, "da") => (Dan, "dan"),
+    (De, "de") => (Deu, "deu"),
+    (El, "el") => (Ell, "ell"),
+    (En, "en") => (Eng, "eng"),
+    (Eo, "eo") => (Epo, "epo"),
+    (Et, "et") => (Est, "est"),
+    (Fi, "fi") => (Fin, "fin"),
+    (Fr, "fr") => (Fra, "fra"),
+    (Gu, "gu") => (Guj, "guj"),
+    (He, "he") => (Heb, "heb"),
+    (Hi, "hi") => (Hin, "hin"),
+    (Hr, "hr") => (Hrv, "hrv"),
+    (Hu, "hu") => (Hun, "hun"),
+    (Hy, "hy") => (Hye, "hye"),
+    (Id, "id") => (Ind, "ind"),
+    (It, "it") => (Ita, "ita"),
+    (Jv, "jv") => (Jav, "jav"),
+    (Ja, "ja") => (Jpn, "jpn"),
+    (Kn, "kn") => (Kan, "kan"),
+    (Ka, "ka") => (Kat, "kat"),
+    (Km, "km") => (Khm, "khm"),
+    (Ko, "ko") => (Kor, "kor"),
+    (La, "la") => (Lat, "lat"),
+    (Lv, "lv") => (Lav, "lav"),
+    (Lt, "lt") => (Lit, "lit"),
+    (Ml, "ml") => (Mal, "mal"),
+    (Mr, "mr") => (Mar, "mar"),
+    (Mk, "mk") => (Mkd, "mkd"),
+    (My, "my") => (Mya, "mya"),
+    (Ne, "ne") => (Nep, "nep"),
+    (Nl, "nl") => (Nld, "nld"),
+    (Nb, "nb") => (Nob, "nob"),
+    (Or, "or") => (Ori, "ori"),
+    (Pa, "pa") => (Pan, "pan"),
+    (Fa, "fa") => (Pes, "pes"),
+    (Pl, "pl") => (Pol, "pol"),
+    (Pt, "pt") => (Por, "por"),
+    (Ro, "ro") => (Ron, "ron"),
+    (Ru, "ru") => (Rus, "rus"),
+    (Si, "si") => (Sin, "sin"),
+    (Sk, "sk") => (Slk, "slk"),
+    (Sl, "sl") => (Slv, "slv"),
+    (Sn, "sn") => (Sna, "sna"),
+    (Es, "es") => (Spa, "spa"),
+    (Sr, "sr") => (Srp, "srp"),
+    (Sv, "sv") => (Swe, "swe"),
+    (Ta, "ta") => (Tam, "tam"),
+    (Te, "te") => (Tel, "tel"),
+    (Tl, "tl") => (Tgl, "tgl"),
+    (Th, "th") => (Tha, "tha"),
+    (Tk, "tk") => (Tuk, "tuk"),
+    (Tr, "tr") => (Tur, "tur"),
+    (Uk, "uk") => (Ukr, "ukr"),
+    (Ur, "ur") => (Urd, "urd"),
+    (Uz, "uz") => (Uzb, "uzb"),
+    (Vi, "vi") => (Vie, "vie"),
+    (Yi, "yi") => (Yid, "yid"),
+    (Zh, "zh") => (Zho, "zho"),
+    (Zu, "zu") => (Zul, "zul"),
+);

meilisearch-types/src/versioning.rs

@@ -10,38 +10,52 @@ static VERSION_MINOR: &str = env!("CARGO_PKG_VERSION_MINOR");
 static VERSION_PATCH: &str = env!("CARGO_PKG_VERSION_PATCH");
 
 /// Persists the version of the current Meilisearch binary to a VERSION file
-pub fn create_version_file(db_path: &Path) -> io::Result<()> {
+pub fn create_current_version_file(db_path: &Path) -> io::Result<()> {
+    create_version_file(db_path, VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH)
+}
+
+pub fn create_version_file(
+    db_path: &Path,
+    major: &str,
+    minor: &str,
+    patch: &str,
+) -> io::Result<()> {
     let version_path = db_path.join(VERSION_FILE_NAME);
-    fs::write(version_path, format!("{}.{}.{}", VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH))
+    fs::write(version_path, format!("{}.{}.{}", major, minor, patch))
 }
 
 /// Ensures Meilisearch version is compatible with the database, returns an error versions mismatch.
 pub fn check_version_file(db_path: &Path) -> anyhow::Result<()> {
-    let version_path = db_path.join(VERSION_FILE_NAME);
+    let (major, minor, patch) = get_version(db_path)?;
 
-    match fs::read_to_string(version_path) {
-        Ok(version) => {
-            let version_components = version.split('.').collect::<Vec<_>>();
-            let (major, minor, patch) = match &version_components[..] {
-                [major, minor, patch] => (major.to_string(), minor.to_string(), patch.to_string()),
-                _ => return Err(VersionFileError::MalformedVersionFile.into()),
-            };
-
-            if major != VERSION_MAJOR || minor != VERSION_MINOR {
-                return Err(VersionFileError::VersionMismatch { major, minor, patch }.into());
-            }
-        }
-        Err(error) => {
-            return match error.kind() {
-                ErrorKind::NotFound => Err(VersionFileError::MissingVersionFile.into()),
-                _ => Err(error.into()),
-            }
-        }
+    if major != VERSION_MAJOR || minor != VERSION_MINOR {
+        return Err(VersionFileError::VersionMismatch { major, minor, patch }.into());
     }
 
     Ok(())
 }
 
+pub fn get_version(db_path: &Path) -> Result<(String, String, String), VersionFileError> {
+    let version_path = db_path.join(VERSION_FILE_NAME);
+
+    match fs::read_to_string(version_path) {
+        Ok(version) => parse_version(&version),
+        Err(error) => match error.kind() {
+            ErrorKind::NotFound => Err(VersionFileError::MissingVersionFile),
+            _ => Err(error.into()),
+        },
+    }
+}
+
+pub fn parse_version(version: &str) -> Result<(String, String, String), VersionFileError> {
+    let version_components = version.split('.').collect::<Vec<_>>();
+    let (major, minor, patch) = match &version_components[..] {
+        [major, minor, patch] => (major.to_string(), minor.to_string(), patch.to_string()),
+        _ => return Err(VersionFileError::MalformedVersionFile),
+    };
+    Ok((major, minor, patch))
+}
+
 #[derive(thiserror::Error, Debug)]
 pub enum VersionFileError {
     #[error(
@@ -58,4 +72,7 @@ pub enum VersionFileError {
         env!("CARGO_PKG_VERSION").to_string()
     )]
     VersionMismatch { major: String, minor: String, patch: String },
+
+    #[error(transparent)]
+    IoError(#[from] std::io::Error),
 }

meilisearch/Cargo.toml

@@ -75,7 +75,7 @@ reqwest = { version = "0.12.5", features = [
 rustls = { version = "0.23.11", features = ["ring"], default-features = false }
 rustls-pki-types = { version = "1.7.0", features = ["alloc"] }
 rustls-pemfile = "2.1.2"
-segment = { version = "0.2.4", optional = true }
+segment = { version = "0.2.4" }
 serde = { version = "1.0.204", features = ["derive"] }
 serde_json = { version = "1.0.120", features = ["preserve_order"] }
 sha2 = "0.10.8"
@@ -104,6 +104,7 @@ tracing-trace = { version = "0.1.0", path = "../tracing-trace" }
 tracing-actix-web = "0.7.11"
 build-info = { version = "1.7.0", path = "../build-info" }
 roaring = "0.10.2"
+mopa-maintained = "0.2.3"
 
 [dev-dependencies]
 actix-rt = "2.10.0"
@@ -131,8 +132,7 @@ tempfile = { version = "3.10.1", optional = true }
 zip = { version = "2.1.3", optional = true }
 
 [features]
-default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
-analytics = ["segment"]
+default = ["meilisearch-types/all-tokenizations", "mini-dashboard"]
 mini-dashboard = [
     "static-files",
     "anyhow",
@@ -153,7 +153,9 @@ greek = ["meilisearch-types/greek"]
 khmer = ["meilisearch-types/khmer"]
 vietnamese = ["meilisearch-types/vietnamese"]
 swedish-recomposition = ["meilisearch-types/swedish-recomposition"]
+german = ["meilisearch-types/german"]
+turkish = ["meilisearch-types/turkish"]
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.14/build.zip"
-sha1 = "592d1b5a3459d621d0aae1dded8fe3154f5c38fe"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.15/build.zip"
+sha1 = "d057600b4a839a2e0c0be7a372cd1b2683f3ca7e"

meilisearch/src/analytics/mock_analytics.rs

@@ -1,109 +0,0 @@
-use std::any::Any;
-use std::sync::Arc;
-
-use actix_web::HttpRequest;
-use meilisearch_types::InstanceUid;
-use serde_json::Value;
-
-use super::{find_user_id, Analytics, DocumentDeletionKind, DocumentFetchKind};
-use crate::routes::indexes::documents::{DocumentEditionByFunction, UpdateDocumentsQuery};
-use crate::Opt;
-
-pub struct MockAnalytics {
-    instance_uid: Option<InstanceUid>,
-}
-
-#[derive(Default)]
-pub struct SearchAggregator;
-
-#[allow(dead_code)]
-impl SearchAggregator {
-    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
-    }
-
-    pub fn succeed(&mut self, _: &dyn Any) {}
-}
-
-#[derive(Default)]
-pub struct SimilarAggregator;
-
-#[allow(dead_code)]
-impl SimilarAggregator {
-    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
-    }
-
-    pub fn succeed(&mut self, _: &dyn Any) {}
-}
-
-#[derive(Default)]
-pub struct MultiSearchAggregator;
-
-#[allow(dead_code)]
-impl MultiSearchAggregator {
-    pub fn from_federated_search(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
-    }
-
-    pub fn succeed(&mut self) {}
-}
-
-#[derive(Default)]
-pub struct FacetSearchAggregator;
-
-#[allow(dead_code)]
-impl FacetSearchAggregator {
-    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
-    }
-
-    pub fn succeed(&mut self, _: &dyn Any) {}
-}
-
-impl MockAnalytics {
-    #[allow(clippy::new_ret_no_self)]
-    pub fn new(opt: &Opt) -> Arc<dyn Analytics> {
-        let instance_uid = find_user_id(&opt.db_path);
-        Arc::new(Self { instance_uid })
-    }
-}
-
-impl Analytics for MockAnalytics {
-    fn instance_uid(&self) -> Option<&meilisearch_types::InstanceUid> {
-        self.instance_uid.as_ref()
-    }
-
-    // These methods are noop and should be optimized out
-    fn publish(&self, _event_name: String, _send: Value, _request: Option<&HttpRequest>) {}
-    fn get_search(&self, _aggregate: super::SearchAggregator) {}
-    fn post_search(&self, _aggregate: super::SearchAggregator) {}
-    fn get_similar(&self, _aggregate: super::SimilarAggregator) {}
-    fn post_similar(&self, _aggregate: super::SimilarAggregator) {}
-    fn post_multi_search(&self, _aggregate: super::MultiSearchAggregator) {}
-    fn post_facet_search(&self, _aggregate: super::FacetSearchAggregator) {}
-    fn add_documents(
-        &self,
-        _documents_query: &UpdateDocumentsQuery,
-        _index_creation: bool,
-        _request: &HttpRequest,
-    ) {
-    }
-    fn delete_documents(&self, _kind: DocumentDeletionKind, _request: &HttpRequest) {}
-    fn update_documents(
-        &self,
-        _documents_query: &UpdateDocumentsQuery,
-        _index_creation: bool,
-        _request: &HttpRequest,
-    ) {
-    }
-    fn update_documents_by_function(
-        &self,
-        _documents_query: &DocumentEditionByFunction,
-        _index_creation: bool,
-        _request: &HttpRequest,
-    ) {
-    }
-    fn get_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
-    fn post_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
-}

meilisearch/src/analytics/mod.rs

@@ -1,44 +1,45 @@
-mod mock_analytics;
-#[cfg(feature = "analytics")]
-mod segment_analytics;
+pub mod segment_analytics;
 
 use std::fs;
 use std::path::{Path, PathBuf};
 use std::str::FromStr;
+use std::sync::Arc;
 
 use actix_web::HttpRequest;
+use index_scheduler::IndexScheduler;
+use meilisearch_auth::AuthController;
 use meilisearch_types::InstanceUid;
-pub use mock_analytics::MockAnalytics;
+use mopa::mopafy;
 use once_cell::sync::Lazy;
 use platform_dirs::AppDirs;
-use serde_json::Value;
-
-use crate::routes::indexes::documents::{DocumentEditionByFunction, UpdateDocumentsQuery};
-
-// if the analytics feature is disabled
-// the `SegmentAnalytics` point to the mock instead of the real analytics
-#[cfg(not(feature = "analytics"))]
-pub type SegmentAnalytics = mock_analytics::MockAnalytics;
-#[cfg(not(feature = "analytics"))]
-pub type SearchAggregator = mock_analytics::SearchAggregator;
-#[cfg(not(feature = "analytics"))]
-pub type SimilarAggregator = mock_analytics::SimilarAggregator;
-#[cfg(not(feature = "analytics"))]
-pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
-#[cfg(not(feature = "analytics"))]
-pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
 
 // if the feature analytics is enabled we use the real analytics
-#[cfg(feature = "analytics")]
 pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
-#[cfg(feature = "analytics")]
-pub type SearchAggregator = segment_analytics::SearchAggregator;
-#[cfg(feature = "analytics")]
-pub type SimilarAggregator = segment_analytics::SimilarAggregator;
-#[cfg(feature = "analytics")]
-pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
-#[cfg(feature = "analytics")]
-pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
+
+use crate::Opt;
+
+/// A macro used to quickly define events that don't aggregate or send anything besides an empty event with its name.
+#[macro_export]
+macro_rules! empty_analytics {
+    ($struct_name:ident, $event_name:literal) => {
+        #[derive(Default)]
+        struct $struct_name {}
+
+        impl $crate::analytics::Aggregate for $struct_name {
+            fn event_name(&self) -> &'static str {
+                $event_name
+            }
+
+            fn aggregate(self: Box<Self>, _other: Box<Self>) -> Box<Self> {
+                self
+            }
+
+            fn into_event(self: Box<Self>) -> serde_json::Value {
+                serde_json::json!({})
+            }
+        }
+    };
+}
 
 /// The Meilisearch config dir:
 /// `~/.config/Meilisearch` on *NIX or *BSD.
@@ -78,60 +79,88 @@ pub enum DocumentFetchKind {
     Normal { with_filter: bool, limit: usize, offset: usize, retrieve_vectors: bool },
 }
 
-pub trait Analytics: Sync + Send {
-    fn instance_uid(&self) -> Option<&InstanceUid>;
+/// To send an event to segment, your event must be able to aggregate itself with another event of the same type.
+pub trait Aggregate: 'static + mopa::Any + Send {
+    /// The name of the event that will be sent to segment.
+    fn event_name(&self) -> &'static str;
+
+    /// Will be called every time an event has been used twice before segment flushed its buffer.
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self>
+    where
+        Self: Sized;
+
+    /// Converts your structure to the final event that'll be sent to segment.
+    fn into_event(self: Box<Self>) -> serde_json::Value;
+}
+
+mopafy!(Aggregate);
+
+/// Helper trait to define multiple aggregates with the same content but a different name.
+/// Commonly used when you must aggregate a search with POST or with GET, for example.
+pub trait AggregateMethod: 'static + Default + Send {
+    fn event_name() -> &'static str;
+}
+
+/// A macro used to quickly define multiple aggregate method with their name
+/// Usage:
+/// ```rust
+/// use meilisearch::aggregate_methods;
+///
+/// aggregate_methods!(
+///     SearchGET => "Documents Searched GET",
+///     SearchPOST => "Documents Searched POST",
+/// );
+/// ```
+#[macro_export]
+macro_rules! aggregate_methods {
+    ($method:ident => $event_name:literal) => {
+        #[derive(Default)]
+        pub struct $method {}
+
+        impl $crate::analytics::AggregateMethod for $method {
+            fn event_name() -> &'static str {
+                $event_name
+            }
+        }
+    };
+    ($($method:ident => $event_name:literal,)+) => {
+        $(
+            aggregate_methods!($method => $event_name);
+        )+
+
+    };
+}
+
+#[derive(Clone)]
+pub struct Analytics {
+    segment: Option<Arc<SegmentAnalytics>>,
+}
+
+impl Analytics {
+    pub async fn new(
+        opt: &Opt,
+        index_scheduler: Arc<IndexScheduler>,
+        auth_controller: Arc<AuthController>,
+    ) -> Self {
+        if opt.no_analytics {
+            Self { segment: None }
+        } else {
+            Self { segment: SegmentAnalytics::new(opt, index_scheduler, auth_controller).await }
+        }
+    }
+
+    pub fn no_analytics() -> Self {
+        Self { segment: None }
+    }
+
+    pub fn instance_uid(&self) -> Option<&InstanceUid> {
+        self.segment.as_ref().map(|segment| segment.instance_uid.as_ref())
+    }
 
     /// The method used to publish most analytics that do not need to be batched every hours
-    fn publish(&self, event_name: String, send: Value, request: Option<&HttpRequest>);
-
-    /// This method should be called to aggregate a get search
-    fn get_search(&self, aggregate: SearchAggregator);
-
-    /// This method should be called to aggregate a post search
-    fn post_search(&self, aggregate: SearchAggregator);
-
-    /// This method should be called to aggregate a get similar request
-    fn get_similar(&self, aggregate: SimilarAggregator);
-
-    /// This method should be called to aggregate a post similar request
-    fn post_similar(&self, aggregate: SimilarAggregator);
-
-    /// This method should be called to aggregate a post array of searches
-    fn post_multi_search(&self, aggregate: MultiSearchAggregator);
-
-    /// This method should be called to aggregate post facet values searches
-    fn post_facet_search(&self, aggregate: FacetSearchAggregator);
-
-    // this method should be called to aggregate an add documents request
-    fn add_documents(
-        &self,
-        documents_query: &UpdateDocumentsQuery,
-        index_creation: bool,
-        request: &HttpRequest,
-    );
-
-    // this method should be called to aggregate a fetch documents request
-    fn get_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest);
-
-    // this method should be called to aggregate a fetch documents request
-    fn post_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest);
-
-    // this method should be called to aggregate a add documents request
-    fn delete_documents(&self, kind: DocumentDeletionKind, request: &HttpRequest);
-
-    // this method should be called to batch an update documents request
-    fn update_documents(
-        &self,
-        documents_query: &UpdateDocumentsQuery,
-        index_creation: bool,
-        request: &HttpRequest,
-    );
-
-    // this method should be called to batch an update documents by function request
-    fn update_documents_by_function(
-        &self,
-        documents_query: &DocumentEditionByFunction,
-        index_creation: bool,
-        request: &HttpRequest,
-    );
+    pub fn publish<T: Aggregate>(&self, event: T, request: &HttpRequest) {
+        if let Some(ref segment) = self.segment {
+            let _ = segment.sender.try_send(segment_analytics::Message::new(event, request));
+        }
+    }
 }

meilisearch/src/error.rs

@@ -4,6 +4,7 @@ use byte_unit::{Byte, UnitType};
 use meilisearch_types::document_formats::{DocumentFormatError, PayloadType};
 use meilisearch_types::error::{Code, ErrorCode, ResponseError};
 use meilisearch_types::index_uid::{IndexUid, IndexUidFormatError};
+use meilisearch_types::milli::OrderBy;
 use serde_json::Value;
 use tokio::task::JoinError;
 
@@ -27,10 +28,20 @@ pub enum MeilisearchHttpError {
     EmptyFilter,
     #[error("Invalid syntax for the filter parameter: `expected {}, found: {1}`.", .0.join(", "))]
     InvalidExpression(&'static [&'static str], Value),
-    #[error("Using `federationOptions` is not allowed in a non-federated search.\n Hint: remove `federationOptions` from query #{0} or add `federation: {{}}` to the request.")]
+    #[error("Using `federationOptions` is not allowed in a non-federated search.\n - Hint: remove `federationOptions` from query #{0} or add `federation` to the request.")]
     FederationOptionsInNonFederatedRequest(usize),
-    #[error("Inside `.queries[{0}]`: Using pagination options is not allowed in federated queries.\n Hint: remove `{1}` from query #{0} or remove `federation: {{}}` from the request")]
+    #[error("Inside `.queries[{0}]`: Using pagination options is not allowed in federated queries.\n - Hint: remove `{1}` from query #{0} or remove `federation` from the request\n - Hint: pass `federation.limit` and `federation.offset` for pagination in federated search")]
     PaginationInFederatedQuery(usize, &'static str),
+    #[error("Inside `.queries[{0}]`: Using facet options is not allowed in federated queries.\n - Hint: remove `facets` from query #{0} or remove `federation` from the request\n - Hint: pass `federation.facetsByIndex.{1}: {2:?}` for facets in federated search")]
+    FacetsInFederatedQuery(usize, String, Vec<String>),
+    #[error("Inconsistent order for values in facet `{facet}`: index `{previous_uid}` orders {previous_facet_order}, but index `{current_uid}` orders {index_facet_order}.\n - Hint: Remove `federation.mergeFacets` or change `faceting.sortFacetValuesBy` to be consistent in settings.")]
+    InconsistentFacetOrder {
+        facet: String,
+        previous_facet_order: OrderBy,
+        previous_uid: String,
+        index_facet_order: OrderBy,
+        current_uid: String,
+    },
     #[error("A {0} payload is missing.")]
     MissingPayload(PayloadType),
     #[error("Too many search requests running at the same time: {0}. Retry after 10s.")]
@@ -61,7 +72,7 @@ pub enum MeilisearchHttpError {
     DocumentFormat(#[from] DocumentFormatError),
     #[error(transparent)]
     Join(#[from] JoinError),
-    #[error("Invalid request: missing `hybrid` parameter when both `q` and `vector` are present.")]
+    #[error("Invalid request: missing `hybrid` parameter when `vector` is present.")]
     MissingSearchHybrid,
 }
 
@@ -96,6 +107,10 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::PaginationInFederatedQuery(_, _) => {
                 Code::InvalidMultiSearchQueryPagination
             }
+            MeilisearchHttpError::FacetsInFederatedQuery(..) => Code::InvalidMultiSearchQueryFacets,
+            MeilisearchHttpError::InconsistentFacetOrder { .. } => {
+                Code::InvalidMultiSearchFacetOrder
+            }
         }
     }
 }

meilisearch/src/lib.rs

@@ -13,11 +13,10 @@ pub mod search_queue;
 
 use std::fs::File;
 use std::io::{BufReader, BufWriter};
-use std::num::NonZeroUsize;
 use std::path::Path;
 use std::str::FromStr;
 use std::sync::Arc;
-use std::thread::{self, available_parallelism};
+use std::thread;
 use std::time::Duration;
 
 use actix_cors::Cors;
@@ -37,7 +36,7 @@ use meilisearch_types::milli::documents::{DocumentsBatchBuilder, DocumentsBatchR
 use meilisearch_types::milli::update::{IndexDocumentsConfig, IndexDocumentsMethod};
 use meilisearch_types::settings::apply_settings_to_builder;
 use meilisearch_types::tasks::KindWithContent;
-use meilisearch_types::versioning::{check_version_file, create_version_file};
+use meilisearch_types::versioning::{check_version_file, create_current_version_file};
 use meilisearch_types::{compression, milli, VERSION_FILE_NAME};
 pub use option::Opt;
 use option::ScheduleSnapshot;
@@ -118,9 +117,10 @@ pub type LogStderrType = tracing_subscriber::filter::Filtered<
 pub fn create_app(
     index_scheduler: Data<IndexScheduler>,
     auth_controller: Data<AuthController>,
+    search_queue: Data<SearchQueue>,
     opt: Opt,
     logs: (LogRouteHandle, LogStderrHandle),
-    analytics: Arc<dyn Analytics>,
+    analytics: Data<Analytics>,
     enable_dashboard: bool,
 ) -> actix_web::App<
     impl ServiceFactory<
@@ -137,6 +137,7 @@ pub fn create_app(
                 s,
                 index_scheduler.clone(),
                 auth_controller.clone(),
+                search_queue.clone(),
                 &opt,
                 logs,
                 analytics.clone(),
@@ -318,7 +319,7 @@ fn open_or_create_database_unchecked(
     match (
         index_scheduler_builder(),
         auth_controller.map_err(anyhow::Error::from),
-        create_version_file(&opt.db_path).map_err(anyhow::Error::from),
+        create_current_version_file(&opt.db_path).map_err(anyhow::Error::from),
     ) {
         (Ok(i), Ok(a), Ok(())) => Ok((i, a)),
         (Err(e), _, _) | (_, Err(e), _) | (_, _, Err(e)) => {
@@ -469,20 +470,17 @@ pub fn configure_data(
     config: &mut web::ServiceConfig,
     index_scheduler: Data<IndexScheduler>,
     auth: Data<AuthController>,
+    search_queue: Data<SearchQueue>,
     opt: &Opt,
     (logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle),
-    analytics: Arc<dyn Analytics>,
+    analytics: Data<Analytics>,
 ) {
-    let search_queue = SearchQueue::new(
-        opt.experimental_search_queue_size,
-        available_parallelism().unwrap_or(NonZeroUsize::new(2).unwrap()),
-    );
     let http_payload_size_limit = opt.http_payload_size_limit.as_u64() as usize;
     config
         .app_data(index_scheduler)
         .app_data(auth)
-        .app_data(web::Data::new(search_queue))
-        .app_data(web::Data::from(analytics))
+        .app_data(search_queue)
+        .app_data(analytics)
         .app_data(web::Data::new(logs_route))
         .app_data(web::Data::new(logs_stderr))
         .app_data(web::Data::new(opt.clone()))

meilisearch/src/main.rs

@@ -1,8 +1,11 @@
 use std::env;
 use std::io::{stderr, LineWriter, Write};
+use std::num::NonZeroUsize;
 use std::path::PathBuf;
 use std::str::FromStr;
 use std::sync::Arc;
+use std::thread::available_parallelism;
+use std::time::Duration;
 
 use actix_web::http::KeepAlive;
 use actix_web::web::Data;
@@ -11,6 +14,7 @@ use index_scheduler::IndexScheduler;
 use is_terminal::IsTerminal;
 use meilisearch::analytics::Analytics;
 use meilisearch::option::LogMode;
+use meilisearch::search_queue::SearchQueue;
 use meilisearch::{
     analytics, create_app, setup_meilisearch, LogRouteHandle, LogRouteType, LogStderrHandle,
     LogStderrType, Opt, SubscriberForSecondLayer,
@@ -72,6 +76,19 @@ fn on_panic(info: &std::panic::PanicInfo) {
 
 #[actix_web::main]
 async fn main() -> anyhow::Result<()> {
+    try_main().await.inspect_err(|error| {
+        tracing::error!(%error);
+        let mut current = error.source();
+        let mut depth = 0;
+        while let Some(source) = current {
+            tracing::info!(%source, depth, "Error caused by");
+            current = source.source();
+            depth += 1;
+        }
+    })
+}
+
+async fn try_main() -> anyhow::Result<()> {
     let (opt, config_read_from) = Opt::try_build()?;
 
     std::panic::set_hook(Box::new(on_panic));
@@ -107,19 +124,12 @@ async fn main() -> anyhow::Result<()> {
 
     let (index_scheduler, auth_controller) = setup_meilisearch(&opt)?;
 
-    #[cfg(all(not(debug_assertions), feature = "analytics"))]
-    let analytics = if !opt.no_analytics {
-        analytics::SegmentAnalytics::new(&opt, index_scheduler.clone(), auth_controller.clone())
-            .await
-    } else {
-        analytics::MockAnalytics::new(&opt)
-    };
-    #[cfg(any(debug_assertions, not(feature = "analytics")))]
-    let analytics = analytics::MockAnalytics::new(&opt);
+    let analytics =
+        analytics::Analytics::new(&opt, index_scheduler.clone(), auth_controller.clone()).await;
 
     print_launch_resume(&opt, analytics.clone(), config_read_from);
 
-    run_http(index_scheduler, auth_controller, opt, log_handle, analytics).await?;
+    run_http(index_scheduler, auth_controller, opt, log_handle, Arc::new(analytics)).await?;
 
     Ok(())
 }
@@ -129,17 +139,30 @@ async fn run_http(
     auth_controller: Arc<AuthController>,
     opt: Opt,
     logs: (LogRouteHandle, LogStderrHandle),
-    analytics: Arc<dyn Analytics>,
+    analytics: Arc<Analytics>,
 ) -> anyhow::Result<()> {
     let enable_dashboard = &opt.env == "development";
     let opt_clone = opt.clone();
     let index_scheduler = Data::from(index_scheduler);
     let auth_controller = Data::from(auth_controller);
+    let analytics = Data::from(analytics);
+    let search_queue = SearchQueue::new(
+        opt.experimental_search_queue_size,
+        available_parallelism()
+            .unwrap_or(NonZeroUsize::new(2).unwrap())
+            .checked_mul(opt.experimental_nb_searches_per_core)
+            .unwrap_or(NonZeroUsize::MAX),
+    )
+    .with_time_to_abort(Duration::from_secs(
+        usize::from(opt.experimental_drop_search_after) as u64
+    ));
+    let search_queue = Data::new(search_queue);
 
     let http_server = HttpServer::new(move || {
         create_app(
             index_scheduler.clone(),
             auth_controller.clone(),
+            search_queue.clone(),
             opt.clone(),
             logs.clone(),
             analytics.clone(),
@@ -158,11 +181,7 @@ async fn run_http(
     Ok(())
 }
 
-pub fn print_launch_resume(
-    opt: &Opt,
-    analytics: Arc<dyn Analytics>,
-    config_read_from: Option<PathBuf>,
-) {
+pub fn print_launch_resume(opt: &Opt, analytics: Analytics, config_read_from: Option<PathBuf>) {
     let build_info = build_info::BuildInfo::from_build();
 
     let protocol =
@@ -204,7 +223,6 @@ pub fn print_launch_resume(
         eprintln!("Prototype:\t\t{:?}", prototype);
     }
 
-    #[cfg(all(not(debug_assertions), feature = "analytics"))]
     {
         if !opt.no_analytics {
             eprintln!(

meilisearch/src/middleware.rs

@@ -55,16 +55,17 @@ where
         let index_scheduler = req.app_data::<Data<IndexScheduler>>().unwrap();
         let features = index_scheduler.features();
 
+        let request_path = req.path();
+        let request_pattern = req.match_pattern();
+        let metric_path = request_pattern.as_ref().map_or(request_path, String::as_str).to_string();
+        let request_method = req.method().to_string();
+
         if features.check_metrics().is_ok() {
-            let request_path = req.path();
             let is_registered_resource = req.resource_map().has_resource(request_path);
             if is_registered_resource {
-                let request_pattern = req.match_pattern();
-                let metric_path = request_pattern.as_ref().map_or(request_path, String::as_str);
-                let request_method = req.method().to_string();
                 histogram_timer = Some(
                     crate::metrics::MEILISEARCH_HTTP_RESPONSE_TIME_SECONDS
-                        .with_label_values(&[&request_method, metric_path])
+                        .with_label_values(&[&request_method, &metric_path])
                         .start_timer(),
                 );
             }
@@ -76,11 +77,7 @@ where
             let res = fut.await?;
 
             crate::metrics::MEILISEARCH_HTTP_REQUESTS_TOTAL
-                .with_label_values(&[
-                    res.request().method().as_str(),
-                    res.request().path(),
-                    res.status().as_str(),
-                ])
+                .with_label_values(&[&request_method, &metric_path, res.status().as_str()])
                 .inc();
 
             if let Some(histogram_timer) = histogram_timer {

meilisearch/src/option.rs

@@ -2,7 +2,7 @@ use std::env::VarError;
 use std::ffi::OsStr;
 use std::fmt::Display;
 use std::io::{BufReader, Read};
-use std::num::ParseIntError;
+use std::num::{NonZeroUsize, ParseIntError};
 use std::ops::Deref;
 use std::path::PathBuf;
 use std::str::FromStr;
@@ -29,7 +29,6 @@ const MEILI_MASTER_KEY: &str = "MEILI_MASTER_KEY";
 const MEILI_ENV: &str = "MEILI_ENV";
 const MEILI_TASK_WEBHOOK_URL: &str = "MEILI_TASK_WEBHOOK_URL";
 const MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER: &str = "MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER";
-#[cfg(feature = "analytics")]
 const MEILI_NO_ANALYTICS: &str = "MEILI_NO_ANALYTICS";
 const MEILI_HTTP_PAYLOAD_SIZE_LIMIT: &str = "MEILI_HTTP_PAYLOAD_SIZE_LIMIT";
 const MEILI_SSL_CERT_PATH: &str = "MEILI_SSL_CERT_PATH";
@@ -55,6 +54,8 @@ const MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE: &str = "MEILI_EXPERIMENTAL_ENABLE_LO
 const MEILI_EXPERIMENTAL_CONTAINS_FILTER: &str = "MEILI_EXPERIMENTAL_CONTAINS_FILTER";
 const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
 const MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE: &str = "MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE";
+const MEILI_EXPERIMENTAL_DROP_SEARCH_AFTER: &str = "MEILI_EXPERIMENTAL_DROP_SEARCH_AFTER";
+const MEILI_EXPERIMENTAL_NB_SEARCHES_PER_CORE: &str = "MEILI_EXPERIMENTAL_NB_SEARCHES_PER_CORE";
 const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str =
     "MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE";
 const MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS: &str =
@@ -208,7 +209,6 @@ pub struct Opt {
     /// Meilisearch automatically collects data from all instances that do not opt out using this flag.
     /// All gathered data is used solely for the purpose of improving Meilisearch, and can be deleted
     /// at any time.
-    #[cfg(feature = "analytics")]
     #[serde(default)] // we can't send true
     #[clap(long, env = MEILI_NO_ANALYTICS)]
     pub no_analytics: bool,
@@ -357,10 +357,26 @@ pub struct Opt {
     /// Lets you customize the size of the search queue. Meilisearch processes your search requests as fast as possible but once the
     /// queue is full it starts returning HTTP 503, Service Unavailable.
     /// The default value is 1000.
-    #[clap(long, env = MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE, default_value_t = 1000)]
-    #[serde(default)]
+    #[clap(long, env = MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE, default_value_t = default_experimental_search_queue_size())]
+    #[serde(default = "default_experimental_search_queue_size")]
     pub experimental_search_queue_size: usize,
 
+    /// Experimental drop search after. For more information, see: <https://github.com/orgs/meilisearch/discussions/783>
+    ///
+    /// Let you customize after how many seconds Meilisearch should consider a search request irrelevant and drop it.
+    /// The default value is 60.
+    #[clap(long, env = MEILI_EXPERIMENTAL_DROP_SEARCH_AFTER, default_value_t = default_drop_search_after())]
+    #[serde(default = "default_drop_search_after")]
+    pub experimental_drop_search_after: NonZeroUsize,
+
+    /// Experimental number of searches per core. For more information, see: <https://github.com/orgs/meilisearch/discussions/784>
+    ///
+    /// Lets you customize how many search requests can run on each core concurrently.
+    /// The default value is 4.
+    #[clap(long, env = MEILI_EXPERIMENTAL_NB_SEARCHES_PER_CORE, default_value_t = default_nb_searches_per_core())]
+    #[serde(default = "default_nb_searches_per_core")]
+    pub experimental_nb_searches_per_core: NonZeroUsize,
+
     /// Experimental logs mode feature. For more information, see: <https://github.com/orgs/meilisearch/discussions/723>
     ///
     /// Change the mode of the logs on the console.
@@ -407,7 +423,6 @@ pub struct Opt {
 
 impl Opt {
     /// Whether analytics should be enabled or not.
-    #[cfg(all(not(debug_assertions), feature = "analytics"))]
     pub fn analytics(&self) -> bool {
         !self.no_analytics
     }
@@ -487,11 +502,12 @@ impl Opt {
             ignore_missing_dump: _,
             ignore_dump_if_db_exists: _,
             config_file_path: _,
-            #[cfg(feature = "analytics")]
             no_analytics,
             experimental_contains_filter,
             experimental_enable_metrics,
             experimental_search_queue_size,
+            experimental_drop_search_after,
+            experimental_nb_searches_per_core,
             experimental_logs_mode,
             experimental_enable_logs_route,
             experimental_replication_parameters,
@@ -513,10 +529,7 @@ impl Opt {
             );
         }
 
-        #[cfg(feature = "analytics")]
-        {
-            export_to_env_if_not_present(MEILI_NO_ANALYTICS, no_analytics.to_string());
-        }
+        export_to_env_if_not_present(MEILI_NO_ANALYTICS, no_analytics.to_string());
         export_to_env_if_not_present(
             MEILI_HTTP_PAYLOAD_SIZE_LIMIT,
             http_payload_size_limit.to_string(),
@@ -559,6 +572,14 @@ impl Opt {
             MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE,
             experimental_search_queue_size.to_string(),
         );
+        export_to_env_if_not_present(
+            MEILI_EXPERIMENTAL_DROP_SEARCH_AFTER,
+            experimental_drop_search_after.to_string(),
+        );
+        export_to_env_if_not_present(
+            MEILI_EXPERIMENTAL_NB_SEARCHES_PER_CORE,
+            experimental_nb_searches_per_core.to_string(),
+        );
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_LOGS_MODE,
             experimental_logs_mode.to_string(),
@@ -890,6 +911,18 @@ fn default_dump_dir() -> PathBuf {
     PathBuf::from(DEFAULT_DUMP_DIR)
 }
 
+fn default_experimental_search_queue_size() -> usize {
+    1000
+}
+
+fn default_drop_search_after() -> NonZeroUsize {
+    NonZeroUsize::new(60).unwrap()
+}
+
+fn default_nb_searches_per_core() -> NonZeroUsize {
+    NonZeroUsize::new(4).unwrap()
+}
+
 /// Indicates if a snapshot was scheduled, and if yes with which interval.
 #[derive(Debug, Default, Copy, Clone, Deserialize, Serialize)]
 pub enum ScheduleSnapshot {

meilisearch/src/routes/dump.rs

@@ -4,7 +4,6 @@ use index_scheduler::IndexScheduler;
 use meilisearch_auth::AuthController;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::tasks::KindWithContent;
-use serde_json::json;
 use tracing::debug;
 
 use crate::analytics::Analytics;
@@ -18,14 +17,16 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::post().to(SeqHandler(create_dump))));
 }
 
+crate::empty_analytics!(DumpAnalytics, "Dump Created");
+
 pub async fn create_dump(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DUMPS_CREATE }>, Data<IndexScheduler>>,
     auth_controller: GuardedData<ActionPolicy<{ actions::DUMPS_CREATE }>, Data<AuthController>>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    analytics.publish("Dump Created".to_string(), json!({}), Some(&req));
+    analytics.publish(DumpAnalytics::default(), &req);
 
     let task = KindWithContent::DumpCreation {
         keys: auth_controller.list_keys()?,

meilisearch/src/routes/features.rs

@@ -6,10 +6,10 @@ use index_scheduler::IndexScheduler;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::keys::actions;
-use serde_json::json;
+use serde::Serialize;
 use tracing::debug;
 
-use crate::analytics::Analytics;
+use crate::analytics::{Aggregate, Analytics};
 use crate::extractors::authentication::policies::ActionPolicy;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
@@ -17,7 +17,7 @@ use crate::extractors::sequential_extractor::SeqHandler;
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
         web::resource("")
-            .route(web::get().to(SeqHandler(get_features)))
+            .route(web::get().to(get_features))
             .route(web::patch().to(SeqHandler(patch_features))),
     );
 }
@@ -27,12 +27,9 @@ async fn get_features(
         ActionPolicy<{ actions::EXPERIMENTAL_FEATURES_GET }>,
         Data<IndexScheduler>,
     >,
-    req: HttpRequest,
-    analytics: Data<dyn Analytics>,
 ) -> HttpResponse {
     let features = index_scheduler.features();
 
-    analytics.publish("Experimental features Seen".to_string(), json!(null), Some(&req));
     let features = features.runtime_features();
     debug!(returns = ?features, "Get features");
     HttpResponse::Ok().json(features)
@@ -53,6 +50,35 @@ pub struct RuntimeTogglableFeatures {
     pub contains_filter: Option<bool>,
 }
 
+#[derive(Serialize)]
+pub struct PatchExperimentalFeatureAnalytics {
+    vector_store: bool,
+    metrics: bool,
+    logs_route: bool,
+    edit_documents_by_function: bool,
+    contains_filter: bool,
+}
+
+impl Aggregate for PatchExperimentalFeatureAnalytics {
+    fn event_name(&self) -> &'static str {
+        "Experimental features Updated"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            vector_store: new.vector_store,
+            metrics: new.metrics,
+            logs_route: new.logs_route,
+            edit_documents_by_function: new.edit_documents_by_function,
+            contains_filter: new.contains_filter,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 async fn patch_features(
     index_scheduler: GuardedData<
         ActionPolicy<{ actions::EXPERIMENTAL_FEATURES_UPDATE }>,
@@ -60,7 +86,7 @@ async fn patch_features(
     >,
     new_features: AwebJson<RuntimeTogglableFeatures, DeserrJsonError>,
     req: HttpRequest,
-    analytics: Data<dyn Analytics>,
+    analytics: Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let features = index_scheduler.features();
     debug!(parameters = ?new_features, "Patch features");
@@ -89,15 +115,14 @@ async fn patch_features(
     } = new_features;
 
     analytics.publish(
-        "Experimental features Updated".to_string(),
-        json!({
-            "vector_store": vector_store,
-            "metrics": metrics,
-            "logs_route": logs_route,
-            "edit_documents_by_function": edit_documents_by_function,
-            "contains_filter": contains_filter,
-        }),
-        Some(&req),
+        PatchExperimentalFeatureAnalytics {
+            vector_store,
+            metrics,
+            logs_route,
+            edit_documents_by_function,
+            contains_filter,
+        },
+        &req,
     );
     index_scheduler.put_runtime_features(new_features)?;
     debug!(returns = ?new_features, "Patch features");

meilisearch/src/routes/indexes/documents.rs

@@ -1,4 +1,6 @@
+use std::collections::HashSet;
 use std::io::ErrorKind;
+use std::marker::PhantomData;
 
 use actix_web::http::header::CONTENT_TYPE;
 use actix_web::web::Data;
@@ -23,14 +25,14 @@ use meilisearch_types::tasks::KindWithContent;
 use meilisearch_types::{milli, Document, Index};
 use mime::Mime;
 use once_cell::sync::Lazy;
-use serde::Deserialize;
+use serde::{Deserialize, Serialize};
 use serde_json::Value;
 use tempfile::tempfile;
 use tokio::fs::File;
 use tokio::io::{AsyncSeekExt, AsyncWriteExt, BufWriter};
 use tracing::debug;
 
-use crate::analytics::{Analytics, DocumentDeletionKind, DocumentFetchKind};
+use crate::analytics::{Aggregate, AggregateMethod, Analytics};
 use crate::error::MeilisearchHttpError;
 use crate::error::PayloadError::ReceivePayload;
 use crate::extractors::authentication::policies::*;
@@ -41,7 +43,7 @@ use crate::routes::{
     get_task_id, is_dry_run, PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT,
 };
 use crate::search::{parse_filter, RetrieveVectors};
-use crate::Opt;
+use crate::{aggregate_methods, Opt};
 
 static ACCEPTED_CONTENT_TYPE: Lazy<Vec<String>> = Lazy::new(|| {
     vec!["application/json".to_string(), "application/x-ndjson".to_string(), "text/csv".to_string()]
@@ -100,12 +102,84 @@ pub struct GetDocument {
     retrieve_vectors: Param<bool>,
 }
 
+aggregate_methods!(
+    DocumentsGET => "Documents Fetched GET",
+    DocumentsPOST => "Documents Fetched POST",
+);
+
+#[derive(Serialize)]
+pub struct DocumentsFetchAggregator<Method: AggregateMethod> {
+    // a call on ../documents/:doc_id
+    per_document_id: bool,
+    // if a filter was used
+    per_filter: bool,
+
+    #[serde(rename = "vector.retrieve_vectors")]
+    retrieve_vectors: bool,
+
+    // pagination
+    #[serde(rename = "pagination.max_limit")]
+    max_limit: usize,
+    #[serde(rename = "pagination.max_offset")]
+    max_offset: usize,
+
+    marker: std::marker::PhantomData<Method>,
+}
+
+#[derive(Copy, Clone, Debug, PartialEq, Eq)]
+pub enum DocumentFetchKind {
+    PerDocumentId { retrieve_vectors: bool },
+    Normal { with_filter: bool, limit: usize, offset: usize, retrieve_vectors: bool },
+}
+
+impl<Method: AggregateMethod> DocumentsFetchAggregator<Method> {
+    pub fn from_query(query: &DocumentFetchKind) -> Self {
+        let (limit, offset, retrieve_vectors) = match query {
+            DocumentFetchKind::PerDocumentId { retrieve_vectors } => (1, 0, *retrieve_vectors),
+            DocumentFetchKind::Normal { limit, offset, retrieve_vectors, .. } => {
+                (*limit, *offset, *retrieve_vectors)
+            }
+        };
+
+        Self {
+            per_document_id: matches!(query, DocumentFetchKind::PerDocumentId { .. }),
+            per_filter: matches!(query, DocumentFetchKind::Normal { with_filter, .. } if *with_filter),
+            max_limit: limit,
+            max_offset: offset,
+            retrieve_vectors,
+
+            marker: PhantomData,
+        }
+    }
+}
+
+impl<Method: AggregateMethod> Aggregate for DocumentsFetchAggregator<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            per_document_id: self.per_document_id | new.per_document_id,
+            per_filter: self.per_filter | new.per_filter,
+            retrieve_vectors: self.retrieve_vectors | new.retrieve_vectors,
+            max_limit: self.max_limit.max(new.max_limit),
+            max_offset: self.max_offset.max(new.max_offset),
+            marker: PhantomData,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 pub async fn get_document(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_GET }>, Data<IndexScheduler>>,
     document_param: web::Path<DocumentParam>,
     params: AwebQueryParameter<GetDocument, DeserrQueryParamError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let DocumentParam { index_uid, document_id } = document_param.into_inner();
     debug!(parameters = ?params, "Get document");
@@ -117,8 +191,15 @@ pub async fn get_document(
     let features = index_scheduler.features();
     let retrieve_vectors = RetrieveVectors::new(param_retrieve_vectors.0, features)?;
 
-    analytics.get_fetch_documents(
-        &DocumentFetchKind::PerDocumentId { retrieve_vectors: param_retrieve_vectors.0 },
+    analytics.publish(
+        DocumentsFetchAggregator::<DocumentsGET> {
+            retrieve_vectors: param_retrieve_vectors.0,
+            per_document_id: true,
+            per_filter: false,
+            max_limit: 0,
+            max_offset: 0,
+            marker: PhantomData,
+        },
         &req,
     );
 
@@ -129,17 +210,52 @@ pub async fn get_document(
     Ok(HttpResponse::Ok().json(document))
 }
 
+#[derive(Serialize)]
+pub struct DocumentsDeletionAggregator {
+    per_document_id: bool,
+    clear_all: bool,
+    per_batch: bool,
+    per_filter: bool,
+}
+
+impl Aggregate for DocumentsDeletionAggregator {
+    fn event_name(&self) -> &'static str {
+        "Documents Deleted"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            per_document_id: self.per_document_id | new.per_document_id,
+            clear_all: self.clear_all | new.clear_all,
+            per_batch: self.per_batch | new.per_batch,
+            per_filter: self.per_filter | new.per_filter,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 pub async fn delete_document(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
     path: web::Path<DocumentParam>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let DocumentParam { index_uid, document_id } = path.into_inner();
     let index_uid = IndexUid::try_from(index_uid)?;
 
-    analytics.delete_documents(DocumentDeletionKind::PerDocumentId, &req);
+    analytics.publish(
+        DocumentsDeletionAggregator {
+            per_document_id: true,
+            clear_all: false,
+            per_batch: false,
+            per_filter: false,
+        },
+        &req,
+    );
 
     let task = KindWithContent::DocumentDeletion {
         index_uid: index_uid.to_string(),
@@ -190,17 +306,19 @@ pub async fn documents_by_query_post(
     index_uid: web::Path<String>,
     body: AwebJson<BrowseQuery, DeserrJsonError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let body = body.into_inner();
     debug!(parameters = ?body, "Get documents POST");
 
-    analytics.post_fetch_documents(
-        &DocumentFetchKind::Normal {
-            with_filter: body.filter.is_some(),
-            limit: body.limit,
-            offset: body.offset,
+    analytics.publish(
+        DocumentsFetchAggregator::<DocumentsPOST> {
+            per_filter: body.filter.is_some(),
             retrieve_vectors: body.retrieve_vectors,
+            max_limit: body.limit,
+            max_offset: body.offset,
+            per_document_id: false,
+            marker: PhantomData,
         },
         &req,
     );
@@ -213,7 +331,7 @@ pub async fn get_documents(
     index_uid: web::Path<String>,
     params: AwebQueryParameter<BrowseQueryGet, DeserrQueryParamError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?params, "Get documents GET");
 
@@ -235,12 +353,14 @@ pub async fn get_documents(
         filter,
     };
 
-    analytics.get_fetch_documents(
-        &DocumentFetchKind::Normal {
-            with_filter: query.filter.is_some(),
-            limit: query.limit,
-            offset: query.offset,
+    analytics.publish(
+        DocumentsFetchAggregator::<DocumentsGET> {
+            per_filter: query.filter.is_some(),
             retrieve_vectors: query.retrieve_vectors,
+            max_limit: query.limit,
+            max_offset: query.offset,
+            per_document_id: false,
+            marker: PhantomData,
         },
         &req,
     );
@@ -298,6 +418,39 @@ fn from_char_csv_delimiter(
     }
 }
 
+aggregate_methods!(
+    Replaced => "Documents Added",
+    Updated => "Documents Updated",
+);
+
+#[derive(Serialize)]
+pub struct DocumentsAggregator<T: AggregateMethod> {
+    payload_types: HashSet<String>,
+    primary_key: HashSet<String>,
+    index_creation: bool,
+    #[serde(skip)]
+    method: PhantomData<T>,
+}
+
+impl<Method: AggregateMethod> Aggregate for DocumentsAggregator<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            payload_types: self.payload_types.union(&new.payload_types).cloned().collect(),
+            primary_key: self.primary_key.union(&new.primary_key).cloned().collect(),
+            index_creation: self.index_creation | new.index_creation,
+            method: PhantomData,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(self).unwrap_or_default()
+    }
+}
+
 pub async fn replace_documents(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ADD }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
@@ -305,16 +458,32 @@ pub async fn replace_documents(
     body: Payload,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     debug!(parameters = ?params, "Replace documents");
     let params = params.into_inner();
 
-    analytics.add_documents(
-        &params,
-        index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
+    let mut content_types = HashSet::new();
+    let content_type = req
+        .headers()
+        .get(CONTENT_TYPE)
+        .and_then(|s| s.to_str().ok())
+        .unwrap_or("unknown")
+        .to_string();
+    content_types.insert(content_type);
+    let mut primary_keys = HashSet::new();
+    if let Some(primary_key) = params.primary_key.clone() {
+        primary_keys.insert(primary_key);
+    }
+    analytics.publish(
+        DocumentsAggregator::<Replaced> {
+            payload_types: content_types,
+            primary_key: primary_keys,
+            index_creation: index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
+            method: PhantomData,
+        },
         &req,
     );
 
@@ -346,16 +515,32 @@ pub async fn update_documents(
     body: Payload,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let params = params.into_inner();
     debug!(parameters = ?params, "Update documents");
 
-    analytics.add_documents(
-        &params,
-        index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
+    let mut content_types = HashSet::new();
+    let content_type = req
+        .headers()
+        .get(CONTENT_TYPE)
+        .and_then(|s| s.to_str().ok())
+        .unwrap_or("unknown")
+        .to_string();
+    content_types.insert(content_type);
+    let mut primary_keys = HashSet::new();
+    if let Some(primary_key) = params.primary_key.clone() {
+        primary_keys.insert(primary_key);
+    }
+    analytics.publish(
+        DocumentsAggregator::<Updated> {
+            payload_types: content_types,
+            primary_key: primary_keys,
+            index_creation: index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
+            method: PhantomData,
+        },
         &req,
     );
 
@@ -524,12 +709,20 @@ pub async fn delete_documents_batch(
     body: web::Json<Vec<Value>>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?body, "Delete documents by batch");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
-    analytics.delete_documents(DocumentDeletionKind::PerBatch, &req);
+    analytics.publish(
+        DocumentsDeletionAggregator {
+            per_batch: true,
+            per_document_id: false,
+            clear_all: false,
+            per_filter: false,
+        },
+        &req,
+    );
 
     let ids = body
         .iter()
@@ -562,14 +755,22 @@ pub async fn delete_documents_by_filter(
     body: AwebJson<DocumentDeletionByFilter, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?body, "Delete documents by filter");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let index_uid = index_uid.into_inner();
     let filter = body.into_inner().filter;
 
-    analytics.delete_documents(DocumentDeletionKind::PerFilter, &req);
+    analytics.publish(
+        DocumentsDeletionAggregator {
+            per_filter: true,
+            per_document_id: false,
+            clear_all: false,
+            per_batch: false,
+        },
+        &req,
+    );
 
     // we ensure the filter is well formed before enqueuing it
     crate::search::parse_filter(&filter, Code::InvalidDocumentFilter, index_scheduler.features())?
@@ -599,13 +800,41 @@ pub struct DocumentEditionByFunction {
     pub function: String,
 }
 
+#[derive(Serialize)]
+struct EditDocumentsByFunctionAggregator {
+    // Set to true if at least one request was filtered
+    filtered: bool,
+    // Set to true if at least one request contained a context
+    with_context: bool,
+
+    index_creation: bool,
+}
+
+impl Aggregate for EditDocumentsByFunctionAggregator {
+    fn event_name(&self) -> &'static str {
+        "Documents Edited By Function"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            filtered: self.filtered | new.filtered,
+            with_context: self.with_context | new.with_context,
+            index_creation: self.index_creation | new.index_creation,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 pub async fn edit_documents_by_function(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ALL }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
     params: AwebJson<DocumentEditionByFunction, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?params, "Edit documents by function");
 
@@ -617,9 +846,12 @@ pub async fn edit_documents_by_function(
     let index_uid = index_uid.into_inner();
     let params = params.into_inner();
 
-    analytics.update_documents_by_function(
-        &params,
-        index_scheduler.index(&index_uid).is_err(),
+    analytics.publish(
+        EditDocumentsByFunctionAggregator {
+            filtered: params.filter.is_some(),
+            with_context: params.context.is_some(),
+            index_creation: index_scheduler.index(&index_uid).is_err(),
+        },
         &req,
     );
 
@@ -670,10 +902,18 @@ pub async fn clear_all_documents(
     index_uid: web::Path<String>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-    analytics.delete_documents(DocumentDeletionKind::ClearAll, &req);
+    analytics.publish(
+        DocumentsDeletionAggregator {
+            clear_all: true,
+            per_document_id: false,
+            per_batch: false,
+            per_filter: false,
+        },
+        &req,
+    );
 
     let task = KindWithContent::DocumentClear { index_uid: index_uid.to_string() };
     let uid = get_task_id(&req, &opt)?;

meilisearch/src/routes/indexes/facet_search.rs

@@ -1,3 +1,5 @@
+use std::collections::{BinaryHeap, HashSet};
+
 use actix_web::web::Data;
 use actix_web::{web, HttpRequest, HttpResponse};
 use deserr::actix_web::AwebJson;
@@ -10,14 +12,15 @@ use meilisearch_types::locales::Locale;
 use serde_json::Value;
 use tracing::debug;
 
-use crate::analytics::{Analytics, FacetSearchAggregator};
+use crate::analytics::{Aggregate, Analytics};
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::routes::indexes::search::search_kind;
 use crate::search::{
-    add_search_rules, perform_facet_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
-    SearchQuery, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
+    add_search_rules, perform_facet_search, FacetSearchResult, HybridQuery, MatchingStrategy,
+    RankingScoreThreshold, SearchQuery, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+    DEFAULT_SEARCH_OFFSET,
 };
 use crate::search_queue::SearchQueue;
 
@@ -53,20 +56,122 @@ pub struct FacetSearchQuery {
     pub locales: Option<Vec<Locale>>,
 }
 
+#[derive(Default)]
+pub struct FacetSearchAggregator {
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // The set of all facetNames that were used
+    facet_names: HashSet<String>,
+
+    // As there been any other parameter than the facetName or facetQuery ones?
+    additional_search_parameters_provided: bool,
+}
+
+impl FacetSearchAggregator {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &FacetSearchQuery) -> Self {
+        let FacetSearchQuery {
+            facet_query: _,
+            facet_name,
+            vector,
+            q,
+            filter,
+            matching_strategy,
+            attributes_to_search_on,
+            hybrid,
+            ranking_score_threshold,
+            locales,
+        } = query;
+
+        Self {
+            total_received: 1,
+            facet_names: Some(facet_name.clone()).into_iter().collect(),
+            additional_search_parameters_provided: q.is_some()
+                || vector.is_some()
+                || filter.is_some()
+                || *matching_strategy != MatchingStrategy::default()
+                || attributes_to_search_on.is_some()
+                || hybrid.is_some()
+                || ranking_score_threshold.is_some()
+                || locales.is_some(),
+            ..Default::default()
+        }
+    }
+
+    pub fn succeed(&mut self, result: &FacetSearchResult) {
+        let FacetSearchResult { facet_hits: _, facet_query: _, processing_time_ms } = result;
+        self.total_succeeded = 1;
+        self.time_spent.push(*processing_time_ms as usize);
+    }
+}
+
+impl Aggregate for FacetSearchAggregator {
+    fn event_name(&self) -> &'static str {
+        "Facet Searched POST"
+    }
+
+    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        for time in new.time_spent {
+            self.time_spent.push(time);
+        }
+
+        Box::new(Self {
+            total_received: self.total_received.saturating_add(new.total_received),
+            total_succeeded: self.total_succeeded.saturating_add(new.total_succeeded),
+            time_spent: self.time_spent,
+            facet_names: self.facet_names.union(&new.facet_names).cloned().collect(),
+            additional_search_parameters_provided: self.additional_search_parameters_provided
+                | new.additional_search_parameters_provided,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            time_spent,
+            facet_names,
+            additional_search_parameters_provided,
+        } = *self;
+        // the index of the 99th percentage of value
+        let percentile_99th = 0.99 * (total_succeeded as f64 - 1.) + 1.;
+        // we get all the values in a sorted manner
+        let time_spent = time_spent.into_sorted_vec();
+        // We are only interested by the slowest value of the 99th fastest results
+        let time_spent = time_spent.get(percentile_99th as usize);
+
+        serde_json::json!({
+            "requests": {
+                "99th_response_time":  time_spent.map(|t| format!("{:.2}", t)),
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+            },
+            "facets": {
+                "total_distinct_facet_count": facet_names.len(),
+                "additional_search_parameters_provided": additional_search_parameters_provided,
+            },
+        })
+    }
+}
+
 pub async fn search(
     index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
     search_queue: Data<SearchQueue>,
     index_uid: web::Path<String>,
     params: AwebJson<FacetSearchQuery, DeserrJsonError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let query = params.into_inner();
     debug!(parameters = ?query, "Facet search");
 
-    let mut aggregate = FacetSearchAggregator::from_query(&query, &req);
+    let mut aggregate = FacetSearchAggregator::from_query(&query);
 
     let facet_query = query.facet_query.clone();
     let facet_name = query.facet_name.clone();
@@ -81,7 +186,7 @@ pub async fn search(
     let index = index_scheduler.index(&index_uid)?;
     let features = index_scheduler.features();
     let search_kind = search_kind(&search_query, &index_scheduler, &index, features)?;
-    let _permit = search_queue.try_get_search_permit().await?;
+    let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
         perform_facet_search(
             &index,
@@ -93,12 +198,14 @@ pub async fn search(
             locales,
         )
     })
-    .await?;
+    .await;
+    permit.drop().await;
+    let search_result = search_result?;
 
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
     }
-    analytics.post_facet_search(aggregate);
+    analytics.publish(aggregate, &req);
 
     let search_result = search_result?;
 

meilisearch/src/routes/indexes/mod.rs

@@ -1,3 +1,4 @@
+use std::collections::BTreeSet;
 use std::convert::Infallible;
 
 use actix_web::web::Data;
@@ -13,12 +14,11 @@ use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::milli::{self, FieldDistribution, Index};
 use meilisearch_types::tasks::KindWithContent;
 use serde::Serialize;
-use serde_json::json;
 use time::OffsetDateTime;
 use tracing::debug;
 
 use super::{get_task_id, Pagination, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT};
-use crate::analytics::Analytics;
+use crate::analytics::{Aggregate, Analytics};
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::{AuthenticationError, GuardedData};
 use crate::extractors::sequential_extractor::SeqHandler;
@@ -28,8 +28,11 @@ use crate::Opt;
 pub mod documents;
 pub mod facet_search;
 pub mod search;
+mod search_analytics;
 pub mod settings;
+mod settings_analytics;
 pub mod similar;
+mod similar_analytics;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
@@ -123,12 +126,31 @@ pub struct IndexCreateRequest {
     primary_key: Option<String>,
 }
 
+#[derive(Serialize)]
+struct IndexCreatedAggregate {
+    primary_key: BTreeSet<String>,
+}
+
+impl Aggregate for IndexCreatedAggregate {
+    fn event_name(&self) -> &'static str {
+        "Index Created"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self { primary_key: self.primary_key.union(&new.primary_key).cloned().collect() })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 pub async fn create_index(
     index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_CREATE }>, Data<IndexScheduler>>,
     body: AwebJson<IndexCreateRequest, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?body, "Create index");
     let IndexCreateRequest { primary_key, uid } = body.into_inner();
@@ -136,9 +158,8 @@ pub async fn create_index(
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&uid);
     if allow_index_creation {
         analytics.publish(
-            "Index Created".to_string(),
-            json!({ "primary_key": primary_key }),
-            Some(&req),
+            IndexCreatedAggregate { primary_key: primary_key.iter().cloned().collect() },
+            &req,
         );
 
         let task = KindWithContent::IndexCreation { index_uid: uid.to_string(), primary_key };
@@ -194,21 +215,38 @@ pub async fn get_index(
     Ok(HttpResponse::Ok().json(index_view))
 }
 
+#[derive(Serialize)]
+struct IndexUpdatedAggregate {
+    primary_key: BTreeSet<String>,
+}
+
+impl Aggregate for IndexUpdatedAggregate {
+    fn event_name(&self) -> &'static str {
+        "Index Updated"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self { primary_key: self.primary_key.union(&new.primary_key).cloned().collect() })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
 pub async fn update_index(
     index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_UPDATE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
     body: AwebJson<UpdateIndexRequest, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?body, "Update index");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let body = body.into_inner();
     analytics.publish(
-        "Index Updated".to_string(),
-        json!({ "primary_key": body.primary_key }),
-        Some(&req),
+        IndexUpdatedAggregate { primary_key: body.primary_key.iter().cloned().collect() },
+        &req,
     );
 
     let task = KindWithContent::IndexUpdate {

meilisearch/src/routes/indexes/search.rs

@@ -13,12 +13,13 @@ use meilisearch_types::serde_cs::vec::CS;
 use serde_json::Value;
 use tracing::debug;
 
-use crate::analytics::{Analytics, SearchAggregator};
+use crate::analytics::Analytics;
 use crate::error::MeilisearchHttpError;
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
 use crate::metrics::MEILISEARCH_DEGRADED_SEARCH_REQUESTS;
+use crate::routes::indexes::search_analytics::{SearchAggregator, SearchGET, SearchPOST};
 use crate::search::{
     add_search_rules, perform_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
     RetrieveVectors, SearchKind, SearchQuery, SemanticRatio, DEFAULT_CROP_LENGTH,
@@ -128,8 +129,10 @@ impl std::ops::Deref for SemanticRatioGet {
     }
 }
 
-impl From<SearchQueryGet> for SearchQuery {
-    fn from(other: SearchQueryGet) -> Self {
+impl TryFrom<SearchQueryGet> for SearchQuery {
+    type Error = ResponseError;
+
+    fn try_from(other: SearchQueryGet) -> Result<Self, Self::Error> {
         let filter = match other.filter {
             Some(f) => match serde_json::from_str(&f) {
                 Ok(v) => Some(v),
@@ -140,19 +143,28 @@ impl From<SearchQueryGet> for SearchQuery {
 
         let hybrid = match (other.hybrid_embedder, other.hybrid_semantic_ratio) {
             (None, None) => None,
-            (None, Some(semantic_ratio)) => {
-                Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder: None })
+            (None, Some(_)) => {
+                return Err(ResponseError::from_msg(
+                    "`hybridEmbedder` is mandatory when `hybridSemanticRatio` is present".into(),
+                    meilisearch_types::error::Code::InvalidHybridQuery,
+                ));
+            }
+            (Some(embedder), None) => {
+                Some(HybridQuery { semantic_ratio: DEFAULT_SEMANTIC_RATIO(), embedder })
             }
-            (Some(embedder), None) => Some(HybridQuery {
-                semantic_ratio: DEFAULT_SEMANTIC_RATIO(),
-                embedder: Some(embedder),
-            }),
             (Some(embedder), Some(semantic_ratio)) => {
-                Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder: Some(embedder) })
+                Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder })
             }
         };
 
-        Self {
+        if other.vector.is_some() && hybrid.is_none() {
+            return Err(ResponseError::from_msg(
+                "`hybridEmbedder` is mandatory when `vector` is present".into(),
+                meilisearch_types::error::Code::MissingSearchHybrid,
+            ));
+        }
+
+        Ok(Self {
             q: other.q,
             vector: other.vector.map(CS::into_inner),
             offset: other.offset.0,
@@ -179,7 +191,7 @@ impl From<SearchQueryGet> for SearchQuery {
             hybrid,
             ranking_score_threshold: other.ranking_score_threshold.map(|o| o.0),
             locales: other.locales.map(|o| o.into_iter().collect()),
-        }
+        })
     }
 }
 
@@ -214,34 +226,36 @@ pub async fn search_with_url_query(
     index_uid: web::Path<String>,
     params: AwebQueryParameter<SearchQueryGet, DeserrQueryParamError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?params, "Search get");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
-    let mut query: SearchQuery = params.into_inner().into();
+    let mut query: SearchQuery = params.into_inner().try_into()?;
 
     // Tenant token search_rules.
     if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
         add_search_rules(&mut query.filter, search_rules);
     }
 
-    let mut aggregate = SearchAggregator::from_query(&query, &req);
+    let mut aggregate = SearchAggregator::<SearchGET>::from_query(&query);
 
     let index = index_scheduler.index(&index_uid)?;
     let features = index_scheduler.features();
 
     let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
     let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)?;
-    let _permit = search_queue.try_get_search_permit().await?;
+    let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
         perform_search(&index, query, search_kind, retrieve_vector, index_scheduler.features())
     })
-    .await?;
+    .await;
+    permit.drop().await;
+    let search_result = search_result?;
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
     }
-    analytics.get_search(aggregate);
+    analytics.publish(aggregate, &req);
 
     let search_result = search_result?;
 
@@ -255,7 +269,7 @@ pub async fn search_with_post(
     index_uid: web::Path<String>,
     params: AwebJson<SearchQuery, DeserrJsonError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
@@ -267,7 +281,7 @@ pub async fn search_with_post(
         add_search_rules(&mut query.filter, search_rules);
     }
 
-    let mut aggregate = SearchAggregator::from_query(&query, &req);
+    let mut aggregate = SearchAggregator::<SearchPOST>::from_query(&query);
 
     let index = index_scheduler.index(&index_uid)?;
 
@@ -276,18 +290,20 @@ pub async fn search_with_post(
     let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
     let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
 
-    let _permit = search_queue.try_get_search_permit().await?;
+    let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
         perform_search(&index, query, search_kind, retrieve_vectors, index_scheduler.features())
     })
-    .await?;
+    .await;
+    permit.drop().await;
+    let search_result = search_result?;
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
         if search_result.degraded {
             MEILISEARCH_DEGRADED_SEARCH_REQUESTS.inc();
         }
     }
-    analytics.post_search(aggregate);
+    analytics.publish(aggregate, &req);
 
     let search_result = search_result?;
 
@@ -308,44 +324,36 @@ pub fn search_kind(
         features.check_vector("Passing `hybrid` as a parameter")?;
     }
 
-    // regardless of anything, always do a keyword search when we don't have a vector and the query is whitespace or missing
-    if query.vector.is_none() {
-        match &query.q {
-            Some(q) if q.trim().is_empty() => return Ok(SearchKind::KeywordOnly),
-            None => return Ok(SearchKind::KeywordOnly),
-            _ => {}
+    // handle with care, the order of cases matters, the semantics is subtle
+    match (query.q.as_deref(), &query.hybrid, query.vector.as_deref()) {
+        // empty query, no vector => placeholder search
+        (Some(q), _, None) if q.trim().is_empty() => Ok(SearchKind::KeywordOnly),
+        // no query, no vector => placeholder search
+        (None, _, None) => Ok(SearchKind::KeywordOnly),
+        // hybrid.semantic_ratio == 1.0 => vector
+        (_, Some(HybridQuery { semantic_ratio, embedder }), v) if **semantic_ratio == 1.0 => {
+            SearchKind::semantic(index_scheduler, index, embedder, v.map(|v| v.len()))
         }
-    }
-
-    match &query.hybrid {
-        Some(HybridQuery { semantic_ratio, embedder }) if **semantic_ratio == 1.0 => {
-            Ok(SearchKind::semantic(
-                index_scheduler,
-                index,
-                embedder.as_deref(),
-                query.vector.as_ref().map(Vec::len),
-            )?)
-        }
-        Some(HybridQuery { semantic_ratio, embedder: _ }) if **semantic_ratio == 0.0 => {
+        // hybrid.semantic_ratio == 0.0 => keyword
+        (_, Some(HybridQuery { semantic_ratio, embedder: _ }), _) if **semantic_ratio == 0.0 => {
             Ok(SearchKind::KeywordOnly)
         }
-        Some(HybridQuery { semantic_ratio, embedder }) => Ok(SearchKind::hybrid(
+        // no query, hybrid, vector => semantic
+        (None, Some(HybridQuery { semantic_ratio: _, embedder }), Some(v)) => {
+            SearchKind::semantic(index_scheduler, index, embedder, Some(v.len()))
+        }
+        // query, no hybrid, no vector => keyword
+        (Some(_), None, None) => Ok(SearchKind::KeywordOnly),
+        // query, hybrid, maybe vector => hybrid
+        (Some(_), Some(HybridQuery { semantic_ratio, embedder }), v) => SearchKind::hybrid(
             index_scheduler,
             index,
-            embedder.as_deref(),
+            embedder,
             **semantic_ratio,
-            query.vector.as_ref().map(Vec::len),
-        )?),
-        None => match (query.q.as_deref(), query.vector.as_deref()) {
-            (_query, None) => Ok(SearchKind::KeywordOnly),
-            (None, Some(_vector)) => Ok(SearchKind::semantic(
-                index_scheduler,
-                index,
-                None,
-                query.vector.as_ref().map(Vec::len),
-            )?),
-            (Some(_), Some(_)) => Err(MeilisearchHttpError::MissingSearchHybrid.into()),
-        },
+            v.map(|v| v.len()),
+        ),
+
+        (_, None, Some(_)) => Err(MeilisearchHttpError::MissingSearchHybrid.into()),
     }
 }
 

meilisearch/src/routes/indexes/search_analytics.rs

@@ -0,0 +1,485 @@
+use once_cell::sync::Lazy;
+use regex::Regex;
+use serde_json::{json, Value};
+use std::collections::{BTreeSet, BinaryHeap, HashMap};
+
+use meilisearch_types::locales::Locale;
+
+use crate::{
+    aggregate_methods,
+    analytics::{Aggregate, AggregateMethod},
+    search::{
+        SearchQuery, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+        DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+        DEFAULT_SEMANTIC_RATIO,
+    },
+};
+
+aggregate_methods!(
+    SearchGET => "Documents Searched GET",
+    SearchPOST => "Documents Searched POST",
+);
+
+#[derive(Default)]
+pub struct SearchAggregator<Method: AggregateMethod> {
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    total_degraded: usize,
+    total_used_negative_operator: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // sort
+    sort_with_geo_point: bool,
+    // every time a request has a filter, this field must be incremented by the number of terms it contains
+    sort_sum_of_criteria_terms: usize,
+    // every time a request has a filter, this field must be incremented by one
+    sort_total_number_of_criteria: usize,
+
+    // distinct
+    distinct: bool,
+
+    // filter
+    filter_with_geo_radius: bool,
+    filter_with_geo_bounding_box: bool,
+    // every time a request has a filter, this field must be incremented by the number of terms it contains
+    filter_sum_of_criteria_terms: usize,
+    // every time a request has a filter, this field must be incremented by one
+    filter_total_number_of_criteria: usize,
+    used_syntax: HashMap<String, usize>,
+
+    // attributes_to_search_on
+    // every time a search is done using attributes_to_search_on
+    attributes_to_search_on_total_number_of_uses: usize,
+
+    // q
+    // The maximum number of terms in a q request
+    max_terms_number: usize,
+
+    // vector
+    // The maximum number of floats in a vector request
+    max_vector_size: usize,
+    // Whether the semantic ratio passed to a hybrid search equals the default ratio.
+    semantic_ratio: bool,
+    hybrid: bool,
+    retrieve_vectors: bool,
+
+    // every time a search is done, we increment the counter linked to the used settings
+    matching_strategy: HashMap<String, usize>,
+
+    // List of the unique Locales passed as parameter
+    locales: BTreeSet<Locale>,
+
+    // pagination
+    max_limit: usize,
+    max_offset: usize,
+    finite_pagination: usize,
+
+    // formatting
+    max_attributes_to_retrieve: usize,
+    max_attributes_to_highlight: usize,
+    highlight_pre_tag: bool,
+    highlight_post_tag: bool,
+    max_attributes_to_crop: usize,
+    crop_marker: bool,
+    show_matches_position: bool,
+    crop_length: bool,
+
+    // facets
+    facets_sum_of_terms: usize,
+    facets_total_number_of_facets: usize,
+
+    // scoring
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+    ranking_score_threshold: bool,
+
+    marker: std::marker::PhantomData<Method>,
+}
+
+impl<Method: AggregateMethod> SearchAggregator<Method> {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &SearchQuery) -> Self {
+        let SearchQuery {
+            q,
+            vector,
+            offset,
+            limit,
+            page,
+            hits_per_page,
+            attributes_to_retrieve: _,
+            retrieve_vectors,
+            attributes_to_crop: _,
+            crop_length,
+            attributes_to_highlight: _,
+            show_matches_position,
+            show_ranking_score,
+            show_ranking_score_details,
+            filter,
+            sort,
+            distinct,
+            facets: _,
+            highlight_pre_tag,
+            highlight_post_tag,
+            crop_marker,
+            matching_strategy,
+            attributes_to_search_on,
+            hybrid,
+            ranking_score_threshold,
+            locales,
+        } = query;
+
+        let mut ret = Self::default();
+
+        ret.total_received = 1;
+
+        if let Some(ref sort) = sort {
+            ret.sort_total_number_of_criteria = 1;
+            ret.sort_with_geo_point = sort.iter().any(|s| s.contains("_geoPoint("));
+            ret.sort_sum_of_criteria_terms = sort.len();
+        }
+
+        ret.distinct = distinct.is_some();
+
+        if let Some(ref filter) = filter {
+            static RE: Lazy<Regex> = Lazy::new(|| Regex::new("AND | OR").unwrap());
+            ret.filter_total_number_of_criteria = 1;
+
+            let syntax = match filter {
+                Value::String(_) => "string".to_string(),
+                Value::Array(values) => {
+                    if values.iter().map(|v| v.to_string()).any(|s| RE.is_match(&s)) {
+                        "mixed".to_string()
+                    } else {
+                        "array".to_string()
+                    }
+                }
+                _ => "none".to_string(),
+            };
+            // convert the string to a HashMap
+            ret.used_syntax.insert(syntax, 1);
+
+            let stringified_filters = filter.to_string();
+            ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
+            ret.filter_with_geo_bounding_box = stringified_filters.contains("_geoBoundingBox(");
+            ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
+        }
+
+        // attributes_to_search_on
+        if attributes_to_search_on.is_some() {
+            ret.attributes_to_search_on_total_number_of_uses = 1;
+        }
+
+        if let Some(ref q) = q {
+            ret.max_terms_number = q.split_whitespace().count();
+        }
+
+        if let Some(ref vector) = vector {
+            ret.max_vector_size = vector.len();
+        }
+        ret.retrieve_vectors |= retrieve_vectors;
+
+        if query.is_finite_pagination() {
+            let limit = hits_per_page.unwrap_or_else(DEFAULT_SEARCH_LIMIT);
+            ret.max_limit = limit;
+            ret.max_offset = page.unwrap_or(1).saturating_sub(1) * limit;
+            ret.finite_pagination = 1;
+        } else {
+            ret.max_limit = *limit;
+            ret.max_offset = *offset;
+            ret.finite_pagination = 0;
+        }
+
+        ret.matching_strategy.insert(format!("{:?}", matching_strategy), 1);
+
+        if let Some(locales) = locales {
+            ret.locales = locales.iter().copied().collect();
+        }
+
+        ret.highlight_pre_tag = *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG();
+        ret.highlight_post_tag = *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG();
+        ret.crop_marker = *crop_marker != DEFAULT_CROP_MARKER();
+        ret.crop_length = *crop_length != DEFAULT_CROP_LENGTH();
+        ret.show_matches_position = *show_matches_position;
+
+        ret.show_ranking_score = *show_ranking_score;
+        ret.show_ranking_score_details = *show_ranking_score_details;
+        ret.ranking_score_threshold = ranking_score_threshold.is_some();
+
+        if let Some(hybrid) = hybrid {
+            ret.semantic_ratio = hybrid.semantic_ratio != DEFAULT_SEMANTIC_RATIO();
+            ret.hybrid = true;
+        }
+
+        ret
+    }
+
+    pub fn succeed(&mut self, result: &SearchResult) {
+        let SearchResult {
+            hits: _,
+            query: _,
+            processing_time_ms,
+            hits_info: _,
+            semantic_hit_count: _,
+            facet_distribution: _,
+            facet_stats: _,
+            degraded,
+            used_negative_operator,
+        } = result;
+
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+        if *degraded {
+            self.total_degraded = self.total_degraded.saturating_add(1);
+        }
+        if *used_negative_operator {
+            self.total_used_negative_operator = self.total_used_negative_operator.saturating_add(1);
+        }
+        self.time_spent.push(*processing_time_ms as usize);
+    }
+}
+
+impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        let Self {
+            total_received,
+            total_succeeded,
+            mut time_spent,
+            sort_with_geo_point,
+            sort_sum_of_criteria_terms,
+            sort_total_number_of_criteria,
+            distinct,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            attributes_to_search_on_total_number_of_uses,
+            max_terms_number,
+            max_vector_size,
+            retrieve_vectors,
+            matching_strategy,
+            max_limit,
+            max_offset,
+            finite_pagination,
+            max_attributes_to_retrieve,
+            max_attributes_to_highlight,
+            highlight_pre_tag,
+            highlight_post_tag,
+            max_attributes_to_crop,
+            crop_marker,
+            show_matches_position,
+            crop_length,
+            facets_sum_of_terms,
+            facets_total_number_of_facets,
+            show_ranking_score,
+            show_ranking_score_details,
+            semantic_ratio,
+            hybrid,
+            total_degraded,
+            total_used_negative_operator,
+            ranking_score_threshold,
+            mut locales,
+            marker: _,
+        } = *new;
+
+        // request
+        self.total_received = self.total_received.saturating_add(total_received);
+        self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
+        self.total_degraded = self.total_degraded.saturating_add(total_degraded);
+        self.total_used_negative_operator =
+            self.total_used_negative_operator.saturating_add(total_used_negative_operator);
+        self.time_spent.append(&mut time_spent);
+
+        // sort
+        self.sort_with_geo_point |= sort_with_geo_point;
+        self.sort_sum_of_criteria_terms =
+            self.sort_sum_of_criteria_terms.saturating_add(sort_sum_of_criteria_terms);
+        self.sort_total_number_of_criteria =
+            self.sort_total_number_of_criteria.saturating_add(sort_total_number_of_criteria);
+
+        // distinct
+        self.distinct |= distinct;
+
+        // filter
+        self.filter_with_geo_radius |= filter_with_geo_radius;
+        self.filter_with_geo_bounding_box |= filter_with_geo_bounding_box;
+        self.filter_sum_of_criteria_terms =
+            self.filter_sum_of_criteria_terms.saturating_add(filter_sum_of_criteria_terms);
+        self.filter_total_number_of_criteria =
+            self.filter_total_number_of_criteria.saturating_add(filter_total_number_of_criteria);
+        for (key, value) in used_syntax.into_iter() {
+            let used_syntax = self.used_syntax.entry(key).or_insert(0);
+            *used_syntax = used_syntax.saturating_add(value);
+        }
+
+        // attributes_to_search_on
+        self.attributes_to_search_on_total_number_of_uses = self
+            .attributes_to_search_on_total_number_of_uses
+            .saturating_add(attributes_to_search_on_total_number_of_uses);
+
+        // q
+        self.max_terms_number = self.max_terms_number.max(max_terms_number);
+
+        // vector
+        self.max_vector_size = self.max_vector_size.max(max_vector_size);
+        self.retrieve_vectors |= retrieve_vectors;
+        self.semantic_ratio |= semantic_ratio;
+        self.hybrid |= hybrid;
+
+        // pagination
+        self.max_limit = self.max_limit.max(max_limit);
+        self.max_offset = self.max_offset.max(max_offset);
+        self.finite_pagination += finite_pagination;
+
+        // formatting
+        self.max_attributes_to_retrieve =
+            self.max_attributes_to_retrieve.max(max_attributes_to_retrieve);
+        self.max_attributes_to_highlight =
+            self.max_attributes_to_highlight.max(max_attributes_to_highlight);
+        self.highlight_pre_tag |= highlight_pre_tag;
+        self.highlight_post_tag |= highlight_post_tag;
+        self.max_attributes_to_crop = self.max_attributes_to_crop.max(max_attributes_to_crop);
+        self.crop_marker |= crop_marker;
+        self.show_matches_position |= show_matches_position;
+        self.crop_length |= crop_length;
+
+        // facets
+        self.facets_sum_of_terms = self.facets_sum_of_terms.saturating_add(facets_sum_of_terms);
+        self.facets_total_number_of_facets =
+            self.facets_total_number_of_facets.saturating_add(facets_total_number_of_facets);
+
+        // matching strategy
+        for (key, value) in matching_strategy.into_iter() {
+            let matching_strategy = self.matching_strategy.entry(key).or_insert(0);
+            *matching_strategy = matching_strategy.saturating_add(value);
+        }
+
+        // scoring
+        self.show_ranking_score |= show_ranking_score;
+        self.show_ranking_score_details |= show_ranking_score_details;
+        self.ranking_score_threshold |= ranking_score_threshold;
+
+        // locales
+        self.locales.append(&mut locales);
+
+        self
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            time_spent,
+            sort_with_geo_point,
+            sort_sum_of_criteria_terms,
+            sort_total_number_of_criteria,
+            distinct,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            attributes_to_search_on_total_number_of_uses,
+            max_terms_number,
+            max_vector_size,
+            retrieve_vectors,
+            matching_strategy,
+            max_limit,
+            max_offset,
+            finite_pagination,
+            max_attributes_to_retrieve,
+            max_attributes_to_highlight,
+            highlight_pre_tag,
+            highlight_post_tag,
+            max_attributes_to_crop,
+            crop_marker,
+            show_matches_position,
+            crop_length,
+            facets_sum_of_terms,
+            facets_total_number_of_facets,
+            show_ranking_score,
+            show_ranking_score_details,
+            semantic_ratio,
+            hybrid,
+            total_degraded,
+            total_used_negative_operator,
+            ranking_score_threshold,
+            locales,
+            marker: _,
+        } = *self;
+
+        // we get all the values in a sorted manner
+        let time_spent = time_spent.into_sorted_vec();
+        // the index of the 99th percentage of value
+        let percentile_99th = time_spent.len() * 99 / 100;
+        // We are only interested by the slowest value of the 99th fastest results
+        let time_spent = time_spent.get(percentile_99th);
+
+        json!({
+            "requests": {
+                "99th_response_time": time_spent.map(|t| format!("{:.2}", t)),
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+                "total_degraded": total_degraded,
+                "total_used_negative_operator": total_used_negative_operator,
+            },
+            "sort": {
+                "with_geoPoint": sort_with_geo_point,
+                "avg_criteria_number": format!("{:.2}", sort_sum_of_criteria_terms as f64 / sort_total_number_of_criteria as f64),
+            },
+            "distinct": distinct,
+            "filter": {
+               "with_geoRadius": filter_with_geo_radius,
+               "with_geoBoundingBox": filter_with_geo_bounding_box,
+               "avg_criteria_number": format!("{:.2}", filter_sum_of_criteria_terms as f64 / filter_total_number_of_criteria as f64),
+               "most_used_syntax": used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+            },
+            "attributes_to_search_on": {
+               "total_number_of_uses": attributes_to_search_on_total_number_of_uses,
+            },
+            "q": {
+               "max_terms_number": max_terms_number,
+            },
+            "vector": {
+                "max_vector_size": max_vector_size,
+                "retrieve_vectors": retrieve_vectors,
+            },
+            "hybrid": {
+                "enabled": hybrid,
+                "semantic_ratio": semantic_ratio,
+            },
+            "pagination": {
+               "max_limit": max_limit,
+               "max_offset": max_offset,
+               "most_used_navigation": if finite_pagination > (total_received / 2) { "exhaustive" } else { "estimated" },
+            },
+            "formatting": {
+                "max_attributes_to_retrieve": max_attributes_to_retrieve,
+                "max_attributes_to_highlight": max_attributes_to_highlight,
+                "highlight_pre_tag": highlight_pre_tag,
+                "highlight_post_tag": highlight_post_tag,
+                "max_attributes_to_crop": max_attributes_to_crop,
+                "crop_marker": crop_marker,
+                "show_matches_position": show_matches_position,
+                "crop_length": crop_length,
+            },
+            "facets": {
+                "avg_facets_number": format!("{:.2}", facets_sum_of_terms as f64 / facets_total_number_of_facets as f64),
+            },
+            "matching_strategy": {
+                "most_used_strategy": matching_strategy.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+            },
+            "locales": locales,
+            "scoring": {
+                "show_ranking_score": show_ranking_score,
+                "show_ranking_score_details": show_ranking_score_details,
+                "ranking_score_threshold": ranking_score_threshold,
+            },
+        })
+    }
+}

meilisearch/src/routes/indexes/settings.rs

@@ -1,15 +1,14 @@
+use super::settings_analytics::*;
 use actix_web::web::Data;
 use actix_web::{web, HttpRequest, HttpResponse};
 use deserr::actix_web::AwebJson;
 use index_scheduler::IndexScheduler;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::ResponseError;
-use meilisearch_types::facet_values_sort::FacetValuesSort;
 use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::milli::update::Setting;
-use meilisearch_types::settings::{settings, RankingRuleView, SecretPolicy, Settings, Unchecked};
+use meilisearch_types::settings::{settings, SecretPolicy, Settings, Unchecked};
 use meilisearch_types::tasks::KindWithContent;
-use serde_json::json;
 use tracing::debug;
 
 use crate::analytics::Analytics;
@@ -20,7 +19,7 @@ use crate::Opt;
 
 #[macro_export]
 macro_rules! make_setting_route {
-    ($route:literal, $update_verb:ident, $type:ty, $err_ty:ty, $attr:ident, $camelcase_attr:literal, $analytics_var:ident, $analytics:expr) => {
+    ($route:literal, $update_verb:ident, $type:ty, $err_ty:ty, $attr:ident, $camelcase_attr:literal, $analytics:ident) => {
         pub mod $attr {
             use actix_web::web::Data;
             use actix_web::{web, HttpRequest, HttpResponse, Resource};
@@ -80,7 +79,7 @@ macro_rules! make_setting_route {
                 body: deserr::actix_web::AwebJson<Option<$type>, $err_ty>,
                 req: HttpRequest,
                 opt: web::Data<Opt>,
-                $analytics_var: web::Data<dyn Analytics>,
+                analytics: web::Data<Analytics>,
             ) -> std::result::Result<HttpResponse, ResponseError> {
                 let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
@@ -88,7 +87,10 @@ macro_rules! make_setting_route {
                 debug!(parameters = ?body, "Update settings");
 
                 #[allow(clippy::redundant_closure_call)]
-                $analytics(&body, &req);
+                analytics.publish(
+                    $crate::routes::indexes::settings_analytics::$analytics::new(body.as_ref()).into_settings(),
+                    &req,
+                );
 
                 let new_settings = Settings {
                     $attr: match body {
@@ -160,21 +162,7 @@ make_setting_route!(
     >,
     filterable_attributes,
     "filterableAttributes",
-    analytics,
-    |setting: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "FilterableAttributes Updated".to_string(),
-            json!({
-                "filterable_attributes": {
-                    "total": setting.as_ref().map(|filter| filter.len()).unwrap_or(0),
-                    "has_geo": setting.as_ref().map(|filter| filter.contains("_geo")).unwrap_or(false),
-                }
-            }),
-            Some(req),
-        );
-    }
+    FilterableAttributesAnalytics
 );
 
 make_setting_route!(
@@ -186,21 +174,7 @@ make_setting_route!(
     >,
     sortable_attributes,
     "sortableAttributes",
-    analytics,
-    |setting: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "SortableAttributes Updated".to_string(),
-            json!({
-                "sortable_attributes": {
-                    "total": setting.as_ref().map(|sort| sort.len()),
-                    "has_geo": setting.as_ref().map(|sort| sort.contains("_geo")),
-                },
-            }),
-            Some(req),
-        );
-    }
+    SortableAttributesAnalytics
 );
 
 make_setting_route!(
@@ -212,21 +186,7 @@ make_setting_route!(
     >,
     displayed_attributes,
     "displayedAttributes",
-    analytics,
-    |displayed: &Option<Vec<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "DisplayedAttributes Updated".to_string(),
-            json!({
-                "displayed_attributes": {
-                    "total": displayed.as_ref().map(|displayed| displayed.len()),
-                    "with_wildcard": displayed.as_ref().map(|displayed| displayed.iter().any(|displayed| displayed == "*")),
-                },
-            }),
-            Some(req),
-        );
-    }
+    DisplayedAttributesAnalytics
 );
 
 make_setting_route!(
@@ -238,40 +198,7 @@ make_setting_route!(
     >,
     typo_tolerance,
     "typoTolerance",
-    analytics,
-    |setting: &Option<meilisearch_types::settings::TypoSettings>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "TypoTolerance Updated".to_string(),
-            json!({
-                "typo_tolerance": {
-                    "enabled": setting.as_ref().map(|s| !matches!(s.enabled, Setting::Set(false))),
-                    "disable_on_attributes": setting
-                        .as_ref()
-                        .and_then(|s| s.disable_on_attributes.as_ref().set().map(|m| !m.is_empty())),
-                    "disable_on_words": setting
-                        .as_ref()
-                        .and_then(|s| s.disable_on_words.as_ref().set().map(|m| !m.is_empty())),
-                    "min_word_size_for_one_typo": setting
-                        .as_ref()
-                        .and_then(|s| s.min_word_size_for_typos
-                            .as_ref()
-                            .set()
-                            .map(|s| s.one_typo.set()))
-                        .flatten(),
-                    "min_word_size_for_two_typos": setting
-                        .as_ref()
-                        .and_then(|s| s.min_word_size_for_typos
-                            .as_ref()
-                            .set()
-                            .map(|s| s.two_typos.set()))
-                        .flatten(),
-                },
-            }),
-            Some(req),
-        );
-    }
+    TypoToleranceAnalytics
 );
 
 make_setting_route!(
@@ -283,21 +210,7 @@ make_setting_route!(
     >,
     searchable_attributes,
     "searchableAttributes",
-    analytics,
-    |setting: &Option<Vec<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "SearchableAttributes Updated".to_string(),
-            json!({
-                "searchable_attributes": {
-                    "total": setting.as_ref().map(|searchable| searchable.len()),
-                    "with_wildcard": setting.as_ref().map(|searchable| searchable.iter().any(|searchable| searchable == "*")),
-                },
-            }),
-            Some(req),
-        );
-    }
+    SearchableAttributesAnalytics
 );
 
 make_setting_route!(
@@ -309,20 +222,7 @@ make_setting_route!(
     >,
     stop_words,
     "stopWords",
-    analytics,
-    |stop_words: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "StopWords Updated".to_string(),
-            json!({
-                "stop_words": {
-                    "total": stop_words.as_ref().map(|stop_words| stop_words.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
+    StopWordsAnalytics
 );
 
 make_setting_route!(
@@ -334,20 +234,7 @@ make_setting_route!(
     >,
     non_separator_tokens,
     "nonSeparatorTokens",
-    analytics,
-    |non_separator_tokens: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "nonSeparatorTokens Updated".to_string(),
-            json!({
-                "non_separator_tokens": {
-                    "total": non_separator_tokens.as_ref().map(|non_separator_tokens| non_separator_tokens.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
+    NonSeparatorTokensAnalytics
 );
 
 make_setting_route!(
@@ -359,20 +246,7 @@ make_setting_route!(
     >,
     separator_tokens,
     "separatorTokens",
-    analytics,
-    |separator_tokens: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "separatorTokens Updated".to_string(),
-            json!({
-                "separator_tokens": {
-                    "total": separator_tokens.as_ref().map(|separator_tokens| separator_tokens.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
+    SeparatorTokensAnalytics
 );
 
 make_setting_route!(
@@ -384,20 +258,7 @@ make_setting_route!(
     >,
     dictionary,
     "dictionary",
-    analytics,
-    |dictionary: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "dictionary Updated".to_string(),
-            json!({
-                "dictionary": {
-                    "total": dictionary.as_ref().map(|dictionary| dictionary.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
+    DictionaryAnalytics
 );
 
 make_setting_route!(
@@ -409,20 +270,7 @@ make_setting_route!(
     >,
     synonyms,
     "synonyms",
-    analytics,
-    |synonyms: &Option<std::collections::BTreeMap<String, Vec<String>>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "Synonyms Updated".to_string(),
-            json!({
-                "synonyms": {
-                    "total": synonyms.as_ref().map(|synonyms| synonyms.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
+    SynonymsAnalytics
 );
 
 make_setting_route!(
@@ -434,19 +282,7 @@ make_setting_route!(
     >,
     distinct_attribute,
     "distinctAttribute",
-    analytics,
-    |distinct: &Option<String>, req: &HttpRequest| {
-        use serde_json::json;
-        analytics.publish(
-            "DistinctAttribute Updated".to_string(),
-            json!({
-                "distinct_attribute": {
-                    "set": distinct.is_some(),
-                }
-            }),
-            Some(req),
-        );
-    }
+    DistinctAttributeAnalytics
 );
 
 make_setting_route!(
@@ -458,20 +294,7 @@ make_setting_route!(
     >,
     proximity_precision,
     "proximityPrecision",
-    analytics,
-    |precision: &Option<meilisearch_types::settings::ProximityPrecisionView>, req: &HttpRequest| {
-        use serde_json::json;
-        analytics.publish(
-            "ProximityPrecision Updated".to_string(),
-            json!({
-                "proximity_precision": {
-                    "set": precision.is_some(),
-                    "value": precision.unwrap_or_default(),
-                }
-            }),
-            Some(req),
-        );
-    }
+    ProximityPrecisionAnalytics
 );
 
 make_setting_route!(
@@ -483,17 +306,7 @@ make_setting_route!(
     >,
     localized_attributes,
     "localizedAttributes",
-    analytics,
-    |rules: &Option<Vec<meilisearch_types::locales::LocalizedAttributesRuleView>>, req: &HttpRequest| {
-        use serde_json::json;
-        analytics.publish(
-            "LocalizedAttributesRules Updated".to_string(),
-            json!({
-                "locales": rules.as_ref().map(|rules| rules.iter().flat_map(|rule| rule.locales.iter().cloned()).collect::<std::collections::BTreeSet<_>>())
-            }),
-            Some(req),
-        );
-    }
+    LocalesAnalytics
 );
 
 make_setting_route!(
@@ -505,26 +318,7 @@ make_setting_route!(
     >,
     ranking_rules,
     "rankingRules",
-    analytics,
-    |setting: &Option<Vec<meilisearch_types::settings::RankingRuleView>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "RankingRules Updated".to_string(),
-            json!({
-                "ranking_rules": {
-                    "words_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Words))),
-                    "typo_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Typo))),
-                    "proximity_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Proximity))),
-                    "attribute_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Attribute))),
-                    "sort_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Sort))),
-                    "exactness_position": setting.as_ref().map(|rr| rr.iter().position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Exactness))),
-                    "values": setting.as_ref().map(|rr| rr.iter().filter(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Asc(_) | meilisearch_types::settings::RankingRuleView::Desc(_)) ).map(|x| x.to_string()).collect::<Vec<_>>().join(", ")),
-                }
-            }),
-            Some(req),
-        );
-    }
+    RankingRulesAnalytics
 );
 
 make_setting_route!(
@@ -536,25 +330,7 @@ make_setting_route!(
     >,
     faceting,
     "faceting",
-    analytics,
-    |setting: &Option<meilisearch_types::settings::FacetingSettings>, req: &HttpRequest| {
-        use serde_json::json;
-        use meilisearch_types::facet_values_sort::FacetValuesSort;
-
-        analytics.publish(
-            "Faceting Updated".to_string(),
-            json!({
-                "faceting": {
-                    "max_values_per_facet": setting.as_ref().and_then(|s| s.max_values_per_facet.set()),
-                    "sort_facet_values_by_star_count": setting.as_ref().and_then(|s| {
-                        s.sort_facet_values_by.as_ref().set().map(|s| s.iter().any(|(k, v)| k == "*" && v == &FacetValuesSort::Count))
-                    }),
-                    "sort_facet_values_by_total": setting.as_ref().and_then(|s| s.sort_facet_values_by.as_ref().set().map(|s| s.len())),
-                },
-            }),
-            Some(req),
-        );
-    }
+    FacetingAnalytics
 );
 
 make_setting_route!(
@@ -566,20 +342,7 @@ make_setting_route!(
     >,
     pagination,
     "pagination",
-    analytics,
-    |setting: &Option<meilisearch_types::settings::PaginationSettings>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "Pagination Updated".to_string(),
-            json!({
-                "pagination": {
-                    "max_total_hits": setting.as_ref().and_then(|s| s.max_total_hits.set()),
-                },
-            }),
-            Some(req),
-        );
-    }
+    PaginationAnalytics
 );
 
 make_setting_route!(
@@ -591,60 +354,9 @@ make_setting_route!(
     >,
     embedders,
     "embedders",
-    analytics,
-    |setting: &Option<std::collections::BTreeMap<String, Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>>>, req: &HttpRequest| {
-
-
-        analytics.publish(
-            "Embedders Updated".to_string(),
-            serde_json::json!({"embedders": crate::routes::indexes::settings::embedder_analytics(setting.as_ref())}),
-            Some(req),
-        );
-    }
+    EmbeddersAnalytics
 );
 
-fn embedder_analytics(
-    setting: Option<
-        &std::collections::BTreeMap<
-            String,
-            Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>,
-        >,
-    >,
-) -> serde_json::Value {
-    let mut sources = std::collections::HashSet::new();
-
-    if let Some(s) = &setting {
-        for source in s
-            .values()
-            .filter_map(|config| config.clone().set())
-            .filter_map(|config| config.source.set())
-        {
-            use meilisearch_types::milli::vector::settings::EmbedderSource;
-            match source {
-                EmbedderSource::OpenAi => sources.insert("openAi"),
-                EmbedderSource::HuggingFace => sources.insert("huggingFace"),
-                EmbedderSource::UserProvided => sources.insert("userProvided"),
-                EmbedderSource::Ollama => sources.insert("ollama"),
-                EmbedderSource::Rest => sources.insert("rest"),
-            };
-        }
-    };
-
-    let document_template_used = setting.as_ref().map(|map| {
-        map.values()
-            .filter_map(|config| config.clone().set())
-            .any(|config| config.document_template.set().is_some())
-    });
-
-    json!(
-        {
-            "total": setting.as_ref().map(|s| s.len()),
-            "sources": sources,
-            "document_template_used": document_template_used,
-        }
-    )
-}
-
 make_setting_route!(
     "/search-cutoff-ms",
     put,
@@ -654,14 +366,7 @@ make_setting_route!(
     >,
     search_cutoff_ms,
     "searchCutoffMs",
-    analytics,
-    |setting: &Option<u64>, req: &HttpRequest| {
-        analytics.publish(
-            "Search Cutoff Updated".to_string(),
-            serde_json::json!({"search_cutoff_ms": setting }),
-            Some(req),
-        );
-    }
+    SearchCutoffMsAnalytics
 );
 
 macro_rules! generate_configure {
@@ -682,6 +387,7 @@ generate_configure!(
     filterable_attributes,
     sortable_attributes,
     displayed_attributes,
+    localized_attributes,
     searchable_attributes,
     distinct_attribute,
     proximity_precision,
@@ -704,7 +410,7 @@ pub async fn update_all(
     body: AwebJson<Settings<Unchecked>, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
@@ -713,104 +419,45 @@ pub async fn update_all(
     let new_settings = validate_settings(new_settings, &index_scheduler)?;
 
     analytics.publish(
-        "Settings Updated".to_string(),
-        json!({
-           "ranking_rules": {
-                "words_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Words))),
-                "typo_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Typo))),
-                "proximity_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Proximity))),
-                "attribute_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Attribute))),
-                "sort_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Sort))),
-                "exactness_position": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().position(|s| matches!(s, RankingRuleView::Exactness))),
-                "values": new_settings.ranking_rules.as_ref().set().map(|rr| rr.iter().filter(|s| !matches!(s, RankingRuleView::Asc(_) | RankingRuleView::Desc(_)) ).map(|x| x.to_string()).collect::<Vec<_>>().join(", ")),
-            },
-            "searchable_attributes": {
-                "total": new_settings.searchable_attributes.as_ref().set().map(|searchable| searchable.len()),
-                "with_wildcard": new_settings.searchable_attributes.as_ref().set().map(|searchable| searchable.iter().any(|searchable| searchable == "*")),
-            },
-            "displayed_attributes": {
-                "total": new_settings.displayed_attributes.as_ref().set().map(|displayed| displayed.len()),
-                "with_wildcard": new_settings.displayed_attributes.as_ref().set().map(|displayed| displayed.iter().any(|displayed| displayed == "*")),
-            },
-           "sortable_attributes": {
-                "total": new_settings.sortable_attributes.as_ref().set().map(|sort| sort.len()),
-                "has_geo": new_settings.sortable_attributes.as_ref().set().map(|sort| sort.iter().any(|s| s == "_geo")),
-            },
-           "filterable_attributes": {
-                "total": new_settings.filterable_attributes.as_ref().set().map(|filter| filter.len()),
-                "has_geo": new_settings.filterable_attributes.as_ref().set().map(|filter| filter.iter().any(|s| s == "_geo")),
-            },
-            "distinct_attribute": {
-                "set": new_settings.distinct_attribute.as_ref().set().is_some()
-            },
-            "proximity_precision": {
-                "set": new_settings.proximity_precision.as_ref().set().is_some(),
-                "value": new_settings.proximity_precision.as_ref().set().copied().unwrap_or_default()
-            },
-            "typo_tolerance": {
-                "enabled": new_settings.typo_tolerance
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.enabled.as_ref().set())
-                    .copied(),
-                "disable_on_attributes": new_settings.typo_tolerance
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.disable_on_attributes.as_ref().set().map(|m| !m.is_empty())),
-                "disable_on_words": new_settings.typo_tolerance
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.disable_on_words.as_ref().set().map(|m| !m.is_empty())),
-                "min_word_size_for_one_typo": new_settings.typo_tolerance
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.min_word_size_for_typos
-                        .as_ref()
-                        .set()
-                        .map(|s| s.one_typo.set()))
-                    .flatten(),
-                "min_word_size_for_two_typos": new_settings.typo_tolerance
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.min_word_size_for_typos
-                        .as_ref()
-                        .set()
-                        .map(|s| s.two_typos.set()))
-                    .flatten(),
-            },
-            "faceting": {
-                "max_values_per_facet": new_settings.faceting
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.max_values_per_facet.as_ref().set()),
-                "sort_facet_values_by_star_count": new_settings.faceting
-                    .as_ref()
-                    .set()
-                    .and_then(|s| {
-                        s.sort_facet_values_by.as_ref().set().map(|s| s.iter().any(|(k, v)| k == "*" && v == &FacetValuesSort::Count))
-                    }),
-                "sort_facet_values_by_total": new_settings.faceting
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.sort_facet_values_by.as_ref().set().map(|s| s.len())),
-            },
-            "pagination": {
-                "max_total_hits": new_settings.pagination
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.max_total_hits.as_ref().set()),
-            },
-            "stop_words": {
-                "total": new_settings.stop_words.as_ref().set().map(|stop_words| stop_words.len()),
-            },
-            "synonyms": {
-                "total": new_settings.synonyms.as_ref().set().map(|synonyms| synonyms.len()),
-            },
-            "embedders": crate::routes::indexes::settings::embedder_analytics(new_settings.embedders.as_ref().set()),
-            "search_cutoff_ms": new_settings.search_cutoff_ms.as_ref().set(),
-            "locales": new_settings.localized_attributes.as_ref().set().map(|rules| rules.iter().flat_map(|rule| rule.locales.iter().cloned()).collect::<std::collections::BTreeSet<_>>()),
-        }),
-        Some(&req),
+        SettingsAnalytics {
+            ranking_rules: RankingRulesAnalytics::new(new_settings.ranking_rules.as_ref().set()),
+            searchable_attributes: SearchableAttributesAnalytics::new(
+                new_settings.searchable_attributes.as_ref().set(),
+            ),
+            displayed_attributes: DisplayedAttributesAnalytics::new(
+                new_settings.displayed_attributes.as_ref().set(),
+            ),
+            sortable_attributes: SortableAttributesAnalytics::new(
+                new_settings.sortable_attributes.as_ref().set(),
+            ),
+            filterable_attributes: FilterableAttributesAnalytics::new(
+                new_settings.filterable_attributes.as_ref().set(),
+            ),
+            distinct_attribute: DistinctAttributeAnalytics::new(
+                new_settings.distinct_attribute.as_ref().set(),
+            ),
+            proximity_precision: ProximityPrecisionAnalytics::new(
+                new_settings.proximity_precision.as_ref().set(),
+            ),
+            typo_tolerance: TypoToleranceAnalytics::new(new_settings.typo_tolerance.as_ref().set()),
+            faceting: FacetingAnalytics::new(new_settings.faceting.as_ref().set()),
+            pagination: PaginationAnalytics::new(new_settings.pagination.as_ref().set()),
+            stop_words: StopWordsAnalytics::new(new_settings.stop_words.as_ref().set()),
+            synonyms: SynonymsAnalytics::new(new_settings.synonyms.as_ref().set()),
+            embedders: EmbeddersAnalytics::new(new_settings.embedders.as_ref().set()),
+            search_cutoff_ms: SearchCutoffMsAnalytics::new(
+                new_settings.search_cutoff_ms.as_ref().set(),
+            ),
+            locales: LocalesAnalytics::new(new_settings.localized_attributes.as_ref().set()),
+            dictionary: DictionaryAnalytics::new(new_settings.dictionary.as_ref().set()),
+            separator_tokens: SeparatorTokensAnalytics::new(
+                new_settings.separator_tokens.as_ref().set(),
+            ),
+            non_separator_tokens: NonSeparatorTokensAnalytics::new(
+                new_settings.non_separator_tokens.as_ref().set(),
+            ),
+        },
+        &req,
     );
 
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);

meilisearch/src/routes/indexes/settings_analytics.rs

@@ -0,0 +1,621 @@
+//! All the structures used to make the analytics on the settings works.
+//! The signatures of the `new` functions are not very rust idiomatic because they must match the types received
+//! through the sub-settings route directly without any manipulation.
+//! This is why we often use a `Option<&Vec<_>>` instead of a `Option<&[_]>`.
+
+use meilisearch_types::locales::{Locale, LocalizedAttributesRuleView};
+use meilisearch_types::milli::update::Setting;
+use meilisearch_types::milli::vector::settings::EmbeddingSettings;
+use meilisearch_types::settings::{
+    FacetingSettings, PaginationSettings, ProximityPrecisionView, TypoSettings,
+};
+use meilisearch_types::{facet_values_sort::FacetValuesSort, settings::RankingRuleView};
+use serde::Serialize;
+use std::collections::{BTreeMap, BTreeSet, HashSet};
+
+use crate::analytics::Aggregate;
+
+#[derive(Serialize, Default)]
+pub struct SettingsAnalytics {
+    pub ranking_rules: RankingRulesAnalytics,
+    pub searchable_attributes: SearchableAttributesAnalytics,
+    pub displayed_attributes: DisplayedAttributesAnalytics,
+    pub sortable_attributes: SortableAttributesAnalytics,
+    pub filterable_attributes: FilterableAttributesAnalytics,
+    pub distinct_attribute: DistinctAttributeAnalytics,
+    pub proximity_precision: ProximityPrecisionAnalytics,
+    pub typo_tolerance: TypoToleranceAnalytics,
+    pub faceting: FacetingAnalytics,
+    pub pagination: PaginationAnalytics,
+    pub stop_words: StopWordsAnalytics,
+    pub synonyms: SynonymsAnalytics,
+    pub embedders: EmbeddersAnalytics,
+    pub search_cutoff_ms: SearchCutoffMsAnalytics,
+    pub locales: LocalesAnalytics,
+    pub dictionary: DictionaryAnalytics,
+    pub separator_tokens: SeparatorTokensAnalytics,
+    pub non_separator_tokens: NonSeparatorTokensAnalytics,
+}
+
+impl Aggregate for SettingsAnalytics {
+    fn event_name(&self) -> &'static str {
+        "Settings Updated"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            ranking_rules: RankingRulesAnalytics {
+                words_position: new
+                    .ranking_rules
+                    .words_position
+                    .or(self.ranking_rules.words_position),
+                typo_position: new.ranking_rules.typo_position.or(self.ranking_rules.typo_position),
+                proximity_position: new
+                    .ranking_rules
+                    .proximity_position
+                    .or(self.ranking_rules.proximity_position),
+                attribute_position: new
+                    .ranking_rules
+                    .attribute_position
+                    .or(self.ranking_rules.attribute_position),
+                sort_position: new.ranking_rules.sort_position.or(self.ranking_rules.sort_position),
+                exactness_position: new
+                    .ranking_rules
+                    .exactness_position
+                    .or(self.ranking_rules.exactness_position),
+                values: new.ranking_rules.values.or(self.ranking_rules.values),
+            },
+            searchable_attributes: SearchableAttributesAnalytics {
+                total: new.searchable_attributes.total.or(self.searchable_attributes.total),
+                with_wildcard: new
+                    .searchable_attributes
+                    .with_wildcard
+                    .or(self.searchable_attributes.with_wildcard),
+            },
+            displayed_attributes: DisplayedAttributesAnalytics {
+                total: new.displayed_attributes.total.or(self.displayed_attributes.total),
+                with_wildcard: new
+                    .displayed_attributes
+                    .with_wildcard
+                    .or(self.displayed_attributes.with_wildcard),
+            },
+            sortable_attributes: SortableAttributesAnalytics {
+                total: new.sortable_attributes.total.or(self.sortable_attributes.total),
+                has_geo: new.sortable_attributes.has_geo.or(self.sortable_attributes.has_geo),
+            },
+            filterable_attributes: FilterableAttributesAnalytics {
+                total: new.filterable_attributes.total.or(self.filterable_attributes.total),
+                has_geo: new.filterable_attributes.has_geo.or(self.filterable_attributes.has_geo),
+            },
+            distinct_attribute: DistinctAttributeAnalytics {
+                set: self.distinct_attribute.set | new.distinct_attribute.set,
+            },
+            proximity_precision: ProximityPrecisionAnalytics {
+                set: self.proximity_precision.set | new.proximity_precision.set,
+                value: new.proximity_precision.value.or(self.proximity_precision.value),
+            },
+            typo_tolerance: TypoToleranceAnalytics {
+                enabled: new.typo_tolerance.enabled.or(self.typo_tolerance.enabled),
+                disable_on_attributes: new
+                    .typo_tolerance
+                    .disable_on_attributes
+                    .or(self.typo_tolerance.disable_on_attributes),
+                disable_on_words: new
+                    .typo_tolerance
+                    .disable_on_words
+                    .or(self.typo_tolerance.disable_on_words),
+                min_word_size_for_one_typo: new
+                    .typo_tolerance
+                    .min_word_size_for_one_typo
+                    .or(self.typo_tolerance.min_word_size_for_one_typo),
+                min_word_size_for_two_typos: new
+                    .typo_tolerance
+                    .min_word_size_for_two_typos
+                    .or(self.typo_tolerance.min_word_size_for_two_typos),
+            },
+            faceting: FacetingAnalytics {
+                max_values_per_facet: new
+                    .faceting
+                    .max_values_per_facet
+                    .or(self.faceting.max_values_per_facet),
+                sort_facet_values_by_star_count: new
+                    .faceting
+                    .sort_facet_values_by_star_count
+                    .or(self.faceting.sort_facet_values_by_star_count),
+                sort_facet_values_by_total: new
+                    .faceting
+                    .sort_facet_values_by_total
+                    .or(self.faceting.sort_facet_values_by_total),
+            },
+            pagination: PaginationAnalytics {
+                max_total_hits: new.pagination.max_total_hits.or(self.pagination.max_total_hits),
+            },
+            stop_words: StopWordsAnalytics {
+                total: new.stop_words.total.or(self.stop_words.total),
+            },
+            synonyms: SynonymsAnalytics { total: new.synonyms.total.or(self.synonyms.total) },
+            embedders: EmbeddersAnalytics {
+                total: new.embedders.total.or(self.embedders.total),
+                sources: match (self.embedders.sources, new.embedders.sources) {
+                    (None, None) => None,
+                    (Some(sources), None) | (None, Some(sources)) => Some(sources),
+                    (Some(this), Some(other)) => Some(this.union(&other).cloned().collect()),
+                },
+                document_template_used: match (
+                    self.embedders.document_template_used,
+                    new.embedders.document_template_used,
+                ) {
+                    (None, None) => None,
+                    (Some(used), None) | (None, Some(used)) => Some(used),
+                    (Some(this), Some(other)) => Some(this | other),
+                },
+                document_template_max_bytes: match (
+                    self.embedders.document_template_max_bytes,
+                    new.embedders.document_template_max_bytes,
+                ) {
+                    (None, None) => None,
+                    (Some(bytes), None) | (None, Some(bytes)) => Some(bytes),
+                    (Some(this), Some(other)) => Some(this.max(other)),
+                },
+                binary_quantization_used: match (
+                    self.embedders.binary_quantization_used,
+                    new.embedders.binary_quantization_used,
+                ) {
+                    (None, None) => None,
+                    (Some(bq), None) | (None, Some(bq)) => Some(bq),
+                    (Some(this), Some(other)) => Some(this | other),
+                },
+            },
+            search_cutoff_ms: SearchCutoffMsAnalytics {
+                search_cutoff_ms: new
+                    .search_cutoff_ms
+                    .search_cutoff_ms
+                    .or(self.search_cutoff_ms.search_cutoff_ms),
+            },
+            locales: LocalesAnalytics { locales: new.locales.locales.or(self.locales.locales) },
+            dictionary: DictionaryAnalytics {
+                total: new.dictionary.total.or(self.dictionary.total),
+            },
+            separator_tokens: SeparatorTokensAnalytics {
+                total: new.non_separator_tokens.total.or(self.separator_tokens.total),
+            },
+            non_separator_tokens: NonSeparatorTokensAnalytics {
+                total: new.non_separator_tokens.total.or(self.non_separator_tokens.total),
+            },
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct RankingRulesAnalytics {
+    pub words_position: Option<usize>,
+    pub typo_position: Option<usize>,
+    pub proximity_position: Option<usize>,
+    pub attribute_position: Option<usize>,
+    pub sort_position: Option<usize>,
+    pub exactness_position: Option<usize>,
+    pub values: Option<String>,
+}
+
+impl RankingRulesAnalytics {
+    pub fn new(rr: Option<&Vec<RankingRuleView>>) -> Self {
+        RankingRulesAnalytics {
+            words_position: rr.as_ref().and_then(|rr| {
+                rr.iter()
+                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Words))
+            }),
+            typo_position: rr.as_ref().and_then(|rr| {
+                rr.iter()
+                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Typo))
+            }),
+            proximity_position: rr.as_ref().and_then(|rr| {
+                rr.iter().position(|s| {
+                    matches!(s, meilisearch_types::settings::RankingRuleView::Proximity)
+                })
+            }),
+            attribute_position: rr.as_ref().and_then(|rr| {
+                rr.iter().position(|s| {
+                    matches!(s, meilisearch_types::settings::RankingRuleView::Attribute)
+                })
+            }),
+            sort_position: rr.as_ref().and_then(|rr| {
+                rr.iter()
+                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Sort))
+            }),
+            exactness_position: rr.as_ref().and_then(|rr| {
+                rr.iter().position(|s| {
+                    matches!(s, meilisearch_types::settings::RankingRuleView::Exactness)
+                })
+            }),
+            values: rr.as_ref().map(|rr| {
+                rr.iter()
+                    .filter(|s| {
+                        matches!(
+                            s,
+                            meilisearch_types::settings::RankingRuleView::Asc(_)
+                                | meilisearch_types::settings::RankingRuleView::Desc(_)
+                        )
+                    })
+                    .map(|x| x.to_string())
+                    .collect::<Vec<_>>()
+                    .join(", ")
+            }),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { ranking_rules: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SearchableAttributesAnalytics {
+    pub total: Option<usize>,
+    pub with_wildcard: Option<bool>,
+}
+
+impl SearchableAttributesAnalytics {
+    pub fn new(setting: Option<&Vec<String>>) -> Self {
+        Self {
+            total: setting.as_ref().map(|searchable| searchable.len()),
+            with_wildcard: setting
+                .as_ref()
+                .map(|searchable| searchable.iter().any(|searchable| searchable == "*")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { searchable_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct DisplayedAttributesAnalytics {
+    pub total: Option<usize>,
+    pub with_wildcard: Option<bool>,
+}
+
+impl DisplayedAttributesAnalytics {
+    pub fn new(displayed: Option<&Vec<String>>) -> Self {
+        Self {
+            total: displayed.as_ref().map(|displayed| displayed.len()),
+            with_wildcard: displayed
+                .as_ref()
+                .map(|displayed| displayed.iter().any(|displayed| displayed == "*")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { displayed_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SortableAttributesAnalytics {
+    pub total: Option<usize>,
+    pub has_geo: Option<bool>,
+}
+
+impl SortableAttributesAnalytics {
+    pub fn new(setting: Option<&BTreeSet<String>>) -> Self {
+        Self {
+            total: setting.as_ref().map(|sort| sort.len()),
+            has_geo: setting.as_ref().map(|sort| sort.contains("_geo")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { sortable_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct FilterableAttributesAnalytics {
+    pub total: Option<usize>,
+    pub has_geo: Option<bool>,
+}
+
+impl FilterableAttributesAnalytics {
+    pub fn new(setting: Option<&BTreeSet<String>>) -> Self {
+        Self {
+            total: setting.as_ref().map(|filter| filter.len()),
+            has_geo: setting.as_ref().map(|filter| filter.contains("_geo")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { filterable_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct DistinctAttributeAnalytics {
+    pub set: bool,
+}
+
+impl DistinctAttributeAnalytics {
+    pub fn new(distinct: Option<&String>) -> Self {
+        Self { set: distinct.is_some() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { distinct_attribute: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct ProximityPrecisionAnalytics {
+    pub set: bool,
+    pub value: Option<ProximityPrecisionView>,
+}
+
+impl ProximityPrecisionAnalytics {
+    pub fn new(precision: Option<&ProximityPrecisionView>) -> Self {
+        Self { set: precision.is_some(), value: precision.cloned() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { proximity_precision: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct TypoToleranceAnalytics {
+    pub enabled: Option<bool>,
+    pub disable_on_attributes: Option<bool>,
+    pub disable_on_words: Option<bool>,
+    pub min_word_size_for_one_typo: Option<u8>,
+    pub min_word_size_for_two_typos: Option<u8>,
+}
+
+impl TypoToleranceAnalytics {
+    pub fn new(setting: Option<&TypoSettings>) -> Self {
+        Self {
+            enabled: setting.as_ref().map(|s| !matches!(s.enabled, Setting::Set(false))),
+            disable_on_attributes: setting
+                .as_ref()
+                .and_then(|s| s.disable_on_attributes.as_ref().set().map(|m| !m.is_empty())),
+            disable_on_words: setting
+                .as_ref()
+                .and_then(|s| s.disable_on_words.as_ref().set().map(|m| !m.is_empty())),
+            min_word_size_for_one_typo: setting
+                .as_ref()
+                .and_then(|s| s.min_word_size_for_typos.as_ref().set().map(|s| s.one_typo.set()))
+                .flatten(),
+            min_word_size_for_two_typos: setting
+                .as_ref()
+                .and_then(|s| s.min_word_size_for_typos.as_ref().set().map(|s| s.two_typos.set()))
+                .flatten(),
+        }
+    }
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { typo_tolerance: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct FacetingAnalytics {
+    pub max_values_per_facet: Option<usize>,
+    pub sort_facet_values_by_star_count: Option<bool>,
+    pub sort_facet_values_by_total: Option<usize>,
+}
+
+impl FacetingAnalytics {
+    pub fn new(setting: Option<&FacetingSettings>) -> Self {
+        Self {
+            max_values_per_facet: setting.as_ref().and_then(|s| s.max_values_per_facet.set()),
+            sort_facet_values_by_star_count: setting.as_ref().and_then(|s| {
+                s.sort_facet_values_by
+                    .as_ref()
+                    .set()
+                    .map(|s| s.iter().any(|(k, v)| k == "*" && v == &FacetValuesSort::Count))
+            }),
+            sort_facet_values_by_total: setting
+                .as_ref()
+                .and_then(|s| s.sort_facet_values_by.as_ref().set().map(|s| s.len())),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { faceting: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct PaginationAnalytics {
+    pub max_total_hits: Option<usize>,
+}
+
+impl PaginationAnalytics {
+    pub fn new(setting: Option<&PaginationSettings>) -> Self {
+        Self { max_total_hits: setting.as_ref().and_then(|s| s.max_total_hits.set()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { pagination: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct StopWordsAnalytics {
+    pub total: Option<usize>,
+}
+
+impl StopWordsAnalytics {
+    pub fn new(stop_words: Option<&BTreeSet<String>>) -> Self {
+        Self { total: stop_words.as_ref().map(|stop_words| stop_words.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { stop_words: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SynonymsAnalytics {
+    pub total: Option<usize>,
+}
+
+impl SynonymsAnalytics {
+    pub fn new(synonyms: Option<&BTreeMap<String, Vec<String>>>) -> Self {
+        Self { total: synonyms.as_ref().map(|synonyms| synonyms.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { synonyms: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct EmbeddersAnalytics {
+    // last
+    pub total: Option<usize>,
+    // Merge the sources
+    pub sources: Option<HashSet<String>>,
+    // |=
+    pub document_template_used: Option<bool>,
+    // max
+    pub document_template_max_bytes: Option<usize>,
+    // |=
+    pub binary_quantization_used: Option<bool>,
+}
+
+impl EmbeddersAnalytics {
+    pub fn new(setting: Option<&BTreeMap<String, Setting<EmbeddingSettings>>>) -> Self {
+        let mut sources = std::collections::HashSet::new();
+
+        if let Some(s) = &setting {
+            for source in s
+                .values()
+                .filter_map(|config| config.clone().set())
+                .filter_map(|config| config.source.set())
+            {
+                use meilisearch_types::milli::vector::settings::EmbedderSource;
+                match source {
+                    EmbedderSource::OpenAi => sources.insert("openAi".to_string()),
+                    EmbedderSource::HuggingFace => sources.insert("huggingFace".to_string()),
+                    EmbedderSource::UserProvided => sources.insert("userProvided".to_string()),
+                    EmbedderSource::Ollama => sources.insert("ollama".to_string()),
+                    EmbedderSource::Rest => sources.insert("rest".to_string()),
+                };
+            }
+        };
+
+        Self {
+            total: setting.as_ref().map(|s| s.len()),
+            sources: Some(sources),
+            document_template_used: setting.as_ref().map(|map| {
+                map.values()
+                    .filter_map(|config| config.clone().set())
+                    .any(|config| config.document_template.set().is_some())
+            }),
+            document_template_max_bytes: setting.as_ref().and_then(|map| {
+                map.values()
+                    .filter_map(|config| config.clone().set())
+                    .filter_map(|config| config.document_template_max_bytes.set())
+                    .max()
+            }),
+            binary_quantization_used: setting.as_ref().map(|map| {
+                map.values()
+                    .filter_map(|config| config.clone().set())
+                    .any(|config| config.binary_quantized.set().is_some())
+            }),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { embedders: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+#[serde(transparent)]
+pub struct SearchCutoffMsAnalytics {
+    pub search_cutoff_ms: Option<u64>,
+}
+
+impl SearchCutoffMsAnalytics {
+    pub fn new(setting: Option<&u64>) -> Self {
+        Self { search_cutoff_ms: setting.copied() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { search_cutoff_ms: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+#[serde(transparent)]
+pub struct LocalesAnalytics {
+    pub locales: Option<BTreeSet<Locale>>,
+}
+
+impl LocalesAnalytics {
+    pub fn new(rules: Option<&Vec<LocalizedAttributesRuleView>>) -> Self {
+        LocalesAnalytics {
+            locales: rules.as_ref().map(|rules| {
+                rules
+                    .iter()
+                    .flat_map(|rule| rule.locales.iter().cloned())
+                    .collect::<std::collections::BTreeSet<_>>()
+            }),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { locales: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct DictionaryAnalytics {
+    pub total: Option<usize>,
+}
+
+impl DictionaryAnalytics {
+    pub fn new(dictionary: Option<&BTreeSet<String>>) -> Self {
+        Self { total: dictionary.as_ref().map(|dictionary| dictionary.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { dictionary: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SeparatorTokensAnalytics {
+    pub total: Option<usize>,
+}
+
+impl SeparatorTokensAnalytics {
+    pub fn new(separator_tokens: Option<&BTreeSet<String>>) -> Self {
+        Self { total: separator_tokens.as_ref().map(|separator_tokens| separator_tokens.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { separator_tokens: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct NonSeparatorTokensAnalytics {
+    pub total: Option<usize>,
+}
+
+impl NonSeparatorTokensAnalytics {
+    pub fn new(non_separator_tokens: Option<&BTreeSet<String>>) -> Self {
+        Self {
+            total: non_separator_tokens
+                .as_ref()
+                .map(|non_separator_tokens| non_separator_tokens.len()),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { non_separator_tokens: self, ..Default::default() }
+    }
+}

meilisearch/src/routes/indexes/similar.rs

@@ -13,9 +13,10 @@ use serde_json::Value;
 use tracing::debug;
 
 use super::ActionPolicy;
-use crate::analytics::{Analytics, SimilarAggregator};
+use crate::analytics::Analytics;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
+use crate::routes::indexes::similar_analytics::{SimilarAggregator, SimilarGET, SimilarPOST};
 use crate::search::{
     add_search_rules, perform_similar, RankingScoreThresholdSimilar, RetrieveVectors, SearchKind,
     SimilarQuery, SimilarResult, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
@@ -34,13 +35,13 @@ pub async fn similar_get(
     index_uid: web::Path<String>,
     params: AwebQueryParameter<SimilarQueryGet, DeserrQueryParamError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let query = params.0.try_into()?;
 
-    let mut aggregate = SimilarAggregator::from_query(&query, &req);
+    let mut aggregate = SimilarAggregator::<SimilarGET>::from_query(&query);
 
     debug!(parameters = ?query, "Similar get");
 
@@ -49,7 +50,7 @@ pub async fn similar_get(
     if let Ok(similar) = &similar {
         aggregate.succeed(similar);
     }
-    analytics.get_similar(aggregate);
+    analytics.publish(aggregate, &req);
 
     let similar = similar?;
 
@@ -62,21 +63,21 @@ pub async fn similar_post(
     index_uid: web::Path<String>,
     params: AwebJson<SimilarQuery, DeserrJsonError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let query = params.into_inner();
     debug!(parameters = ?query, "Similar post");
 
-    let mut aggregate = SimilarAggregator::from_query(&query, &req);
+    let mut aggregate = SimilarAggregator::<SimilarPOST>::from_query(&query);
 
     let similar = similar(index_scheduler, index_uid, query).await;
 
     if let Ok(similar) = &similar {
         aggregate.succeed(similar);
     }
-    analytics.post_similar(aggregate);
+    analytics.publish(aggregate, &req);
 
     let similar = similar?;
 
@@ -102,8 +103,8 @@ async fn similar(
 
     let index = index_scheduler.index(&index_uid)?;
 
-    let (embedder_name, embedder) =
-        SearchKind::embedder(&index_scheduler, &index, query.embedder.as_deref(), None)?;
+    let (embedder_name, embedder, quantized) =
+        SearchKind::embedder(&index_scheduler, &index, &query.embedder, None)?;
 
     tokio::task::spawn_blocking(move || {
         perform_similar(
@@ -111,6 +112,7 @@ async fn similar(
             query,
             embedder_name,
             embedder,
+            quantized,
             retrieve_vectors,
             index_scheduler.features(),
         )
@@ -139,8 +141,8 @@ pub struct SimilarQueryGet {
     show_ranking_score_details: Param<bool>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSimilarRankingScoreThreshold>, default)]
     pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidEmbedder>)]
-    pub embedder: Option<String>,
+    #[deserr(error = DeserrQueryParamError<InvalidEmbedder>)]
+    pub embedder: String,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]

meilisearch/src/routes/indexes/similar_analytics.rs

@@ -0,0 +1,235 @@
+use std::collections::{BinaryHeap, HashMap};
+
+use once_cell::sync::Lazy;
+use regex::Regex;
+use serde_json::{json, Value};
+
+use crate::{
+    aggregate_methods,
+    analytics::{Aggregate, AggregateMethod},
+    search::{SimilarQuery, SimilarResult},
+};
+
+aggregate_methods!(
+    SimilarPOST => "Similar POST",
+    SimilarGET => "Similar GET",
+);
+
+#[derive(Default)]
+pub struct SimilarAggregator<Method: AggregateMethod> {
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // filter
+    filter_with_geo_radius: bool,
+    filter_with_geo_bounding_box: bool,
+    // every time a request has a filter, this field must be incremented by the number of terms it contains
+    filter_sum_of_criteria_terms: usize,
+    // every time a request has a filter, this field must be incremented by one
+    filter_total_number_of_criteria: usize,
+    used_syntax: HashMap<String, usize>,
+
+    // Whether a non-default embedder was specified
+    retrieve_vectors: bool,
+
+    // pagination
+    max_limit: usize,
+    max_offset: usize,
+
+    // formatting
+    max_attributes_to_retrieve: usize,
+
+    // scoring
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+    ranking_score_threshold: bool,
+
+    marker: std::marker::PhantomData<Method>,
+}
+
+impl<Method: AggregateMethod> SimilarAggregator<Method> {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &SimilarQuery) -> Self {
+        let SimilarQuery {
+            id: _,
+            embedder: _,
+            offset,
+            limit,
+            attributes_to_retrieve: _,
+            retrieve_vectors,
+            show_ranking_score,
+            show_ranking_score_details,
+            filter,
+            ranking_score_threshold,
+        } = query;
+
+        let mut ret = Self::default();
+
+        ret.total_received = 1;
+
+        if let Some(ref filter) = filter {
+            static RE: Lazy<Regex> = Lazy::new(|| Regex::new("AND | OR").unwrap());
+            ret.filter_total_number_of_criteria = 1;
+
+            let syntax = match filter {
+                Value::String(_) => "string".to_string(),
+                Value::Array(values) => {
+                    if values.iter().map(|v| v.to_string()).any(|s| RE.is_match(&s)) {
+                        "mixed".to_string()
+                    } else {
+                        "array".to_string()
+                    }
+                }
+                _ => "none".to_string(),
+            };
+            // convert the string to a HashMap
+            ret.used_syntax.insert(syntax, 1);
+
+            let stringified_filters = filter.to_string();
+            ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
+            ret.filter_with_geo_bounding_box = stringified_filters.contains("_geoBoundingBox(");
+            ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
+        }
+
+        ret.max_limit = *limit;
+        ret.max_offset = *offset;
+
+        ret.show_ranking_score = *show_ranking_score;
+        ret.show_ranking_score_details = *show_ranking_score_details;
+        ret.ranking_score_threshold = ranking_score_threshold.is_some();
+
+        ret.retrieve_vectors = *retrieve_vectors;
+
+        ret
+    }
+
+    pub fn succeed(&mut self, result: &SimilarResult) {
+        let SimilarResult { id: _, hits: _, processing_time_ms, hits_info: _ } = result;
+
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+
+        self.time_spent.push(*processing_time_ms as usize);
+    }
+}
+
+impl<Method: AggregateMethod> Aggregate for SimilarAggregator<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    /// Aggregate one [SimilarAggregator] into another.
+    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        let Self {
+            total_received,
+            total_succeeded,
+            mut time_spent,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            max_limit,
+            max_offset,
+            max_attributes_to_retrieve,
+            show_ranking_score,
+            show_ranking_score_details,
+            ranking_score_threshold,
+            retrieve_vectors,
+            marker: _,
+        } = *new;
+
+        // request
+        self.total_received = self.total_received.saturating_add(total_received);
+        self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
+        self.time_spent.append(&mut time_spent);
+
+        // filter
+        self.filter_with_geo_radius |= filter_with_geo_radius;
+        self.filter_with_geo_bounding_box |= filter_with_geo_bounding_box;
+        self.filter_sum_of_criteria_terms =
+            self.filter_sum_of_criteria_terms.saturating_add(filter_sum_of_criteria_terms);
+        self.filter_total_number_of_criteria =
+            self.filter_total_number_of_criteria.saturating_add(filter_total_number_of_criteria);
+        for (key, value) in used_syntax.into_iter() {
+            let used_syntax = self.used_syntax.entry(key).or_insert(0);
+            *used_syntax = used_syntax.saturating_add(value);
+        }
+
+        self.retrieve_vectors |= retrieve_vectors;
+
+        // pagination
+        self.max_limit = self.max_limit.max(max_limit);
+        self.max_offset = self.max_offset.max(max_offset);
+
+        // formatting
+        self.max_attributes_to_retrieve =
+            self.max_attributes_to_retrieve.max(max_attributes_to_retrieve);
+
+        // scoring
+        self.show_ranking_score |= show_ranking_score;
+        self.show_ranking_score_details |= show_ranking_score_details;
+        self.ranking_score_threshold |= ranking_score_threshold;
+
+        self
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            time_spent,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            max_limit,
+            max_offset,
+            max_attributes_to_retrieve,
+            show_ranking_score,
+            show_ranking_score_details,
+            ranking_score_threshold,
+            retrieve_vectors,
+            marker: _,
+        } = *self;
+
+        // we get all the values in a sorted manner
+        let time_spent = time_spent.into_sorted_vec();
+        // the index of the 99th percentage of value
+        let percentile_99th = time_spent.len() * 99 / 100;
+        // We are only interested by the slowest value of the 99th fastest results
+        let time_spent = time_spent.get(percentile_99th);
+
+        json!({
+            "requests": {
+                "99th_response_time": time_spent.map(|t| format!("{:.2}", t)),
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+            },
+            "filter": {
+               "with_geoRadius": filter_with_geo_radius,
+               "with_geoBoundingBox": filter_with_geo_bounding_box,
+               "avg_criteria_number": format!("{:.2}", filter_sum_of_criteria_terms as f64 / filter_total_number_of_criteria as f64),
+               "most_used_syntax": used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+            },
+            "vector": {
+                "retrieve_vectors": retrieve_vectors,
+            },
+            "pagination": {
+               "max_limit": max_limit,
+               "max_offset": max_offset,
+            },
+            "formatting": {
+                "max_attributes_to_retrieve": max_attributes_to_retrieve,
+            },
+            "scoring": {
+                "show_ranking_score": show_ranking_score,
+                "show_ranking_score_details": show_ranking_score_details,
+                "ranking_score_threshold": ranking_score_threshold,
+            }
+        })
+    }
+}

meilisearch/src/routes/mod.rs

@@ -25,6 +25,7 @@ pub mod indexes;
 mod logs;
 mod metrics;
 mod multi_search;
+mod multi_search_analytics;
 mod snapshot;
 mod swap_indexes;
 pub mod tasks;

meilisearch/src/routes/multi_search.rs

@@ -9,7 +9,7 @@ use meilisearch_types::keys::actions;
 use serde::Serialize;
 use tracing::debug;
 
-use crate::analytics::{Analytics, MultiSearchAggregator};
+use crate::analytics::Analytics;
 use crate::error::MeilisearchHttpError;
 use crate::extractors::authentication::policies::ActionPolicy;
 use crate::extractors::authentication::{AuthenticationError, GuardedData};
@@ -21,6 +21,8 @@ use crate::search::{
 };
 use crate::search_queue::SearchQueue;
 
+use super::multi_search_analytics::MultiSearchAggregator;
+
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::post().to(SeqHandler(multi_search_with_post))));
 }
@@ -35,15 +37,15 @@ pub async fn multi_search_with_post(
     search_queue: Data<SearchQueue>,
     params: AwebJson<FederatedSearch, DeserrJsonError>,
     req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     // Since we don't want to process half of the search requests and then get a permit refused
     // we're going to get one permit for the whole duration of the multi-search request.
-    let _permit = search_queue.try_get_search_permit().await?;
+    let permit = search_queue.try_get_search_permit().await?;
 
     let federated_search = params.into_inner();
 
-    let mut multi_aggregate = MultiSearchAggregator::from_federated_search(&federated_search, &req);
+    let mut multi_aggregate = MultiSearchAggregator::from_federated_search(&federated_search);
 
     let FederatedSearch { mut queries, federation } = federated_search;
 
@@ -81,12 +83,13 @@ pub async fn multi_search_with_post(
                 perform_federated_search(&index_scheduler, queries, federation, features)
             })
             .await;
+            permit.drop().await;
 
             if let Ok(Ok(_)) = search_result {
                 multi_aggregate.succeed();
             }
 
-            analytics.post_multi_search(multi_aggregate);
+            analytics.publish(multi_aggregate, &req);
             HttpResponse::Ok().json(search_result??)
         }
         None => {
@@ -143,11 +146,12 @@ pub async fn multi_search_with_post(
                 Ok(search_results)
             }
             .await;
+            permit.drop().await;
 
             if search_results.is_ok() {
                 multi_aggregate.succeed();
             }
-            analytics.post_multi_search(multi_aggregate);
+            analytics.publish(multi_aggregate, &req);
 
             let search_results = search_results.map_err(|(mut err, query_index)| {
                 // Add the query index that failed as context for the error message.

meilisearch/src/routes/multi_search_analytics.rs

@@ -0,0 +1,170 @@
+use std::collections::HashSet;
+
+use serde_json::json;
+
+use crate::{
+    analytics::Aggregate,
+    search::{FederatedSearch, SearchQueryWithIndex},
+};
+
+#[derive(Default)]
+pub struct MultiSearchAggregator {
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+
+    // sum of the number of distinct indexes in each single request, use with total_received to compute an avg
+    total_distinct_index_count: usize,
+    // number of queries with a single index, use with total_received to compute a proportion
+    total_single_index: usize,
+
+    // sum of the number of search queries in the requests, use with total_received to compute an average
+    total_search_count: usize,
+
+    // scoring
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+
+    // federation
+    use_federation: bool,
+}
+
+impl MultiSearchAggregator {
+    pub fn from_federated_search(federated_search: &FederatedSearch) -> Self {
+        let use_federation = federated_search.federation.is_some();
+
+        let distinct_indexes: HashSet<_> = federated_search
+            .queries
+            .iter()
+            .map(|query| {
+                let query = &query;
+                // make sure we get a compilation error if a field gets added to / removed from SearchQueryWithIndex
+                let SearchQueryWithIndex {
+                    index_uid,
+                    federation_options: _,
+                    q: _,
+                    vector: _,
+                    offset: _,
+                    limit: _,
+                    page: _,
+                    hits_per_page: _,
+                    attributes_to_retrieve: _,
+                    retrieve_vectors: _,
+                    attributes_to_crop: _,
+                    crop_length: _,
+                    attributes_to_highlight: _,
+                    show_ranking_score: _,
+                    show_ranking_score_details: _,
+                    show_matches_position: _,
+                    filter: _,
+                    sort: _,
+                    distinct: _,
+                    facets: _,
+                    highlight_pre_tag: _,
+                    highlight_post_tag: _,
+                    crop_marker: _,
+                    matching_strategy: _,
+                    attributes_to_search_on: _,
+                    hybrid: _,
+                    ranking_score_threshold: _,
+                    locales: _,
+                } = query;
+
+                index_uid.as_str()
+            })
+            .collect();
+
+        let show_ranking_score =
+            federated_search.queries.iter().any(|query| query.show_ranking_score);
+        let show_ranking_score_details =
+            federated_search.queries.iter().any(|query| query.show_ranking_score_details);
+
+        Self {
+            total_received: 1,
+            total_succeeded: 0,
+            total_distinct_index_count: distinct_indexes.len(),
+            total_single_index: if distinct_indexes.len() == 1 { 1 } else { 0 },
+            total_search_count: federated_search.queries.len(),
+            show_ranking_score,
+            show_ranking_score_details,
+            use_federation,
+        }
+    }
+
+    pub fn succeed(&mut self) {
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+    }
+}
+
+impl Aggregate for MultiSearchAggregator {
+    fn event_name(&self) -> &'static str {
+        "Documents Searched by Multi-Search POST"
+    }
+
+    /// Aggregate one [MultiSearchAggregator] into another.
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        // write the aggregate in a way that will cause a compilation error if a field is added.
+
+        // get ownership of self, replacing it by a default value.
+        let this = *self;
+
+        let total_received = this.total_received.saturating_add(new.total_received);
+        let total_succeeded = this.total_succeeded.saturating_add(new.total_succeeded);
+        let total_distinct_index_count =
+            this.total_distinct_index_count.saturating_add(new.total_distinct_index_count);
+        let total_single_index = this.total_single_index.saturating_add(new.total_single_index);
+        let total_search_count = this.total_search_count.saturating_add(new.total_search_count);
+        let show_ranking_score = this.show_ranking_score || new.show_ranking_score;
+        let show_ranking_score_details =
+            this.show_ranking_score_details || new.show_ranking_score_details;
+        let use_federation = this.use_federation || new.use_federation;
+
+        Box::new(Self {
+            total_received,
+            total_succeeded,
+            total_distinct_index_count,
+            total_single_index,
+            total_search_count,
+            show_ranking_score,
+            show_ranking_score_details,
+            use_federation,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            total_distinct_index_count,
+            total_single_index,
+            total_search_count,
+            show_ranking_score,
+            show_ranking_score_details,
+            use_federation,
+        } = *self;
+
+        json!({
+            "requests": {
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+            },
+            "indexes": {
+                "total_single_index": total_single_index,
+                "total_distinct_index_count": total_distinct_index_count,
+                "avg_distinct_index_count": (total_distinct_index_count as f64) / (total_received as f64), // not 0 else returned early
+            },
+            "searches": {
+                "total_search_count": total_search_count,
+                "avg_search_count": (total_search_count as f64) / (total_received as f64),
+            },
+            "scoring": {
+                "show_ranking_score": show_ranking_score,
+                "show_ranking_score_details": show_ranking_score_details,
+            },
+            "federation": {
+                "use_federation": use_federation,
+            }
+        })
+    }
+}

meilisearch/src/routes/snapshot.rs

@@ -3,7 +3,6 @@ use actix_web::{web, HttpRequest, HttpResponse};
 use index_scheduler::IndexScheduler;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::tasks::KindWithContent;
-use serde_json::json;
 use tracing::debug;
 
 use crate::analytics::Analytics;
@@ -17,13 +16,15 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::post().to(SeqHandler(create_snapshot))));
 }
 
+crate::empty_analytics!(SnapshotAnalytics, "Snapshot Created");
+
 pub async fn create_snapshot(
     index_scheduler: GuardedData<ActionPolicy<{ actions::SNAPSHOTS_CREATE }>, Data<IndexScheduler>>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    analytics.publish("Snapshot Created".to_string(), json!({}), Some(&req));
+    analytics.publish(SnapshotAnalytics::default(), &req);
 
     let task = KindWithContent::SnapshotCreation;
     let uid = get_task_id(&req, &opt)?;

meilisearch/src/routes/swap_indexes.rs

@@ -8,10 +8,10 @@ use meilisearch_types::error::deserr_codes::InvalidSwapIndexes;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::tasks::{IndexSwap, KindWithContent};
-use serde_json::json;
+use serde::Serialize;
 
 use super::{get_task_id, is_dry_run, SummarizedTaskView};
-use crate::analytics::Analytics;
+use crate::analytics::{Aggregate, Analytics};
 use crate::error::MeilisearchHttpError;
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::{AuthenticationError, GuardedData};
@@ -29,21 +29,36 @@ pub struct SwapIndexesPayload {
     indexes: Vec<IndexUid>,
 }
 
+#[derive(Serialize)]
+struct IndexSwappedAnalytics {
+    swap_operation_number: usize,
+}
+
+impl Aggregate for IndexSwappedAnalytics {
+    fn event_name(&self) -> &'static str {
+        "Indexes Swapped"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            swap_operation_number: self.swap_operation_number.max(new.swap_operation_number),
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 pub async fn swap_indexes(
     index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_SWAP }>, Data<IndexScheduler>>,
     params: AwebJson<Vec<SwapIndexesPayload>, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let params = params.into_inner();
-    analytics.publish(
-        "Indexes Swapped".to_string(),
-        json!({
-            "swap_operation_number": params.len(),
-        }),
-        Some(&req),
-    );
+    analytics.publish(IndexSwappedAnalytics { swap_operation_number: params.len() }, &req);
     let filters = index_scheduler.filters();
 
     let mut swaps = vec![];

meilisearch/src/routes/tasks.rs

@@ -12,18 +12,17 @@ use meilisearch_types::star_or::{OptionStarOr, OptionStarOrList};
 use meilisearch_types::task_view::TaskView;
 use meilisearch_types::tasks::{Kind, KindWithContent, Status};
 use serde::Serialize;
-use serde_json::json;
 use time::format_description::well_known::Rfc3339;
 use time::macros::format_description;
 use time::{Date, Duration, OffsetDateTime, Time};
 use tokio::task;
 
 use super::{get_task_id, is_dry_run, SummarizedTaskView};
-use crate::analytics::Analytics;
+use crate::analytics::{Aggregate, AggregateMethod, Analytics};
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
-use crate::Opt;
+use crate::{aggregate_methods, Opt};
 
 const DEFAULT_LIMIT: u32 = 20;
 
@@ -158,12 +157,69 @@ impl TaskDeletionOrCancelationQuery {
     }
 }
 
+aggregate_methods!(
+    CancelTasks => "Tasks Canceled",
+    DeleteTasks => "Tasks Deleted",
+);
+
+#[derive(Serialize)]
+struct TaskFilterAnalytics<Method: AggregateMethod> {
+    filtered_by_uid: bool,
+    filtered_by_index_uid: bool,
+    filtered_by_type: bool,
+    filtered_by_status: bool,
+    filtered_by_canceled_by: bool,
+    filtered_by_before_enqueued_at: bool,
+    filtered_by_after_enqueued_at: bool,
+    filtered_by_before_started_at: bool,
+    filtered_by_after_started_at: bool,
+    filtered_by_before_finished_at: bool,
+    filtered_by_after_finished_at: bool,
+
+    #[serde(skip)]
+    marker: std::marker::PhantomData<Method>,
+}
+
+impl<Method: AggregateMethod + 'static> Aggregate for TaskFilterAnalytics<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            filtered_by_uid: self.filtered_by_uid | new.filtered_by_uid,
+            filtered_by_index_uid: self.filtered_by_index_uid | new.filtered_by_index_uid,
+            filtered_by_type: self.filtered_by_type | new.filtered_by_type,
+            filtered_by_status: self.filtered_by_status | new.filtered_by_status,
+            filtered_by_canceled_by: self.filtered_by_canceled_by | new.filtered_by_canceled_by,
+            filtered_by_before_enqueued_at: self.filtered_by_before_enqueued_at
+                | new.filtered_by_before_enqueued_at,
+            filtered_by_after_enqueued_at: self.filtered_by_after_enqueued_at
+                | new.filtered_by_after_enqueued_at,
+            filtered_by_before_started_at: self.filtered_by_before_started_at
+                | new.filtered_by_before_started_at,
+            filtered_by_after_started_at: self.filtered_by_after_started_at
+                | new.filtered_by_after_started_at,
+            filtered_by_before_finished_at: self.filtered_by_before_finished_at
+                | new.filtered_by_before_finished_at,
+            filtered_by_after_finished_at: self.filtered_by_after_finished_at
+                | new.filtered_by_after_finished_at,
+
+            marker: std::marker::PhantomData,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
 async fn cancel_tasks(
     index_scheduler: GuardedData<ActionPolicy<{ actions::TASKS_CANCEL }>, Data<IndexScheduler>>,
     params: AwebQueryParameter<TaskDeletionOrCancelationQuery, DeserrQueryParamError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let params = params.into_inner();
 
@@ -172,21 +228,22 @@ async fn cancel_tasks(
     }
 
     analytics.publish(
-        "Tasks Canceled".to_string(),
-        json!({
-            "filtered_by_uid": params.uids.is_some(),
-            "filtered_by_index_uid": params.index_uids.is_some(),
-            "filtered_by_type": params.types.is_some(),
-            "filtered_by_status": params.statuses.is_some(),
-            "filtered_by_canceled_by": params.canceled_by.is_some(),
-            "filtered_by_before_enqueued_at": params.before_enqueued_at.is_some(),
-            "filtered_by_after_enqueued_at": params.after_enqueued_at.is_some(),
-            "filtered_by_before_started_at": params.before_started_at.is_some(),
-            "filtered_by_after_started_at": params.after_started_at.is_some(),
-            "filtered_by_before_finished_at": params.before_finished_at.is_some(),
-            "filtered_by_after_finished_at": params.after_finished_at.is_some(),
-        }),
-        Some(&req),
+        TaskFilterAnalytics::<CancelTasks> {
+            filtered_by_uid: params.uids.is_some(),
+            filtered_by_index_uid: params.index_uids.is_some(),
+            filtered_by_type: params.types.is_some(),
+            filtered_by_status: params.statuses.is_some(),
+            filtered_by_canceled_by: params.canceled_by.is_some(),
+            filtered_by_before_enqueued_at: params.before_enqueued_at.is_some(),
+            filtered_by_after_enqueued_at: params.after_enqueued_at.is_some(),
+            filtered_by_before_started_at: params.before_started_at.is_some(),
+            filtered_by_after_started_at: params.after_started_at.is_some(),
+            filtered_by_before_finished_at: params.before_finished_at.is_some(),
+            filtered_by_after_finished_at: params.after_finished_at.is_some(),
+
+            marker: std::marker::PhantomData,
+        },
+        &req,
     );
 
     let query = params.into_query();
@@ -214,7 +271,7 @@ async fn delete_tasks(
     params: AwebQueryParameter<TaskDeletionOrCancelationQuery, DeserrQueryParamError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
-    analytics: web::Data<dyn Analytics>,
+    analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let params = params.into_inner();
 
@@ -223,22 +280,24 @@ async fn delete_tasks(
     }
 
     analytics.publish(
-        "Tasks Deleted".to_string(),
-        json!({
-            "filtered_by_uid": params.uids.is_some(),
-            "filtered_by_index_uid": params.index_uids.is_some(),
-            "filtered_by_type": params.types.is_some(),
-            "filtered_by_status": params.statuses.is_some(),
-            "filtered_by_canceled_by": params.canceled_by.is_some(),
-            "filtered_by_before_enqueued_at": params.before_enqueued_at.is_some(),
-            "filtered_by_after_enqueued_at": params.after_enqueued_at.is_some(),
-            "filtered_by_before_started_at": params.before_started_at.is_some(),
-            "filtered_by_after_started_at": params.after_started_at.is_some(),
-            "filtered_by_before_finished_at": params.before_finished_at.is_some(),
-            "filtered_by_after_finished_at": params.after_finished_at.is_some(),
-        }),
-        Some(&req),
+        TaskFilterAnalytics::<DeleteTasks> {
+            filtered_by_uid: params.uids.is_some(),
+            filtered_by_index_uid: params.index_uids.is_some(),
+            filtered_by_type: params.types.is_some(),
+            filtered_by_status: params.statuses.is_some(),
+            filtered_by_canceled_by: params.canceled_by.is_some(),
+            filtered_by_before_enqueued_at: params.before_enqueued_at.is_some(),
+            filtered_by_after_enqueued_at: params.after_enqueued_at.is_some(),
+            filtered_by_before_started_at: params.before_started_at.is_some(),
+            filtered_by_after_started_at: params.after_started_at.is_some(),
+            filtered_by_before_finished_at: params.before_finished_at.is_some(),
+            filtered_by_after_finished_at: params.after_finished_at.is_some(),
+
+            marker: std::marker::PhantomData,
+        },
+        &req,
     );
+
     let query = params.into_query();
 
     let (tasks, _) = index_scheduler.get_task_ids_from_authorized_indexes(

meilisearch/src/search/federated.rs

@@ -9,20 +9,24 @@ use std::vec::{IntoIter, Vec};
 
 use actix_http::StatusCode;
 use index_scheduler::{IndexScheduler, RoFeatures};
+use indexmap::IndexMap;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::deserr_codes::{
-    InvalidMultiSearchWeight, InvalidSearchLimit, InvalidSearchOffset,
+    InvalidMultiSearchFacetsByIndex, InvalidMultiSearchMaxValuesPerFacet,
+    InvalidMultiSearchMergeFacets, InvalidMultiSearchWeight, InvalidSearchLimit,
+    InvalidSearchOffset,
 };
 use meilisearch_types::error::ResponseError;
+use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::milli::score_details::{ScoreDetails, ScoreValue};
-use meilisearch_types::milli::{self, DocumentId, TimeBudget};
+use meilisearch_types::milli::{self, DocumentId, OrderBy, TimeBudget};
 use roaring::RoaringBitmap;
 use serde::Serialize;
 
 use super::ranking_rules::{self, RankingRules};
 use super::{
-    prepare_search, AttributesFormat, HitMaker, HitsInfo, RetrieveVectors, SearchHit, SearchKind,
-    SearchQuery, SearchQueryWithIndex,
+    compute_facet_distribution_stats, prepare_search, AttributesFormat, ComputedFacets, FacetStats,
+    HitMaker, HitsInfo, RetrieveVectors, SearchHit, SearchKind, SearchQuery, SearchQueryWithIndex,
 };
 use crate::error::MeilisearchHttpError;
 use crate::routes::indexes::search::search_kind;
@@ -73,6 +77,17 @@ pub struct Federation {
     pub limit: usize,
     #[deserr(default = super::DEFAULT_SEARCH_OFFSET(), error = DeserrJsonError<InvalidSearchOffset>)]
     pub offset: usize,
+    #[deserr(default, error = DeserrJsonError<InvalidMultiSearchFacetsByIndex>)]
+    pub facets_by_index: BTreeMap<IndexUid, Option<Vec<String>>>,
+    #[deserr(default, error = DeserrJsonError<InvalidMultiSearchMergeFacets>)]
+    pub merge_facets: Option<MergeFacets>,
+}
+
+#[derive(Copy, Clone, Debug, deserr::Deserr, Default)]
+#[deserr(error = DeserrJsonError<InvalidMultiSearchMergeFacets>, rename_all = camelCase, deny_unknown_fields)]
+pub struct MergeFacets {
+    #[deserr(default, error = DeserrJsonError<InvalidMultiSearchMaxValuesPerFacet>)]
+    pub max_values_per_facet: Option<usize>,
 }
 
 #[derive(Debug, deserr::Deserr)]
@@ -82,7 +97,7 @@ pub struct FederatedSearch {
     #[deserr(default)]
     pub federation: Option<Federation>,
 }
-#[derive(Serialize, Clone, PartialEq)]
+#[derive(Serialize, Clone)]
 #[serde(rename_all = "camelCase")]
 pub struct FederatedSearchResult {
     pub hits: Vec<SearchHit>,
@@ -93,6 +108,13 @@ pub struct FederatedSearchResult {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub semantic_hit_count: Option<u32>,
 
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub facet_distribution: Option<BTreeMap<String, IndexMap<String, u64>>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub facet_stats: Option<BTreeMap<String, FacetStats>>,
+    #[serde(skip_serializing_if = "FederatedFacets::is_empty")]
+    pub facets_by_index: FederatedFacets,
+
     // These fields are only used for analytics purposes
     #[serde(skip)]
     pub degraded: bool,
@@ -109,6 +131,9 @@ impl fmt::Debug for FederatedSearchResult {
             semantic_hit_count,
             degraded,
             used_negative_operator,
+            facet_distribution,
+            facet_stats,
+            facets_by_index,
         } = self;
 
         let mut debug = f.debug_struct("SearchResult");
@@ -122,9 +147,18 @@ impl fmt::Debug for FederatedSearchResult {
         if *degraded {
             debug.field("degraded", degraded);
         }
+        if let Some(facet_distribution) = facet_distribution {
+            debug.field("facet_distribution", &facet_distribution);
+        }
+        if let Some(facet_stats) = facet_stats {
+            debug.field("facet_stats", &facet_stats);
+        }
         if let Some(semantic_hit_count) = semantic_hit_count {
             debug.field("semantic_hit_count", &semantic_hit_count);
         }
+        if !facets_by_index.is_empty() {
+            debug.field("facets_by_index", &facets_by_index);
+        }
 
         debug.finish()
     }
@@ -313,16 +347,104 @@ struct SearchHitByIndex {
 }
 
 struct SearchResultByIndex {
+    index: String,
     hits: Vec<SearchHitByIndex>,
-    candidates: RoaringBitmap,
+    estimated_total_hits: usize,
     degraded: bool,
     used_negative_operator: bool,
+    facets: Option<ComputedFacets>,
+}
+
+#[derive(Debug, Clone, Default, Serialize)]
+pub struct FederatedFacets(pub BTreeMap<String, ComputedFacets>);
+
+impl FederatedFacets {
+    pub fn insert(&mut self, index: String, facets: Option<ComputedFacets>) {
+        if let Some(facets) = facets {
+            self.0.insert(index, facets);
+        }
+    }
+
+    pub fn is_empty(&self) -> bool {
+        self.0.is_empty()
+    }
+
+    pub fn merge(
+        self,
+        MergeFacets { max_values_per_facet }: MergeFacets,
+        facet_order: BTreeMap<String, (String, OrderBy)>,
+    ) -> Option<ComputedFacets> {
+        if self.is_empty() {
+            return None;
+        }
+
+        let mut distribution: BTreeMap<String, _> = Default::default();
+        let mut stats: BTreeMap<String, FacetStats> = Default::default();
+
+        for facets_by_index in self.0.into_values() {
+            for (facet, index_distribution) in facets_by_index.distribution {
+                match distribution.entry(facet) {
+                    std::collections::btree_map::Entry::Vacant(entry) => {
+                        entry.insert(index_distribution);
+                    }
+                    std::collections::btree_map::Entry::Occupied(mut entry) => {
+                        let distribution = entry.get_mut();
+
+                        for (value, index_count) in index_distribution {
+                            distribution
+                                .entry(value)
+                                .and_modify(|count| *count += index_count)
+                                .or_insert(index_count);
+                        }
+                    }
+                }
+            }
+
+            for (facet, index_stats) in facets_by_index.stats {
+                match stats.entry(facet) {
+                    std::collections::btree_map::Entry::Vacant(entry) => {
+                        entry.insert(index_stats);
+                    }
+                    std::collections::btree_map::Entry::Occupied(mut entry) => {
+                        let stats = entry.get_mut();
+
+                        stats.min = f64::min(stats.min, index_stats.min);
+                        stats.max = f64::max(stats.max, index_stats.max);
+                    }
+                }
+            }
+        }
+
+        // fixup order
+        for (facet, values) in &mut distribution {
+            let order_by = facet_order.get(facet).map(|(_, order)| *order).unwrap_or_default();
+
+            match order_by {
+                OrderBy::Lexicographic => {
+                    values.sort_unstable_by(|left, _, right, _| left.cmp(right))
+                }
+                OrderBy::Count => {
+                    values.sort_unstable_by(|_, left, _, right| {
+                        left.cmp(right)
+                            // biggest first
+                            .reverse()
+                    })
+                }
+            }
+
+            if let Some(max_values_per_facet) = max_values_per_facet {
+                values.truncate(max_values_per_facet)
+            };
+        }
+
+        Some(ComputedFacets { distribution, stats })
+    }
 }
 
 pub fn perform_federated_search(
     index_scheduler: &IndexScheduler,
     queries: Vec<SearchQueryWithIndex>,
-    federation: Federation,
+    mut federation: Federation,
     features: RoFeatures,
 ) -> Result<FederatedSearchResult, ResponseError> {
     let before_search = std::time::Instant::now();
@@ -342,6 +464,16 @@ pub fn perform_federated_search(
             .into());
         }
 
+        if let Some(facets) = federated_query.has_facets() {
+            let facets = facets.to_owned();
+            return Err(MeilisearchHttpError::FacetsInFederatedQuery(
+                query_index,
+                federated_query.index_uid.into_inner(),
+                facets,
+            )
+            .into());
+        }
+
         let (index_uid, query, federation_options) = federated_query.into_index_query_federation();
 
         queries_by_index.entry(index_uid.into_inner()).or_default().push(QueryByIndex {
@@ -353,13 +485,24 @@ pub fn perform_federated_search(
 
     // 2. perform queries, merge and make hits index by index
     let required_hit_count = federation.limit + federation.offset;
+
     // In step (2), semantic_hit_count will be set to Some(0) if any search kind uses semantic
     // Then in step (3), we'll update its value if there is any semantic search
     let mut semantic_hit_count = None;
     let mut results_by_index = Vec::with_capacity(queries_by_index.len());
     let mut previous_query_data: Option<(RankingRules, usize, String)> = None;
 
+    // remember the order and name of first index for each facet when merging with index settings
+    // to detect if the order is inconsistent for a facet.
+    let mut facet_order: Option<BTreeMap<String, (String, OrderBy)>> = match federation.merge_facets
+    {
+        Some(MergeFacets { .. }) => Some(Default::default()),
+        _ => None,
+    };
+
     for (index_uid, queries) in queries_by_index {
+        let first_query_index = queries.first().map(|query| query.query_index);
+
         let index = match index_scheduler.index(&index_uid) {
             Ok(index) => index,
             Err(err) => {
@@ -367,9 +510,8 @@ pub fn perform_federated_search(
                 // Patch the HTTP status code to 400 as it defaults to 404 for `index_not_found`, but
                 // here the resource not found is not part of the URL.
                 err.code = StatusCode::BAD_REQUEST;
-                if let Some(query) = queries.first() {
-                    err.message =
-                        format!("Inside `.queries[{}]`: {}", query.query_index, err.message);
+                if let Some(query_index) = first_query_index {
+                    err.message = format!("Inside `.queries[{}]`: {}", query_index, err.message);
                 }
                 return Err(err);
             }
@@ -394,6 +536,23 @@ pub fn perform_federated_search(
         let mut used_negative_operator = false;
         let mut candidates = RoaringBitmap::new();
 
+        let facets_by_index = federation.facets_by_index.remove(&index_uid).flatten();
+
+        // TODO: recover the max size + facets_by_index as return value of this function so as not to ask it for all queries
+        if let Err(mut error) =
+            check_facet_order(&mut facet_order, &index_uid, &facets_by_index, &index, &rtxn)
+        {
+            error.message = format!(
+                "Inside `.federation.facetsByIndex.{index_uid}`: {error}{}",
+                if let Some(query_index) = first_query_index {
+                    format!("\n - Note: index `{index_uid}` used in `.queries[{query_index}]`")
+                } else {
+                    Default::default()
+                }
+            );
+            return Err(error);
+        }
+
         // 2.1. Compute all candidates for each query in the index
         let mut results_by_query = Vec::with_capacity(queries.len());
 
@@ -562,34 +721,116 @@ pub fn perform_federated_search(
                 .collect();
 
         let merged_result = merged_result?;
+
+        let estimated_total_hits = candidates.len() as usize;
+
+        let facets = facets_by_index
+            .map(|facets_by_index| {
+                compute_facet_distribution_stats(
+                    &facets_by_index,
+                    &index,
+                    &rtxn,
+                    candidates,
+                    super::Route::MultiSearch,
+                )
+            })
+            .transpose()
+            .map_err(|mut error| {
+                error.message = format!(
+                    "Inside `.federation.facetsByIndex.{index_uid}`: {}{}",
+                    error.message,
+                    if let Some(query_index) = first_query_index {
+                        format!("\n - Note: index `{index_uid}` used in `.queries[{query_index}]`")
+                    } else {
+                        Default::default()
+                    }
+                );
+                error
+            })?;
+
         results_by_index.push(SearchResultByIndex {
+            index: index_uid,
             hits: merged_result,
-            candidates,
+            estimated_total_hits,
             degraded,
             used_negative_operator,
+            facets,
         });
     }
 
+    // bonus step, make sure to return an error if an index wants a non-faceted field, even if no query actually uses that index.
+    for (index_uid, facets) in federation.facets_by_index {
+        let index = match index_scheduler.index(&index_uid) {
+            Ok(index) => index,
+            Err(err) => {
+                let mut err = ResponseError::from(err);
+                // Patch the HTTP status code to 400 as it defaults to 404 for `index_not_found`, but
+                // here the resource not found is not part of the URL.
+                err.code = StatusCode::BAD_REQUEST;
+                err.message = format!(
+                    "Inside `.federation.facetsByIndex.{index_uid}`: {}\n - Note: index `{index_uid}` is not used in queries",
+                    err.message
+                );
+                return Err(err);
+            }
+        };
+
+        // Important: this is the only transaction we'll use for this index during this federated search
+        let rtxn = index.read_txn()?;
+
+        if let Err(mut error) =
+            check_facet_order(&mut facet_order, &index_uid, &facets, &index, &rtxn)
+        {
+            error.message = format!(
+                "Inside `.federation.facetsByIndex.{index_uid}`: {error}\n - Note: index `{index_uid}` is not used in queries",
+            );
+            return Err(error);
+        }
+
+        if let Some(facets) = facets {
+            if let Err(mut error) = compute_facet_distribution_stats(
+                &facets,
+                &index,
+                &rtxn,
+                Default::default(),
+                super::Route::MultiSearch,
+            ) {
+                error.message =
+                    format!("Inside `.federation.facetsByIndex.{index_uid}`: {}\n - Note: index `{index_uid}` is not used in queries", error.message);
+                return Err(error);
+            }
+        }
+    }
+
     // 3. merge hits and metadata across indexes
     // 3.1 merge metadata
-    let (estimated_total_hits, degraded, used_negative_operator) = {
+    let (estimated_total_hits, degraded, used_negative_operator, facets) = {
         let mut estimated_total_hits = 0;
         let mut degraded = false;
         let mut used_negative_operator = false;
 
+        let mut facets: FederatedFacets = FederatedFacets::default();
+
         for SearchResultByIndex {
+            index,
             hits: _,
-            candidates,
+            estimated_total_hits: estimated_total_hits_by_index,
+            facets: facets_by_index,
             degraded: degraded_by_index,
             used_negative_operator: used_negative_operator_by_index,
-        } in &results_by_index
+        } in &mut results_by_index
         {
-            estimated_total_hits += candidates.len() as usize;
+            estimated_total_hits += *estimated_total_hits_by_index;
             degraded |= *degraded_by_index;
             used_negative_operator |= *used_negative_operator_by_index;
+
+            let facets_by_index = std::mem::take(facets_by_index);
+            let index = std::mem::take(index);
+
+            facets.insert(index, facets_by_index);
         }
 
-        (estimated_total_hits, degraded, used_negative_operator)
+        (estimated_total_hits, degraded, used_negative_operator, facets)
     };
 
     // 3.2 merge hits
@@ -606,6 +847,20 @@ pub fn perform_federated_search(
         .map(|hit| hit.hit)
         .collect();
 
+    let (facet_distribution, facet_stats, facets_by_index) =
+        match federation.merge_facets.zip(facet_order) {
+            Some((merge_facets, facet_order)) => {
+                let facets = facets.merge(merge_facets, facet_order);
+
+                let (facet_distribution, facet_stats) = facets
+                    .map(|ComputedFacets { distribution, stats }| (distribution, stats))
+                    .unzip();
+
+                (facet_distribution, facet_stats, FederatedFacets::default())
+            }
+            None => (None, None, facets),
+        };
+
     let search_result = FederatedSearchResult {
         hits: merged_hits,
         processing_time_ms: before_search.elapsed().as_millis(),
@@ -617,7 +872,39 @@ pub fn perform_federated_search(
         semantic_hit_count,
         degraded,
         used_negative_operator,
+        facet_distribution,
+        facet_stats,
+        facets_by_index,
     };
 
     Ok(search_result)
 }
+
+fn check_facet_order(
+    facet_order: &mut Option<BTreeMap<String, (String, OrderBy)>>,
+    current_index: &str,
+    facets_by_index: &Option<Vec<String>>,
+    index: &milli::Index,
+    rtxn: &milli::heed::RoTxn<'_>,
+) -> Result<(), ResponseError> {
+    if let (Some(facet_order), Some(facets_by_index)) = (facet_order, facets_by_index) {
+        let index_facet_order = index.sort_facet_values_by(rtxn)?;
+        for facet in facets_by_index {
+            let index_facet_order = index_facet_order.get(facet);
+            let (previous_index, previous_facet_order) = facet_order
+                .entry(facet.to_owned())
+                .or_insert_with(|| (current_index.to_owned(), index_facet_order));
+            if previous_facet_order != &index_facet_order {
+                return Err(MeilisearchHttpError::InconsistentFacetOrder {
+                    facet: facet.clone(),
+                    previous_facet_order: *previous_facet_order,
+                    previous_uid: previous_index.clone(),
+                    current_uid: current_index.to_owned(),
+                    index_facet_order,
+                }
+                .into());
+            }
+        }
+    };
+    Ok(())
+}

meilisearch/src/search/mod.rs

@@ -267,58 +267,54 @@ impl fmt::Debug for SearchQuery {
 pub struct HybridQuery {
     #[deserr(default, error = DeserrJsonError<InvalidSearchSemanticRatio>, default)]
     pub semantic_ratio: SemanticRatio,
-    #[deserr(default, error = DeserrJsonError<InvalidEmbedder>, default)]
-    pub embedder: Option<String>,
+    #[deserr(error = DeserrJsonError<InvalidEmbedder>)]
+    pub embedder: String,
 }
 
 #[derive(Clone)]
 pub enum SearchKind {
     KeywordOnly,
-    SemanticOnly { embedder_name: String, embedder: Arc<Embedder> },
-    Hybrid { embedder_name: String, embedder: Arc<Embedder>, semantic_ratio: f32 },
+    SemanticOnly { embedder_name: String, embedder: Arc<Embedder>, quantized: bool },
+    Hybrid { embedder_name: String, embedder: Arc<Embedder>, quantized: bool, semantic_ratio: f32 },
 }
 
 impl SearchKind {
     pub(crate) fn semantic(
         index_scheduler: &index_scheduler::IndexScheduler,
         index: &Index,
-        embedder_name: Option<&str>,
+        embedder_name: &str,
         vector_len: Option<usize>,
     ) -> Result<Self, ResponseError> {
-        let (embedder_name, embedder) =
+        let (embedder_name, embedder, quantized) =
             Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
-        Ok(Self::SemanticOnly { embedder_name, embedder })
+        Ok(Self::SemanticOnly { embedder_name, embedder, quantized })
     }
 
     pub(crate) fn hybrid(
         index_scheduler: &index_scheduler::IndexScheduler,
         index: &Index,
-        embedder_name: Option<&str>,
+        embedder_name: &str,
         semantic_ratio: f32,
         vector_len: Option<usize>,
     ) -> Result<Self, ResponseError> {
-        let (embedder_name, embedder) =
+        let (embedder_name, embedder, quantized) =
             Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
-        Ok(Self::Hybrid { embedder_name, embedder, semantic_ratio })
+        Ok(Self::Hybrid { embedder_name, embedder, quantized, semantic_ratio })
     }
 
     pub(crate) fn embedder(
         index_scheduler: &index_scheduler::IndexScheduler,
         index: &Index,
-        embedder_name: Option<&str>,
+        embedder_name: &str,
         vector_len: Option<usize>,
-    ) -> Result<(String, Arc<Embedder>), ResponseError> {
+    ) -> Result<(String, Arc<Embedder>, bool), ResponseError> {
         let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
         let embedders = index_scheduler.embedders(embedder_configs)?;
 
-        let embedder_name = embedder_name.unwrap_or_else(|| embedders.get_default_embedder_name());
-
-        let embedder = embedders.get(embedder_name);
-
-        let embedder = embedder
+        let (embedder, _, quantized) = embedders
+            .get(embedder_name)
             .ok_or(milli::UserError::InvalidEmbedder(embedder_name.to_owned()))
-            .map_err(milli::Error::from)?
-            .0;
+            .map_err(milli::Error::from)?;
 
         if let Some(vector_len) = vector_len {
             if vector_len != embedder.dimensions() {
@@ -332,7 +328,7 @@ impl SearchKind {
             }
         }
 
-        Ok((embedder_name.to_owned(), embedder))
+        Ok((embedder_name.to_owned(), embedder, quantized))
     }
 }
 
@@ -441,9 +437,6 @@ pub struct SearchQueryWithIndex {
 }
 
 impl SearchQueryWithIndex {
-    pub fn has_federation_options(&self) -> bool {
-        self.federation_options.is_some()
-    }
     pub fn has_pagination(&self) -> Option<&'static str> {
         if self.offset.is_some() {
             Some("offset")
@@ -458,6 +451,10 @@ impl SearchQueryWithIndex {
         }
     }
 
+    pub fn has_facets(&self) -> Option<&[String]> {
+        self.facets.as_deref().filter(|v| !v.is_empty())
+    }
+
     pub fn into_index_query_federation(self) -> (IndexUid, SearchQuery, Option<FederationOptions>) {
         let SearchQueryWithIndex {
             index_uid,
@@ -537,8 +534,8 @@ pub struct SimilarQuery {
     pub limit: usize,
     #[deserr(default, error = DeserrJsonError<InvalidSimilarFilter>)]
     pub filter: Option<Value>,
-    #[deserr(default, error = DeserrJsonError<InvalidEmbedder>, default)]
-    pub embedder: Option<String>,
+    #[deserr(error = DeserrJsonError<InvalidEmbedder>)]
+    pub embedder: String,
     #[deserr(default, error = DeserrJsonError<InvalidSimilarAttributesToRetrieve>)]
     pub attributes_to_retrieve: Option<BTreeSet<String>>,
     #[deserr(default, error = DeserrJsonError<InvalidSimilarRetrieveVectors>)]
@@ -792,28 +789,35 @@ fn prepare_search<'t>(
                 search.query(q);
             }
         }
-        SearchKind::SemanticOnly { embedder_name, embedder } => {
+        SearchKind::SemanticOnly { embedder_name, embedder, quantized } => {
             let vector = match query.vector.clone() {
                 Some(vector) => vector,
                 None => {
                     let span = tracing::trace_span!(target: "search::vector", "embed_one");
                     let _entered = span.enter();
 
+                    let deadline = std::time::Instant::now() + std::time::Duration::from_secs(10);
+
                     embedder
-                        .embed_one(query.q.clone().unwrap())
+                        .embed_one(query.q.clone().unwrap(), Some(deadline))
                         .map_err(milli::vector::Error::from)
                         .map_err(milli::Error::from)?
                 }
             };
 
-            search.semantic(embedder_name.clone(), embedder.clone(), Some(vector));
+            search.semantic(embedder_name.clone(), embedder.clone(), *quantized, Some(vector));
         }
-        SearchKind::Hybrid { embedder_name, embedder, semantic_ratio: _ } => {
+        SearchKind::Hybrid { embedder_name, embedder, quantized, semantic_ratio: _ } => {
             if let Some(q) = &query.q {
                 search.query(q);
             }
             // will be embedded in hybrid search if necessary
-            search.semantic(embedder_name.clone(), embedder.clone(), query.vector.clone());
+            search.semantic(
+                embedder_name.clone(),
+                embedder.clone(),
+                *quantized,
+                query.vector.clone(),
+            );
         }
     }
 
@@ -987,39 +991,13 @@ pub fn perform_search(
         HitsInfo::OffsetLimit { limit, offset, estimated_total_hits: number_of_hits }
     };
 
-    let (facet_distribution, facet_stats) = match facets {
-        Some(ref fields) => {
-            let mut facet_distribution = index.facets_distribution(&rtxn);
-
-            let max_values_by_facet = index
-                .max_values_per_facet(&rtxn)
-                .map_err(milli::Error::from)?
-                .map(|x| x as usize)
-                .unwrap_or(DEFAULT_VALUES_PER_FACET);
-            facet_distribution.max_values_per_facet(max_values_by_facet);
-
-            let sort_facet_values_by =
-                index.sort_facet_values_by(&rtxn).map_err(milli::Error::from)?;
-
-            if fields.iter().all(|f| f != "*") {
-                let fields: Vec<_> =
-                    fields.iter().map(|n| (n, sort_facet_values_by.get(n))).collect();
-                facet_distribution.facets(fields);
-            }
-
-            let distribution = facet_distribution
-                .candidates(candidates)
-                .default_order_by(sort_facet_values_by.get("*"))
-                .execute()?;
-            let stats = facet_distribution.compute_stats()?;
-            (Some(distribution), Some(stats))
-        }
-        None => (None, None),
-    };
-
-    let facet_stats = facet_stats.map(|stats| {
-        stats.into_iter().map(|(k, (min, max))| (k, FacetStats { min, max })).collect()
-    });
+    let (facet_distribution, facet_stats) = facets
+        .map(move |facets| {
+            compute_facet_distribution_stats(&facets, index, &rtxn, candidates, Route::Search)
+        })
+        .transpose()?
+        .map(|ComputedFacets { distribution, stats }| (distribution, stats))
+        .unzip();
 
     let result = SearchResult {
         hits: documents,
@@ -1035,6 +1013,61 @@ pub fn perform_search(
     Ok(result)
 }
 
+#[derive(Debug, Clone, Default, Serialize)]
+pub struct ComputedFacets {
+    pub distribution: BTreeMap<String, IndexMap<String, u64>>,
+    pub stats: BTreeMap<String, FacetStats>,
+}
+
+enum Route {
+    Search,
+    MultiSearch,
+}
+
+fn compute_facet_distribution_stats<S: AsRef<str>>(
+    facets: &[S],
+    index: &Index,
+    rtxn: &RoTxn,
+    candidates: roaring::RoaringBitmap,
+    route: Route,
+) -> Result<ComputedFacets, ResponseError> {
+    let mut facet_distribution = index.facets_distribution(rtxn);
+
+    let max_values_by_facet = index
+        .max_values_per_facet(rtxn)
+        .map_err(milli::Error::from)?
+        .map(|x| x as usize)
+        .unwrap_or(DEFAULT_VALUES_PER_FACET);
+
+    facet_distribution.max_values_per_facet(max_values_by_facet);
+
+    let sort_facet_values_by = index.sort_facet_values_by(rtxn).map_err(milli::Error::from)?;
+
+    // add specific facet if there is no placeholder
+    if facets.iter().all(|f| f.as_ref() != "*") {
+        let fields: Vec<_> =
+            facets.iter().map(|n| (n, sort_facet_values_by.get(n.as_ref()))).collect();
+        facet_distribution.facets(fields);
+    }
+
+    let distribution = facet_distribution
+        .candidates(candidates)
+        .default_order_by(sort_facet_values_by.get("*"))
+        .execute()
+        .map_err(|error| match (error, route) {
+            (
+                error @ milli::Error::UserError(milli::UserError::InvalidFacetsDistribution {
+                    ..
+                }),
+                Route::MultiSearch,
+            ) => ResponseError::from_msg(error.to_string(), Code::InvalidMultiSearchFacets),
+            (error, _) => error.into(),
+        })?;
+    let stats = facet_distribution.compute_stats()?;
+    let stats = stats.into_iter().map(|(k, (min, max))| (k, FacetStats { min, max })).collect();
+    Ok(ComputedFacets { distribution, stats })
+}
+
 pub fn search_from_kind(
     search_kind: SearchKind,
     search: milli::Search<'_>,
@@ -1164,8 +1197,13 @@ impl<'a> HitMaker<'a> {
         let vectors_is_hidden = match (&displayed_ids, vectors_fid) {
             // displayed_ids is a wildcard, so `_vectors` can be displayed regardless of its fid
             (None, _) => false,
-            // displayed_ids is a finite list, and `_vectors` cannot be part of it because it is not an existing field
-            (Some(_), None) => true,
+            // vectors has no fid, so check its explicit name
+            (Some(_), None) => {
+                // unwrap as otherwise we'd go to the first one
+                let displayed_names = index.displayed_fields(rtxn)?.unwrap();
+                !displayed_names
+                    .contains(&milli::vector::parsed_vectors::RESERVED_VECTORS_FIELD_NAME)
+            }
             // displayed_ids is a finit list, so hide if `_vectors` is not part of it
             (Some(map), Some(vectors_fid)) => map.contains(&vectors_fid),
         };
@@ -1369,12 +1407,18 @@ pub fn perform_facet_search(
         None => TimeBudget::default(),
     };
 
+    // In the faceted search context, we want to use the intersection between the locales provided by the user
+    // and the locales of the facet string.
+    // If the facet string is not localized, we **ignore** the locales provided by the user because the facet data has no locale.
+    // If the user does not provide locales, we use the locales of the facet string.
     let localized_attributes = index.localized_attributes_rules(&rtxn)?.unwrap_or_default();
-    let locales = locales.or_else(|| {
-        localized_attributes
+    let localized_attributes_locales =
+        localized_attributes.into_iter().find(|attr| attr.match_str(&facet_name));
+    let locales = localized_attributes_locales.map(|attr| {
+        attr.locales
             .into_iter()
-            .find(|attr| attr.match_str(&facet_name))
-            .map(|attr| attr.locales)
+            .filter(|locale| locales.as_ref().map_or(true, |locales| locales.contains(locale)))
+            .collect()
     });
 
     let (search, _, _, _) =
@@ -1407,6 +1451,7 @@ pub fn perform_similar(
     query: SimilarQuery,
     embedder_name: String,
     embedder: Arc<Embedder>,
+    quantized: bool,
     retrieve_vectors: RetrieveVectors,
     features: RoFeatures,
 ) -> Result<SimilarResult, ResponseError> {
@@ -1435,8 +1480,16 @@ pub fn perform_similar(
         ));
     };
 
-    let mut similar =
-        milli::Similar::new(internal_id, offset, limit, index, &rtxn, embedder_name, embedder);
+    let mut similar = milli::Similar::new(
+        internal_id,
+        offset,
+        limit,
+        index,
+        &rtxn,
+        embedder_name,
+        embedder,
+        quantized,
+    );
 
     if let Some(ref filter) = query.filter {
         if let Some(facets) = parse_filter(filter, Code::InvalidSimilarFilter, features)? {

meilisearch/src/search_queue.rs

@@ -18,6 +18,7 @@
 //!                         And should drop the Permit only once you have freed all the RAM consumed by the method.
 
 use std::num::NonZeroUsize;
+use std::time::Duration;
 
 use rand::rngs::StdRng;
 use rand::{Rng, SeedableRng};
@@ -29,16 +30,31 @@ use crate::error::MeilisearchHttpError;
 pub struct SearchQueue {
     sender: mpsc::Sender<oneshot::Sender<Permit>>,
     capacity: usize,
+    /// If we have waited longer than this to get a permit, we should abort the search request entirely.
+    /// The client probably already closed the connection, but we have no way to find out.
+    time_to_abort: Duration,
 }
 
 /// You should only run search requests while holding this permit.
 /// Once it's dropped, a new search request will be able to process.
+/// You should always try to drop the permit yourself calling the `drop` async method on it.
 #[derive(Debug)]
 pub struct Permit {
     sender: mpsc::Sender<()>,
 }
 
+impl Permit {
+    /// Drop the permit giving back on permit to the search queue.
+    pub async fn drop(self) {
+        // if the channel is closed then the whole instance is down
+        let _ = self.sender.send(()).await;
+    }
+}
+
 impl Drop for Permit {
+    /// The implicit drop implementation can still be called in multiple cases:
+    /// - We forgot to call the explicit one somewhere => this should be fixed on our side asap
+    /// - The future is cancelled while running and the permit dropped with it
     fn drop(&mut self) {
         let sender = self.sender.clone();
         // if the channel is closed then the whole instance is down
@@ -53,7 +69,11 @@ impl SearchQueue {
         let (sender, receiver) = mpsc::channel(1);
 
         tokio::task::spawn(Self::run(capacity, paralellism, receiver));
-        Self { sender, capacity }
+        Self { sender, capacity, time_to_abort: Duration::from_secs(60) }
+    }
+
+    pub fn with_time_to_abort(self, time_to_abort: Duration) -> Self {
+        Self { time_to_abort, ..self }
     }
 
     /// This function is the main loop, it's in charge on scheduling which search request should execute first and
@@ -119,9 +139,23 @@ impl SearchQueue {
     /// Returns a search `Permit`.
     /// It should be dropped as soon as you've freed all the RAM associated with the search request being processed.
     pub async fn try_get_search_permit(&self) -> Result<Permit, MeilisearchHttpError> {
+        let now = std::time::Instant::now();
         let (sender, receiver) = oneshot::channel();
         self.sender.send(sender).await.map_err(|_| MeilisearchHttpError::SearchLimiterIsDown)?;
-        receiver.await.map_err(|_| MeilisearchHttpError::TooManySearchRequests(self.capacity))
+        let permit = receiver
+            .await
+            .map_err(|_| MeilisearchHttpError::TooManySearchRequests(self.capacity))?;
+
+        // If we've been for more than one minute to get a search permit, it's better to simply
+        // abort the search request than spending time processing something were the client
+        // most certainly exited or got a timeout a long time ago.
+        // We may find a better solution in https://github.com/actix/actix-web/issues/3462.
+        if now.elapsed() > self.time_to_abort {
+            permit.drop().await;
+            Err(MeilisearchHttpError::TooManySearchRequests(self.capacity))
+        } else {
+            Ok(permit)
+        }
     }
 
     /// Returns `Ok(())` if everything seems normal.

meilisearch/tests/auth/mod.rs

@@ -5,63 +5,3 @@ mod payload;
 mod tenant_token;
 
 mod tenant_token_multi_search;
-
-use actix_web::http::StatusCode;
-
-use crate::common::{Server, Value};
-use crate::json;
-
-impl Server {
-    pub fn use_api_key(&mut self, api_key: impl AsRef<str>) {
-        self.service.api_key = Some(api_key.as_ref().to_string());
-    }
-
-    /// Fetch and use the default admin key for nexts http requests.
-    pub async fn use_admin_key(&mut self, master_key: impl AsRef<str>) {
-        self.use_api_key(master_key);
-        let (response, code) = self.list_api_keys("").await;
-        assert_eq!(200, code, "{:?}", response);
-        let admin_key = &response["results"][1]["key"];
-        self.use_api_key(admin_key.as_str().unwrap());
-    }
-
-    pub async fn add_api_key(&self, content: Value) -> (Value, StatusCode) {
-        let url = "/keys";
-        self.service.post(url, content).await
-    }
-
-    pub async fn get_api_key(&self, key: impl AsRef<str>) -> (Value, StatusCode) {
-        let url = format!("/keys/{}", key.as_ref());
-        self.service.get(url).await
-    }
-
-    pub async fn patch_api_key(&self, key: impl AsRef<str>, content: Value) -> (Value, StatusCode) {
-        let url = format!("/keys/{}", key.as_ref());
-        self.service.patch(url, content).await
-    }
-
-    pub async fn list_api_keys(&self, params: &str) -> (Value, StatusCode) {
-        let url = format!("/keys{params}");
-        self.service.get(url).await
-    }
-
-    pub async fn delete_api_key(&self, key: impl AsRef<str>) -> (Value, StatusCode) {
-        let url = format!("/keys/{}", key.as_ref());
-        self.service.delete(url).await
-    }
-
-    pub async fn dummy_request(
-        &self,
-        method: impl AsRef<str>,
-        url: impl AsRef<str>,
-    ) -> (Value, StatusCode) {
-        match method.as_ref() {
-            "POST" => self.service.post(url, json!({})).await,
-            "PUT" => self.service.put(url, json!({})).await,
-            "PATCH" => self.service.patch(url, json!({})).await,
-            "GET" => self.service.get(url).await,
-            "DELETE" => self.service.delete(url).await,
-            _ => unreachable!(),
-        }
-    }
-}

meilisearch/tests/auth/tenant_token.rs

@@ -6,7 +6,7 @@ use once_cell::sync::Lazy;
 use time::{Duration, OffsetDateTime};
 
 use super::authorization::{ALL_ACTIONS, AUTHORIZATIONS};
-use crate::common::{Server, Value};
+use crate::common::{Server, Value, DOCUMENTS};
 use crate::json;
 
 fn generate_tenant_token(
@@ -22,36 +22,6 @@ fn generate_tenant_token(
         .unwrap()
 }
 
-static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "title": "Shazam!",
-            "id": "287947",
-            "color": ["green", "blue"]
-        },
-        {
-            "title": "Captain Marvel",
-            "id": "299537",
-            "color": ["yellow", "blue"]
-        },
-        {
-            "title": "Escape Room",
-            "id": "522681",
-            "color": ["yellow", "red"]
-        },
-        {
-            "title": "How to Train Your Dragon: The Hidden World",
-            "id": "166428",
-            "color": ["green", "red"]
-        },
-        {
-            "title": "Glass",
-            "id": "450465",
-            "color": ["blue", "red"]
-        }
-    ])
-});
-
 static INVALID_RESPONSE: Lazy<Value> = Lazy::new(|| {
     json!({
         "message": null,

meilisearch/tests/common/index.rs

@@ -1,4 +1,5 @@
 use std::fmt::Write;
+use std::marker::PhantomData;
 use std::panic::{catch_unwind, resume_unwind, UnwindSafe};
 use std::time::Duration;
 
@@ -9,19 +10,24 @@ use urlencoding::encode as urlencode;
 use super::encoder::Encoder;
 use super::service::Service;
 use super::Value;
+use super::{Owned, Shared};
 use crate::json;
 
-pub struct Index<'a> {
+pub struct Index<'a, State = Owned> {
     pub uid: String,
     pub service: &'a Service,
-    pub encoder: Encoder,
+    pub(super) encoder: Encoder,
+    pub(super) marker: PhantomData<State>,
 }
 
-#[allow(dead_code)]
-impl Index<'_> {
-    pub async fn get(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}", urlencode(self.uid.as_ref()));
-        self.service.get(url).await
+impl<'a> Index<'a, Owned> {
+    pub fn to_shared(&self) -> Index<'a, Shared> {
+        Index {
+            uid: self.uid.clone(),
+            service: self.service,
+            encoder: self.encoder,
+            marker: PhantomData,
+        }
     }
 
     pub async fn load_test_set(&self) -> u64 {
@@ -57,11 +63,7 @@ impl Index<'_> {
     }
 
     pub async fn create(&self, primary_key: Option<&str>) -> (Value, StatusCode) {
-        let body = json!({
-            "uid": self.uid,
-            "primaryKey": primary_key,
-        });
-        self.service.post_encoded("/indexes", body, self.encoder).await
+        self._create(primary_key).await
     }
 
     pub async fn update_raw(&self, body: Value) -> (Value, StatusCode) {
@@ -88,13 +90,7 @@ impl Index<'_> {
         documents: Value,
         primary_key: Option<&str>,
     ) -> (Value, StatusCode) {
-        let url = match primary_key {
-            Some(key) => {
-                format!("/indexes/{}/documents?primaryKey={}", urlencode(self.uid.as_ref()), key)
-            }
-            None => format!("/indexes/{}/documents", urlencode(self.uid.as_ref())),
-        };
-        self.service.post_encoded(url, documents, self.encoder).await
+        self._add_documents(documents, primary_key).await
     }
 
     pub async fn raw_add_documents(
@@ -136,80 +132,11 @@ impl Index<'_> {
         }
     }
 
-    pub async fn wait_task(&self, update_id: u64) -> Value {
-        // try several times to get status, or panic to not wait forever
-        let url = format!("/tasks/{}", update_id);
-        for _ in 0..100 {
-            let (response, status_code) = self.service.get(&url).await;
-            assert_eq!(200, status_code, "response: {}", response);
-
-            if response["status"] == "succeeded" || response["status"] == "failed" {
-                return response;
-            }
-
-            // wait 0.5 second.
-            sleep(Duration::from_millis(500)).await;
-        }
-        panic!("Timeout waiting for update id");
-    }
-
-    pub async fn get_task(&self, update_id: u64) -> (Value, StatusCode) {
-        let url = format!("/tasks/{}", update_id);
-        self.service.get(url).await
-    }
-
     pub async fn list_tasks(&self) -> (Value, StatusCode) {
         let url = format!("/tasks?indexUids={}", self.uid);
         self.service.get(url).await
     }
 
-    pub async fn filtered_tasks(
-        &self,
-        types: &[&str],
-        statuses: &[&str],
-        canceled_by: &[&str],
-    ) -> (Value, StatusCode) {
-        let mut url = format!("/tasks?indexUids={}", self.uid);
-        if !types.is_empty() {
-            let _ = write!(url, "&types={}", types.join(","));
-        }
-        if !statuses.is_empty() {
-            let _ = write!(url, "&statuses={}", statuses.join(","));
-        }
-        if !canceled_by.is_empty() {
-            let _ = write!(url, "&canceledBy={}", canceled_by.join(","));
-        }
-        self.service.get(url).await
-    }
-
-    pub async fn get_document(&self, id: u64, options: Option<Value>) -> (Value, StatusCode) {
-        let mut url = format!("/indexes/{}/documents/{}", urlencode(self.uid.as_ref()), id);
-        if let Some(options) = options {
-            write!(url, "{}", yaup::to_string(&options).unwrap()).unwrap();
-        }
-        self.service.get(url).await
-    }
-
-    pub async fn get_document_by_filter(&self, payload: Value) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/documents/fetch", urlencode(self.uid.as_ref()));
-        self.service.post(url, payload).await
-    }
-
-    pub async fn get_all_documents_raw(&self, options: &str) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/documents{}", urlencode(self.uid.as_ref()), options);
-        self.service.get(url).await
-    }
-
-    pub async fn get_all_documents(&self, options: GetAllDocumentsOptions) -> (Value, StatusCode) {
-        let url = format!(
-            "/indexes/{}/documents{}",
-            urlencode(self.uid.as_ref()),
-            yaup::to_string(&options).unwrap()
-        );
-
-        self.service.get(url).await
-    }
-
     pub async fn delete_document(&self, id: u64) -> (Value, StatusCode) {
         let url = format!("/indexes/{}/documents/{}", urlencode(self.uid.as_ref()), id);
         self.service.delete(url).await
@@ -237,14 +164,8 @@ impl Index<'_> {
         self.service.post_encoded(url, body, self.encoder).await
     }
 
-    pub async fn settings(&self) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/settings", urlencode(self.uid.as_ref()));
-        self.service.get(url).await
-    }
-
     pub async fn update_settings(&self, settings: Value) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/settings", urlencode(self.uid.as_ref()));
-        self.service.patch_encoded(url, settings, self.encoder).await
+        self._update_settings(settings).await
     }
 
     pub async fn update_settings_displayed_attributes(
@@ -327,6 +248,146 @@ impl Index<'_> {
         self.service.delete(url).await
     }
 
+    pub async fn update_distinct_attribute(&self, value: Value) -> (Value, StatusCode) {
+        let url =
+            format!("/indexes/{}/settings/{}", urlencode(self.uid.as_ref()), "distinct-attribute");
+        self.service.put_encoded(url, value, self.encoder).await
+    }
+}
+
+impl<'a> Index<'a, Shared> {
+    /// You cannot modify the content of a shared index, thus the delete_document_by_filter call
+    /// must fail. If the task successfully enqueue itself, we'll wait for the task to finishes,
+    /// and if it succeed the function will panic.
+    pub async fn delete_document_by_filter_fail(&self, body: Value) -> (Value, StatusCode) {
+        let (mut task, code) = self._delete_document_by_filter(body).await;
+        if code.is_success() {
+            task = self.wait_task(task.uid()).await;
+            if task.is_success() {
+                panic!(
+                    "`delete_document_by_filter_fail` succeeded: {}",
+                    serde_json::to_string_pretty(&task).unwrap()
+                );
+            }
+        }
+        (task, code)
+    }
+}
+
+#[allow(dead_code)]
+impl<State> Index<'_, State> {
+    pub async fn get(&self) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}", urlencode(self.uid.as_ref()));
+        self.service.get(url).await
+    }
+
+    /// add_documents is not allowed on shared index but we need to use it to initialize
+    /// a bunch of very common indexes in `common/mod.rs`.
+    pub(super) async fn _add_documents(
+        &self,
+        documents: Value,
+        primary_key: Option<&str>,
+    ) -> (Value, StatusCode) {
+        let url = match primary_key {
+            Some(key) => {
+                format!("/indexes/{}/documents?primaryKey={}", urlencode(self.uid.as_ref()), key)
+            }
+            None => format!("/indexes/{}/documents", urlencode(self.uid.as_ref())),
+        };
+        self.service.post_encoded(url, documents, self.encoder).await
+    }
+
+    pub(super) async fn _update_settings(&self, settings: Value) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}/settings", urlencode(self.uid.as_ref()));
+        self.service.patch_encoded(url, settings, self.encoder).await
+    }
+
+    pub(super) async fn _delete_document_by_filter(&self, body: Value) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}/documents/delete", urlencode(self.uid.as_ref()));
+        self.service.post_encoded(url, body, self.encoder).await
+    }
+
+    pub(super) async fn _create(&self, primary_key: Option<&str>) -> (Value, StatusCode) {
+        let body = json!({
+            "uid": self.uid,
+            "primaryKey": primary_key,
+        });
+        self.service.post_encoded("/indexes", body, self.encoder).await
+    }
+    pub async fn wait_task(&self, update_id: u64) -> Value {
+        // try several times to get status, or panic to not wait forever
+        let url = format!("/tasks/{}", update_id);
+        for _ in 0..100 {
+            let (response, status_code) = self.service.get(&url).await;
+            assert_eq!(200, status_code, "response: {}", response);
+
+            if response["status"] == "succeeded" || response["status"] == "failed" {
+                return response;
+            }
+
+            // wait 0.5 second.
+            sleep(Duration::from_millis(500)).await;
+        }
+        panic!("Timeout waiting for update id");
+    }
+
+    pub async fn get_task(&self, update_id: u64) -> (Value, StatusCode) {
+        let url = format!("/tasks/{}", update_id);
+        self.service.get(url).await
+    }
+
+    pub async fn filtered_tasks(
+        &self,
+        types: &[&str],
+        statuses: &[&str],
+        canceled_by: &[&str],
+    ) -> (Value, StatusCode) {
+        let mut url = format!("/tasks?indexUids={}", self.uid);
+        if !types.is_empty() {
+            let _ = write!(url, "&types={}", types.join(","));
+        }
+        if !statuses.is_empty() {
+            let _ = write!(url, "&statuses={}", statuses.join(","));
+        }
+        if !canceled_by.is_empty() {
+            let _ = write!(url, "&canceledBy={}", canceled_by.join(","));
+        }
+        self.service.get(url).await
+    }
+
+    pub async fn get_document(&self, id: u64, options: Option<Value>) -> (Value, StatusCode) {
+        let mut url = format!("/indexes/{}/documents/{}", urlencode(self.uid.as_ref()), id);
+        if let Some(options) = options {
+            write!(url, "{}", yaup::to_string(&options).unwrap()).unwrap();
+        }
+        self.service.get(url).await
+    }
+
+    pub async fn get_document_by_filter(&self, payload: Value) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}/documents/fetch", urlencode(self.uid.as_ref()));
+        self.service.post(url, payload).await
+    }
+
+    pub async fn get_all_documents_raw(&self, options: &str) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}/documents{}", urlencode(self.uid.as_ref()), options);
+        self.service.get(url).await
+    }
+
+    pub async fn get_all_documents(&self, options: GetAllDocumentsOptions) -> (Value, StatusCode) {
+        let url = format!(
+            "/indexes/{}/documents{}",
+            urlencode(self.uid.as_ref()),
+            yaup::to_string(&options).unwrap()
+        );
+
+        self.service.get(url).await
+    }
+
+    pub async fn settings(&self) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}/settings", urlencode(self.uid.as_ref()));
+        self.service.get(url).await
+    }
+
     pub async fn stats(&self) -> (Value, StatusCode) {
         let url = format!("/indexes/{}/stats", urlencode(self.uid.as_ref()));
         self.service.get(url).await
@@ -411,12 +472,6 @@ impl Index<'_> {
         self.service.post_encoded(url, query, self.encoder).await
     }
 
-    pub async fn update_distinct_attribute(&self, value: Value) -> (Value, StatusCode) {
-        let url =
-            format!("/indexes/{}/settings/{}", urlencode(self.uid.as_ref()), "distinct-attribute");
-        self.service.put_encoded(url, value, self.encoder).await
-    }
-
     pub async fn get_distinct_attribute(&self) -> (Value, StatusCode) {
         let url =
             format!("/indexes/{}/settings/{}", urlencode(self.uid.as_ref()), "distinct-attribute");

meilisearch/tests/common/mod.rs

@@ -8,9 +8,16 @@ use std::fmt::{self, Display};
 #[allow(unused)]
 pub use index::GetAllDocumentsOptions;
 use meili_snap::json_string;
+use once_cell::sync::Lazy;
 use serde::{Deserialize, Serialize};
 #[allow(unused)]
 pub use server::{default_settings, Server};
+use tokio::sync::OnceCell;
+
+use crate::common::index::Index;
+
+pub enum Shared {}
+pub enum Owned {}
 
 #[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq)]
 pub struct Value(pub serde_json::Value);
@@ -27,10 +34,20 @@ impl Value {
         }
     }
 
+    /// Return `true` if the `status` field is set to `succeeded`.
+    /// Panic if the `status` field doesn't exists.
+    #[track_caller]
+    pub fn is_success(&self) -> bool {
+        if !self["status"].is_string() {
+            panic!("Called `is_success` on {}", serde_json::to_string_pretty(&self.0).unwrap());
+        }
+        self["status"] == serde_json::Value::String(String::from("succeeded"))
+    }
+
     // Panic if the json doesn't contain the `status` field set to "succeeded"
     #[track_caller]
     pub fn succeeded(&self) -> &Self {
-        if self["status"] != serde_json::Value::String(String::from("succeeded")) {
+        if !self.is_success() {
             panic!("Called succeeded on {}", serde_json::to_string_pretty(&self.0).unwrap());
         }
         self
@@ -81,6 +98,7 @@ impl Display for Value {
             f,
             "{}",
             json_string!(self, {
+                ".uid" => "[uid]",
                 ".enqueuedAt" => "[date]",
                 ".startedAt" => "[date]",
                 ".finishedAt" => "[date]",
@@ -121,3 +139,253 @@ macro_rules! test_post_get_search {
             .map_err(|e| panic!("panic in post route: {:?}", e.downcast_ref::<&str>().unwrap()));
     };
 }
+
+pub async fn shared_does_not_exists_index() -> &'static Index<'static, Shared> {
+    static INDEX: Lazy<Index<'static, Shared>> = Lazy::new(|| {
+        let server = Server::new_shared();
+        server._index("DOES_NOT_EXISTS").to_shared()
+    });
+    &INDEX
+}
+
+pub async fn shared_empty_index() -> &'static Index<'static, Shared> {
+    static INDEX: OnceCell<Index<'static, Shared>> = OnceCell::const_new();
+
+    INDEX
+        .get_or_init(|| async {
+            let server = Server::new_shared();
+            let index = server._index("EMPTY_INDEX").to_shared();
+            let (response, _code) = index._create(None).await;
+            index.wait_task(response.uid()).await.succeeded();
+            index
+        })
+        .await
+}
+
+pub static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
+    json!([
+        {
+            "title": "Shazam!",
+            "id": "287947",
+            "color": ["green", "blue"],
+            "_vectors": { "manual": [1, 2, 3]},
+        },
+        {
+            "title": "Captain Marvel",
+            "id": "299537",
+            "color": ["yellow", "blue"],
+            "_vectors": { "manual": [1, 2, 54] },
+        },
+        {
+            "title": "Escape Room",
+            "id": "522681",
+            "color": ["yellow", "red"],
+            "_vectors": { "manual": [10, -23, 32] },
+        },
+        {
+            "title": "How to Train Your Dragon: The Hidden World",
+            "id": "166428",
+            "color": ["green", "red"],
+            "_vectors": { "manual": [-100, 231, 32] },
+        },
+        {
+            "title": "Gläss",
+            "id": "450465",
+            "color": ["blue", "red"],
+            "_vectors": { "manual": [-100, 340, 90] },
+        }
+    ])
+});
+
+pub async fn shared_index_with_documents() -> &'static Index<'static, Shared> {
+    static INDEX: OnceCell<Index<'static, Shared>> = OnceCell::const_new();
+    INDEX.get_or_init(|| async {
+        let server = Server::new_shared();
+        let index = server._index("SHARED_DOCUMENTS").to_shared();
+        let documents = DOCUMENTS.clone();
+        let (response, _code) = index._add_documents(documents, None).await;
+        index.wait_task(response.uid()).await.succeeded();
+        let (response, _code) = index
+            ._update_settings(
+                json!({"filterableAttributes": ["id", "title"], "sortableAttributes": ["id", "title"]}),
+            )
+            .await;
+        index.wait_task(response.uid()).await.succeeded();
+        index
+    }).await
+}
+
+pub static SCORE_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
+    json!([
+        {
+            "title": "Batman the dark knight returns: Part 1",
+            "id": "A",
+        },
+        {
+            "title": "Batman the dark knight returns: Part 2",
+            "id": "B",
+        },
+        {
+            "title": "Batman Returns",
+            "id": "C",
+        },
+        {
+            "title": "Batman",
+            "id": "D",
+        },
+        {
+            "title": "Badman",
+            "id": "E",
+        }
+    ])
+});
+
+pub static NESTED_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
+    json!([
+        {
+            "id": 852,
+            "father": "jean",
+            "mother": "michelle",
+            "doggos": [
+                {
+                    "name": "bobby",
+                    "age": 2,
+                },
+                {
+                    "name": "buddy",
+                    "age": 4,
+                },
+            ],
+            "cattos": "pésti",
+            "_vectors": { "manual": [1, 2, 3]},
+        },
+        {
+            "id": 654,
+            "father": "pierre",
+            "mother": "sabine",
+            "doggos": [
+                {
+                    "name": "gros bill",
+                    "age": 8,
+                },
+            ],
+            "cattos": ["simba", "pestiféré"],
+            "_vectors": { "manual": [1, 2, 54] },
+        },
+        {
+            "id": 750,
+            "father": "romain",
+            "mother": "michelle",
+            "cattos": ["enigma"],
+            "_vectors": { "manual": [10, 23, 32] },
+        },
+        {
+            "id": 951,
+            "father": "jean-baptiste",
+            "mother": "sophie",
+            "doggos": [
+                {
+                    "name": "turbo",
+                    "age": 5,
+                },
+                {
+                    "name": "fast",
+                    "age": 6,
+                },
+            ],
+            "cattos": ["moumoute", "gomez"],
+            "_vectors": { "manual": [10, 23, 32] },
+        },
+    ])
+});
+
+pub async fn shared_index_with_nested_documents() -> &'static Index<'static, Shared> {
+    static INDEX: OnceCell<Index<'static, Shared>> = OnceCell::const_new();
+    INDEX.get_or_init(|| async {
+        let server = Server::new_shared();
+        let index = server._index("SHARED_NESTED_DOCUMENTS").to_shared();
+        let documents = NESTED_DOCUMENTS.clone();
+        let (response, _code) = index._add_documents(documents, None).await;
+        index.wait_task(response.uid()).await.succeeded();
+        let (response, _code) = index
+            ._update_settings(
+                json!({"filterableAttributes": ["father", "doggos"], "sortableAttributes": ["doggos"]}),
+            )
+            .await;
+        index.wait_task(response.uid()).await.succeeded();
+        index
+    }).await
+}
+
+pub static FRUITS_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
+    json!([
+        {
+            "name": "Exclusive sale: green apple",
+            "id": "green-apple-boosted",
+            "BOOST": true
+        },
+        {
+            "name": "Pear",
+            "id": "pear",
+        },
+        {
+            "name": "Red apple gala",
+            "id": "red-apple-gala",
+        },
+        {
+            "name": "Exclusive sale: Red Tomato",
+            "id": "red-tomatoes-boosted",
+            "BOOST": true
+        },
+        {
+            "name": "Exclusive sale: Red delicious apple",
+            "id": "red-delicious-boosted",
+            "BOOST": true,
+        }
+    ])
+});
+
+pub static VECTOR_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
+    json!([
+      {
+        "id": "A",
+        "description": "the dog barks at the cat",
+        "_vectors": {
+          // dimensions [canine, feline, young]
+          "animal": [0.9, 0.8, 0.05],
+          // dimensions [negative/positive, energy]
+          "sentiment": [-0.1, 0.55]
+        }
+      },
+      {
+        "id": "B",
+        "description": "the kitten scratched the beagle",
+        "_vectors": {
+          // dimensions [canine, feline, young]
+          "animal": [0.8, 0.9, 0.5],
+          // dimensions [negative/positive, energy]
+          "sentiment": [-0.2, 0.65]
+        }
+      },
+      {
+        "id": "C",
+        "description": "the dog had to stay alone today",
+        "_vectors": {
+          // dimensions [canine, feline, young]
+          "animal": [0.85, 0.02, 0.1],
+          // dimensions [negative/positive, energy]
+          "sentiment": [-1.0, 0.1]
+        }
+      },
+      {
+        "id": "D",
+        "description": "the little boy pets the puppy",
+        "_vectors": {
+          // dimensions [canine, feline, young]
+          "animal": [0.8, 0.09, 0.8],
+          // dimensions [negative/positive, energy]
+          "sentiment": [0.8, 0.3]
+        }
+      },
+    ])
+});

meilisearch/tests/common/server.rs

@@ -1,7 +1,8 @@
 #![allow(dead_code)]
 
+use std::marker::PhantomData;
 use std::path::Path;
-use std::str::FromStr as _;
+use std::str::FromStr;
 use std::time::Duration;
 
 use actix_http::body::MessageBody;
@@ -10,28 +11,34 @@ use actix_web::http::StatusCode;
 use byte_unit::{Byte, Unit};
 use clap::Parser;
 use meilisearch::option::{IndexerOpts, MaxMemory, MaxThreads, Opt};
-use meilisearch::{analytics, create_app, setup_meilisearch, SubscriberForSecondLayer};
+use meilisearch::setup_meilisearch;
 use once_cell::sync::Lazy;
 use tempfile::TempDir;
+use tokio::sync::OnceCell;
 use tokio::time::sleep;
-use tracing::level_filters::LevelFilter;
-use tracing_subscriber::Layer;
+use uuid::Uuid;
 
 use super::index::Index;
 use super::service::Service;
+use super::{Owned, Shared};
 use crate::common::encoder::Encoder;
 use crate::common::Value;
 use crate::json;
 
-pub struct Server {
+pub struct Server<State = Owned> {
     pub service: Service,
     // hold ownership to the tempdir while we use the server instance.
     _dir: Option<TempDir>,
+    _marker: PhantomData<State>,
 }
 
 pub static TEST_TEMP_DIR: Lazy<TempDir> = Lazy::new(|| TempDir::new().unwrap());
 
-impl Server {
+impl Server<Owned> {
+    fn into_shared(self) -> Server<Shared> {
+        Server { service: self.service, _dir: self._dir, _marker: PhantomData }
+    }
+
     pub async fn new() -> Self {
         let dir = TempDir::new().unwrap();
 
@@ -46,7 +53,7 @@ impl Server {
         let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
         let service = Service { index_scheduler, auth, options, api_key: None };
 
-        Server { service, _dir: Some(dir) }
+        Server { service, _dir: Some(dir), _marker: PhantomData }
     }
 
     pub async fn new_auth_with_options(mut options: Opt, dir: TempDir) -> Self {
@@ -61,7 +68,7 @@ impl Server {
         let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
         let service = Service { index_scheduler, auth, options, api_key: None };
 
-        Server { service, _dir: Some(dir) }
+        Server { service, _dir: Some(dir), _marker: PhantomData }
     }
 
     pub async fn new_auth() -> Self {
@@ -74,38 +81,35 @@ impl Server {
         let (index_scheduler, auth) = setup_meilisearch(&options)?;
         let service = Service { index_scheduler, auth, options, api_key: None };
 
-        Ok(Server { service, _dir: None })
+        Ok(Server { service, _dir: None, _marker: PhantomData })
     }
 
-    pub async fn init_web_app(
-        &self,
-    ) -> impl actix_web::dev::Service<
-        actix_http::Request,
-        Response = ServiceResponse<impl MessageBody>,
-        Error = actix_web::Error,
-    > {
-        let (_route_layer, route_layer_handle) =
-            tracing_subscriber::reload::Layer::new(None.with_filter(
-                tracing_subscriber::filter::Targets::new().with_target("", LevelFilter::OFF),
-            ));
-        let (_stderr_layer, stderr_layer_handle) = tracing_subscriber::reload::Layer::new(
-            (Box::new(
-                tracing_subscriber::fmt::layer()
-                    .with_span_events(tracing_subscriber::fmt::format::FmtSpan::CLOSE),
-            )
-                as Box<dyn tracing_subscriber::Layer<SubscriberForSecondLayer> + Send + Sync>)
-                .with_filter(tracing_subscriber::filter::Targets::new()),
-        );
+    pub fn use_api_key(&mut self, api_key: impl AsRef<str>) {
+        self.service.api_key = Some(api_key.as_ref().to_string());
+    }
 
-        actix_web::test::init_service(create_app(
-            self.service.index_scheduler.clone().into(),
-            self.service.auth.clone().into(),
-            self.service.options.clone(),
-            (route_layer_handle, stderr_layer_handle),
-            analytics::MockAnalytics::new(&self.service.options),
-            true,
-        ))
-        .await
+    /// Fetch and use the default admin key for nexts http requests.
+    pub async fn use_admin_key(&mut self, master_key: impl AsRef<str>) {
+        self.use_api_key(master_key);
+        let (response, code) = self.list_api_keys("").await;
+        assert_eq!(200, code, "{:?}", response);
+        let admin_key = &response["results"][1]["key"];
+        self.use_api_key(admin_key.as_str().unwrap());
+    }
+
+    pub async fn add_api_key(&self, content: Value) -> (Value, StatusCode) {
+        let url = "/keys";
+        self.service.post(url, content).await
+    }
+
+    pub async fn patch_api_key(&self, key: impl AsRef<str>, content: Value) -> (Value, StatusCode) {
+        let url = format!("/keys/{}", key.as_ref());
+        self.service.patch(url, content).await
+    }
+
+    pub async fn delete_api_key(&self, key: impl AsRef<str>) -> (Value, StatusCode) {
+        let url = format!("/keys/{}", key.as_ref());
+        self.service.delete(url).await
     }
 
     /// Returns a view to an index. There is no guarantee that the index exists.
@@ -118,15 +122,12 @@ impl Server {
     }
 
     pub fn index_with_encoder(&self, uid: impl AsRef<str>, encoder: Encoder) -> Index<'_> {
-        Index { uid: uid.as_ref().to_string(), service: &self.service, encoder }
-    }
-
-    pub async fn multi_search(&self, queries: Value) -> (Value, StatusCode) {
-        self.service.post("/multi-search", queries).await
-    }
-
-    pub async fn list_indexes_raw(&self, parameters: &str) -> (Value, StatusCode) {
-        self.service.get(format!("/indexes{parameters}")).await
+        Index {
+            uid: uid.as_ref().to_string(),
+            service: &self.service,
+            encoder,
+            marker: PhantomData,
+        }
     }
 
     pub async fn list_indexes(
@@ -150,10 +151,6 @@ impl Server {
         }
     }
 
-    pub async fn version(&self) -> (Value, StatusCode) {
-        self.service.get("/version").await
-    }
-
     pub async fn stats(&self) -> (Value, StatusCode) {
         self.service.get("/stats").await
     }
@@ -162,12 +159,174 @@ impl Server {
         self.service.get("/tasks").await
     }
 
+    pub async fn set_features(&self, value: Value) -> (Value, StatusCode) {
+        self.service.patch("/experimental-features", value).await
+    }
+
+    pub async fn get_metrics(&self) -> (Value, StatusCode) {
+        self.service.get("/metrics").await
+    }
+}
+
+impl Server<Shared> {
+    fn init_new_shared_instance() -> Server<Shared> {
+        let dir = TempDir::new().unwrap();
+
+        if cfg!(windows) {
+            std::env::set_var("TMP", TEST_TEMP_DIR.path());
+        } else {
+            std::env::set_var("TMPDIR", TEST_TEMP_DIR.path());
+        }
+
+        let options = default_settings(dir.path());
+
+        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
+        let service = Service { index_scheduler, auth, api_key: None, options };
+
+        Server { service, _dir: Some(dir), _marker: PhantomData }
+    }
+
+    pub fn new_shared() -> &'static Server<Shared> {
+        static SERVER: Lazy<Server<Shared>> = Lazy::new(Server::init_new_shared_instance);
+        &SERVER
+    }
+
+    pub async fn new_shared_with_admin_key() -> &'static Server<Shared> {
+        static SERVER: OnceCell<Server<Shared>> = OnceCell::const_new();
+        SERVER
+            .get_or_init(|| async {
+                let mut server = Server::new_auth().await;
+                server.use_admin_key("MASTER_KEY").await;
+                server.into_shared()
+            })
+            .await
+    }
+
+    /// You shouldn't access random indexes on a shared instance thus this method
+    /// must fail.
+    pub async fn get_index_fail(&self, uid: impl AsRef<str>) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}", urlencoding::encode(uid.as_ref()));
+        let (value, code) = self.service.get(url).await;
+        if code.is_success() {
+            panic!("`get_index_fail` succeeded with uid: {}", uid.as_ref());
+        }
+        (value, code)
+    }
+
+    pub async fn delete_index_fail(&self, uid: impl AsRef<str>) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}", urlencoding::encode(uid.as_ref()));
+        let (value, code) = self.service.delete(url).await;
+        if code.is_success() {
+            panic!("`delete_index_fail` succeeded with uid: {}", uid.as_ref());
+        }
+        (value, code)
+    }
+
+    pub async fn update_raw_index_fail(
+        &self,
+        uid: impl AsRef<str>,
+        body: Value,
+    ) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}", urlencoding::encode(uid.as_ref()));
+        let (value, code) = self.service.patch_encoded(url, body, Encoder::Plain).await;
+        if code.is_success() {
+            panic!("`update_raw_index_fail` succeeded with uid: {}", uid.as_ref());
+        }
+        (value, code)
+    }
+
+    /// Since this call updates the state of the instance, it must fail.
+    /// If it doesn't fail, the test will panic to help you debug what
+    /// is going on.
+    pub async fn create_index_fail(&self, body: Value) -> (Value, StatusCode) {
+        let (mut task, code) = self._create_index(body).await;
+        if code.is_success() {
+            task = self.wait_task(task.uid()).await;
+            if task.is_success() {
+                panic!(
+                    "`create_index_fail` succeeded: {}",
+                    serde_json::to_string_pretty(&task).unwrap()
+                );
+            }
+        }
+        (task, code)
+    }
+}
+
+impl<State> Server<State> {
+    pub async fn init_web_app(
+        &self,
+    ) -> impl actix_web::dev::Service<
+        actix_http::Request,
+        Response = ServiceResponse<impl MessageBody>,
+        Error = actix_web::Error,
+    > {
+        self.service.init_web_app().await
+    }
+
+    pub async fn list_api_keys(&self, params: &str) -> (Value, StatusCode) {
+        let url = format!("/keys{params}");
+        self.service.get(url).await
+    }
+
+    pub async fn dummy_request(
+        &self,
+        method: impl AsRef<str>,
+        url: impl AsRef<str>,
+    ) -> (Value, StatusCode) {
+        match method.as_ref() {
+            "POST" => self.service.post(url, json!({})).await,
+            "PUT" => self.service.put(url, json!({})).await,
+            "PATCH" => self.service.patch(url, json!({})).await,
+            "GET" => self.service.get(url).await,
+            "DELETE" => self.service.delete(url).await,
+            _ => unreachable!(),
+        }
+    }
+
+    pub async fn get_api_key(&self, key: impl AsRef<str>) -> (Value, StatusCode) {
+        let url = format!("/keys/{}", key.as_ref());
+        self.service.get(url).await
+    }
+
+    pub(super) fn _index(&self, uid: impl AsRef<str>) -> Index<'_> {
+        Index {
+            uid: uid.as_ref().to_string(),
+            service: &self.service,
+            encoder: Encoder::Plain,
+            marker: PhantomData,
+        }
+    }
+
+    /// Returns a view to an index. There is no guarantee that the index exists.
+    pub fn unique_index(&self) -> Index<'_> {
+        let uuid = Uuid::new_v4();
+        Index {
+            uid: uuid.to_string(),
+            service: &self.service,
+            encoder: Encoder::Plain,
+            marker: PhantomData,
+        }
+    }
+
+    pub(super) async fn _create_index(&self, body: Value) -> (Value, StatusCode) {
+        self.service.post("/indexes", body).await
+    }
+
+    pub async fn multi_search(&self, queries: Value) -> (Value, StatusCode) {
+        self.service.post("/multi-search", queries).await
+    }
+
+    pub async fn list_indexes_raw(&self, parameters: &str) -> (Value, StatusCode) {
+        self.service.get(format!("/indexes{parameters}")).await
+    }
+
     pub async fn tasks_filter(&self, filter: &str) -> (Value, StatusCode) {
         self.service.get(format!("/tasks?{}", filter)).await
     }
 
-    pub async fn get_dump_status(&self, uid: &str) -> (Value, StatusCode) {
-        self.service.get(format!("/dumps/{}/status", uid)).await
+    pub async fn version(&self) -> (Value, StatusCode) {
+        self.service.get("/version").await
     }
 
     pub async fn create_dump(&self) -> (Value, StatusCode) {
@@ -215,14 +374,6 @@ impl Server {
     pub async fn get_features(&self) -> (Value, StatusCode) {
         self.service.get("/experimental-features").await
     }
-
-    pub async fn set_features(&self, value: Value) -> (Value, StatusCode) {
-        self.service.patch("/experimental-features", value).await
-    }
-
-    pub async fn get_metrics(&self) -> (Value, StatusCode) {
-        self.service.get("/metrics").await
-    }
 }
 
 pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
@@ -230,7 +381,6 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
         db_path: dir.as_ref().join("db"),
         dump_dir: dir.as_ref().join("dumps"),
         env: "development".to_owned(),
-        #[cfg(feature = "analytics")]
         no_analytics: true,
         max_index_size: Byte::from_u64_with_unit(100, Unit::MiB).unwrap(),
         max_task_db_size: Byte::from_u64_with_unit(1, Unit::GiB).unwrap(),
@@ -240,7 +390,8 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
             // memory has to be unlimited because several meilisearch are running in test context.
             max_indexing_memory: MaxMemory::unlimited(),
             skip_index_budget: true,
-            max_indexing_threads: MaxThreads::from_str("1").unwrap(),
+            // Having 2 threads makes the tests way faster
+            max_indexing_threads: MaxThreads::from_str("2").unwrap(),
         },
         experimental_enable_metrics: false,
         ..Parser::parse_from(None as Option<&str>)

meilisearch/tests/common/service.rs

@@ -1,11 +1,17 @@
+use std::num::NonZeroUsize;
 use std::sync::Arc;
 
+use actix_web::body::MessageBody;
+use actix_web::dev::ServiceResponse;
 use actix_web::http::header::ContentType;
 use actix_web::http::StatusCode;
 use actix_web::test;
 use actix_web::test::TestRequest;
+use actix_web::web::Data;
 use index_scheduler::IndexScheduler;
-use meilisearch::{analytics, create_app, Opt, SubscriberForSecondLayer};
+use meilisearch::analytics::Analytics;
+use meilisearch::search_queue::SearchQueue;
+use meilisearch::{create_app, Opt, SubscriberForSecondLayer};
 use meilisearch_auth::AuthController;
 use tracing::level_filters::LevelFilter;
 use tracing_subscriber::Layer;
@@ -106,7 +112,13 @@ impl Service {
         self.request(req).await
     }
 
-    pub async fn request(&self, mut req: test::TestRequest) -> (Value, StatusCode) {
+    pub async fn init_web_app(
+        &self,
+    ) -> impl actix_web::dev::Service<
+        actix_http::Request,
+        Response = ServiceResponse<impl MessageBody>,
+        Error = actix_web::Error,
+    > {
         let (_route_layer, route_layer_handle) =
             tracing_subscriber::reload::Layer::new(None.with_filter(
                 tracing_subscriber::filter::Targets::new().with_target("", LevelFilter::OFF),
@@ -119,16 +131,25 @@ impl Service {
                 as Box<dyn tracing_subscriber::Layer<SubscriberForSecondLayer> + Send + Sync>)
                 .with_filter(tracing_subscriber::filter::Targets::new()),
         );
+        let search_queue = SearchQueue::new(
+            self.options.experimental_search_queue_size,
+            NonZeroUsize::new(1).unwrap(),
+        );
 
-        let app = test::init_service(create_app(
+        actix_web::test::init_service(create_app(
             self.index_scheduler.clone().into(),
             self.auth.clone().into(),
+            Data::new(search_queue),
             self.options.clone(),
             (route_layer_handle, stderr_layer_handle),
-            analytics::MockAnalytics::new(&self.options),
+            Data::new(Analytics::no_analytics()),
             true,
         ))
-        .await;
+        .await
+    }
+
+    pub async fn request(&self, mut req: test::TestRequest) -> (Value, StatusCode) {
+        let app = self.init_web_app().await;
 
         if let Some(api_key) = &self.api_key {
             req = req.insert_header(("Authorization", ["Bearer ", api_key].concat()));

meilisearch/tests/content_type.rs

@@ -6,6 +6,7 @@ use actix_web::test;
 
 use crate::common::{Server, Value};
 
+#[derive(Debug)]
 enum HttpVerb {
     Put,
     Patch,
@@ -80,7 +81,7 @@ async fn error_json_bad_content_type() {
         let status_code = res.status();
         let body = test::read_body(res).await;
         let response: Value = serde_json::from_slice(&body).unwrap_or_default();
-        assert_eq!(status_code, 415, "calling the route `{}` without content-type is supposed to throw a bad media type error", route);
+        assert_eq!(status_code, 415, "calling the route `{verb:?} {route}` without content-type is supposed to throw a bad media type error:\n{}", String::from_utf8_lossy(&body));
         assert_eq!(
             response,
             json!({

meilisearch/tests/documents/add_documents.rs

@@ -1110,7 +1110,7 @@ async fn document_addition_with_huge_int_primary_key() {
     snapshot!(response,
         @r###"
     {
-      "uid": 0,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1402,7 +1402,7 @@ async fn error_document_field_limit_reached_over_multiple_documents() {
     snapshot!(response,
         @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1436,7 +1436,7 @@ async fn error_document_field_limit_reached_over_multiple_documents() {
     snapshot!(response,
         @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -1485,7 +1485,7 @@ async fn error_document_field_limit_reached_in_one_nested_document() {
     snapshot!(response,
         @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1528,7 +1528,7 @@ async fn error_document_field_limit_reached_over_multiple_documents_with_nested_
     snapshot!(response,
         @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1563,7 +1563,7 @@ async fn error_document_field_limit_reached_over_multiple_documents_with_nested_
     snapshot!(response,
         @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -2209,7 +2209,7 @@ async fn add_invalid_geo_and_then_settings() {
     let ret = index.wait_task(ret.uid()).await;
     snapshot!(ret, @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -2231,7 +2231,7 @@ async fn add_invalid_geo_and_then_settings() {
     let ret = index.wait_task(ret.uid()).await;
     snapshot!(ret, @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "failed",
       "type": "settingsUpdate",

meilisearch/tests/documents/errors.rs

@@ -1,14 +1,15 @@
 use meili_snap::*;
 use urlencoding::encode;
 
-use crate::common::Server;
+use crate::common::{
+    shared_does_not_exists_index, shared_empty_index, shared_index_with_documents, Server,
+};
 use crate::json;
 
 #[actix_rt::test]
 async fn get_all_documents_bad_offset() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.get_all_documents_raw("?offset").await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
@@ -45,9 +46,8 @@ async fn get_all_documents_bad_offset() {
 
 #[actix_rt::test]
 async fn get_all_documents_bad_limit() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.get_all_documents_raw("?limit").await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
@@ -84,17 +84,13 @@ async fn get_all_documents_bad_limit() {
 
 #[actix_rt::test]
 async fn get_all_documents_bad_filter() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let index = shared_does_not_exists_index().await;
 
-    // Since the filter can't be parsed automatically by deserr, we have the wrong error message
-    // if the index does not exist: we could expect to get an error message about the invalid filter before
-    // the existence of the index is checked, but it is not the case.
     let (response, code) = index.get_all_documents_raw("?filter").await;
     snapshot!(code, @"404 Not Found");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Index `test` not found.",
+      "message": "Index `DOES_NOT_EXISTS` not found.",
       "code": "index_not_found",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#index_not_found"
@@ -105,7 +101,7 @@ async fn get_all_documents_bad_filter() {
     snapshot!(code, @"404 Not Found");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Index `test` not found.",
+      "message": "Index `DOES_NOT_EXISTS` not found.",
       "code": "index_not_found",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#index_not_found"
@@ -116,42 +112,14 @@ async fn get_all_documents_bad_filter() {
     snapshot!(code, @"404 Not Found");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Index `test` not found.",
+      "message": "Index `DOES_NOT_EXISTS` not found.",
       "code": "index_not_found",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#index_not_found"
     }
     "###);
 
-    let (response, code) = index.create(None).await;
-    snapshot!(code, @"202 Accepted");
-    snapshot!(json_string!(response, { ".enqueuedAt" => "[date]" }), @r###"
-    {
-      "taskUid": 0,
-      "indexUid": "test",
-      "status": "enqueued",
-      "type": "indexCreation",
-      "enqueuedAt": "[date]"
-    }
-    "###);
-    let response = server.wait_task(0).await;
-    snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" }), @r###"
-    {
-      "uid": 0,
-      "indexUid": "test",
-      "status": "succeeded",
-      "type": "indexCreation",
-      "canceledBy": null,
-      "details": {
-        "primaryKey": null
-      },
-      "error": null,
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
+    let index = shared_empty_index().await;
 
     let (response, code) = index.get_all_documents_raw("?filter").await;
     snapshot!(code, @"200 OK");
@@ -168,7 +136,7 @@ async fn get_all_documents_bad_filter() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `doggo`.\n1:6 doggo",
+      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `doggo`.\n1:6 doggo",
       "code": "invalid_document_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@@ -189,9 +157,8 @@ async fn get_all_documents_bad_filter() {
 
 #[actix_rt::test]
 async fn delete_documents_batch() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.delete_batch_raw(json!("doggo")).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
@@ -206,9 +173,8 @@ async fn delete_documents_batch() {
 
 #[actix_rt::test]
 async fn replace_documents_missing_payload() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) =
         index.raw_add_documents("", vec![("Content-Type", "application/json")], "").await;
     snapshot!(code, @"400 Bad Request");
@@ -248,9 +214,8 @@ async fn replace_documents_missing_payload() {
 
 #[actix_rt::test]
 async fn update_documents_missing_payload() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.raw_update_documents("", Some("application/json"), "").await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
@@ -287,9 +252,8 @@ async fn update_documents_missing_payload() {
 
 #[actix_rt::test]
 async fn replace_documents_missing_content_type() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.raw_add_documents("", Vec::new(), "").await;
     snapshot!(code, @"415 Unsupported Media Type");
     snapshot!(json_string!(response), @r###"
@@ -316,9 +280,8 @@ async fn replace_documents_missing_content_type() {
 
 #[actix_rt::test]
 async fn update_documents_missing_content_type() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.raw_update_documents("", None, "").await;
     snapshot!(code, @"415 Unsupported Media Type");
     snapshot!(json_string!(response), @r###"
@@ -345,9 +308,8 @@ async fn update_documents_missing_content_type() {
 
 #[actix_rt::test]
 async fn replace_documents_bad_content_type() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.raw_add_documents("", vec![("Content-Type", "doggo")], "").await;
     snapshot!(code, @"415 Unsupported Media Type");
     snapshot!(json_string!(response), @r###"
@@ -362,9 +324,8 @@ async fn replace_documents_bad_content_type() {
 
 #[actix_rt::test]
 async fn update_documents_bad_content_type() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.raw_update_documents("", Some("doggo"), "").await;
     snapshot!(code, @"415 Unsupported Media Type");
     snapshot!(json_string!(response), @r###"
@@ -379,9 +340,8 @@ async fn update_documents_bad_content_type() {
 
 #[actix_rt::test]
 async fn replace_documents_bad_csv_delimiter() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index
         .raw_add_documents("", vec![("Content-Type", "application/json")], "?csvDelimiter")
         .await;
@@ -428,9 +388,8 @@ async fn replace_documents_bad_csv_delimiter() {
 
 #[actix_rt::test]
 async fn update_documents_bad_csv_delimiter() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) =
         index.raw_update_documents("", Some("application/json"), "?csvDelimiter").await;
     snapshot!(code, @"400 Bad Request");
@@ -475,9 +434,8 @@ async fn update_documents_bad_csv_delimiter() {
 
 #[actix_rt::test]
 async fn replace_documents_csv_delimiter_with_bad_content_type() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index
         .raw_add_documents("", vec![("Content-Type", "application/json")], "?csvDelimiter=a")
         .await;
@@ -507,9 +465,8 @@ async fn replace_documents_csv_delimiter_with_bad_content_type() {
 
 #[actix_rt::test]
 async fn update_documents_csv_delimiter_with_bad_content_type() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) =
         index.raw_update_documents("", Some("application/json"), "?csvDelimiter=a").await;
     snapshot!(code, @"415 Unsupported Media Type");
@@ -537,13 +494,12 @@ async fn update_documents_csv_delimiter_with_bad_content_type() {
 
 #[actix_rt::test]
 async fn delete_document_by_filter() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    // send a bad payload type
     let (response, code) = index.delete_document_by_filter(json!("hello")).await;
     snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
+    snapshot!(response, @r###"
     {
       "message": "Invalid value type: expected an object, but found a string: `\"hello\"`",
       "code": "bad_request",
@@ -555,7 +511,7 @@ async fn delete_document_by_filter() {
     // send bad payload type
     let (response, code) = index.delete_document_by_filter(json!({ "filter": true })).await;
     snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
+    snapshot!(response, @r###"
     {
       "message": "Invalid syntax for the filter parameter: `expected String, Array, found: true`.",
       "code": "invalid_document_filter",
@@ -567,9 +523,9 @@ async fn delete_document_by_filter() {
     // send bad filter
     let (response, code) = index.delete_document_by_filter(json!({ "filter": "hello"})).await;
     snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
+    snapshot!(response, @r###"
     {
-      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `hello`.\n1:6 hello",
+      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `hello`.\n1:6 hello",
       "code": "invalid_document_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@@ -579,7 +535,7 @@ async fn delete_document_by_filter() {
     // send empty filter
     let (response, code) = index.delete_document_by_filter(json!({ "filter": ""})).await;
     snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
+    snapshot!(response, @r###"
     {
       "message": "Sending an empty filter is forbidden.",
       "code": "invalid_document_filter",
@@ -591,7 +547,7 @@ async fn delete_document_by_filter() {
     // do not send any filter
     let (response, code) = index.delete_document_by_filter(json!({})).await;
     snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
+    snapshot!(response, @r###"
     {
       "message": "Missing field `filter`",
       "code": "missing_document_filter",
@@ -600,15 +556,14 @@ async fn delete_document_by_filter() {
     }
     "###);
 
+    let index = shared_does_not_exists_index().await;
     // index does not exists
-    let (response, code) =
-        index.delete_document_by_filter(json!({ "filter": "doggo = bernese"})).await;
-    snapshot!(code, @"202 Accepted");
-    let response = server.wait_task(response["taskUid"].as_u64().unwrap()).await;
-    snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]"}), @r###"
+    let (response, _code) =
+        index.delete_document_by_filter_fail(json!({ "filter": "doggo = bernese"})).await;
+    snapshot!(response, @r###"
     {
-      "uid": 0,
-      "indexUid": "doggo",
+      "uid": "[uid]",
+      "indexUid": "DOES_NOT_EXISTS",
       "status": "failed",
       "type": "documentDeletion",
       "canceledBy": null,
@@ -618,7 +573,7 @@ async fn delete_document_by_filter() {
         "originalFilter": "\"doggo = bernese\""
       },
       "error": {
-        "message": "Index `doggo` not found.",
+        "message": "Index `DOES_NOT_EXISTS` not found.",
         "code": "index_not_found",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#index_not_found"
@@ -630,19 +585,14 @@ async fn delete_document_by_filter() {
     }
     "###);
 
-    let (response, code) = index.create(None).await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response["taskUid"].as_u64().unwrap()).await;
-
     // no filterable are set
-    let (response, code) =
-        index.delete_document_by_filter(json!({ "filter": "doggo = bernese"})).await;
-    snapshot!(code, @"202 Accepted");
-    let response = server.wait_task(response["taskUid"].as_u64().unwrap()).await;
-    snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]"}), @r###"
+    let index = shared_empty_index().await;
+    let (response, _code) =
+        index.delete_document_by_filter_fail(json!({ "filter": "doggo = bernese"})).await;
+    snapshot!(response, @r###"
     {
-      "uid": 2,
-      "indexUid": "doggo",
+      "uid": "[uid]",
+      "indexUid": "EMPTY_INDEX",
       "status": "failed",
       "type": "documentDeletion",
       "canceledBy": null,
@@ -664,19 +614,16 @@ async fn delete_document_by_filter() {
     }
     "###);
 
-    let (response, code) = index.update_settings_filterable_attributes(json!(["doggo"])).await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response["taskUid"].as_u64().unwrap()).await;
-
     // not filterable while there is a filterable attribute
+    let index = shared_index_with_documents().await;
     let (response, code) =
-        index.delete_document_by_filter(json!({ "filter": "catto = jorts"})).await;
+        index.delete_document_by_filter_fail(json!({ "filter": "catto = jorts"})).await;
     snapshot!(code, @"202 Accepted");
-    let response = server.wait_task(response["taskUid"].as_u64().unwrap()).await;
-    snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]"}), @r###"
+    let response = server.wait_task(response.uid()).await;
+    snapshot!(response, @r###"
     {
-      "uid": 4,
-      "indexUid": "doggo",
+      "uid": "[uid]",
+      "indexUid": "SHARED_DOCUMENTS",
       "status": "failed",
       "type": "documentDeletion",
       "canceledBy": null,
@@ -686,7 +633,7 @@ async fn delete_document_by_filter() {
         "originalFilter": "\"catto = jorts\""
       },
       "error": {
-        "message": "Attribute `catto` is not filterable. Available filterable attributes are: `doggo`.\n1:6 catto = jorts",
+        "message": "Attribute `catto` is not filterable. Available filterable attributes are: `id`, `title`.\n1:6 catto = jorts",
         "code": "invalid_document_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@@ -701,10 +648,10 @@ async fn delete_document_by_filter() {
 
 #[actix_rt::test]
 async fn fetch_document_by_filter() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
+    let server = Server::new_shared();
+    let index = server.unique_index();
     index.update_settings_filterable_attributes(json!(["color"])).await;
-    index
+    let (task, _code) = index
         .add_documents(
             json!([
                 { "id": 0, "color": "red" },
@@ -715,7 +662,7 @@ async fn fetch_document_by_filter() {
             Some("id"),
         )
         .await;
-    index.wait_task(1).await;
+    index.wait_task(task.uid()).await.succeeded();
 
     let (response, code) = index.get_document_by_filter(json!(null)).await;
     snapshot!(code, @"400 Bad Request");
@@ -776,7 +723,7 @@ async fn fetch_document_by_filter() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(response, @r###"
     {
-      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `cool doggo`.\n1:11 cool doggo",
+      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `cool doggo`.\n1:11 cool doggo",
       "code": "invalid_document_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@@ -798,8 +745,7 @@ async fn fetch_document_by_filter() {
 
 #[actix_rt::test]
 async fn retrieve_vectors() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
+    let index = shared_empty_index().await;
 
     // GET ALL DOCUMENTS BY QUERY
     let (response, _code) = index.get_all_documents_raw("?retrieveVectors=tamo").await;

meilisearch/tests/dumps/mod.rs

@@ -2097,7 +2097,8 @@ async fn generate_and_import_dump_containing_vectors() {
           "source": "huggingFace",
           "model": "sentence-transformers/all-MiniLM-L6-v2",
           "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
-          "documentTemplate": "{{doc.doggo}}"
+          "documentTemplate": "{{doc.doggo}}",
+          "documentTemplateMaxBytes": 400
         }
       },
       "searchCutoffMs": null,

meilisearch/tests/dumps/snapshots/mod.rs/generate_and_import_dump_containing_vectors/1.snap

@@ -2,7 +2,7 @@
 source: meilisearch/tests/dumps/mod.rs
 ---
 {
-  "uid": 0,
+  "uid": "[uid]",
   "indexUid": "pets",
   "status": "succeeded",
   "type": "settingsUpdate",

meilisearch/tests/dumps/snapshots/mod.rs/generate_and_import_dump_containing_vectors/2.snap

@@ -2,7 +2,7 @@
 source: meilisearch/tests/dumps/mod.rs
 ---
 {
-  "uid": 1,
+  "uid": "[uid]",
   "indexUid": "pets",
   "status": "succeeded",
   "type": "documentAdditionOrUpdate",

meilisearch/tests/index/errors.rs

@@ -5,7 +5,7 @@ use crate::json;
 
 #[actix_rt::test]
 async fn get_indexes_bad_offset() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.list_indexes_raw("?offset=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -21,7 +21,7 @@ async fn get_indexes_bad_offset() {
 
 #[actix_rt::test]
 async fn get_indexes_bad_limit() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.list_indexes_raw("?limit=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -37,7 +37,7 @@ async fn get_indexes_bad_limit() {
 
 #[actix_rt::test]
 async fn get_indexes_unknown_field() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.list_indexes_raw("?doggo=nolimit").await;
     snapshot!(code, @"400 Bad Request");
@@ -53,9 +53,9 @@ async fn get_indexes_unknown_field() {
 
 #[actix_rt::test]
 async fn create_index_missing_uid() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
-    let (response, code) = server.create_index(json!({ "primaryKey": "doggo" })).await;
+    let (response, code) = server.create_index_fail(json!({ "primaryKey": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -69,9 +69,9 @@ async fn create_index_missing_uid() {
 
 #[actix_rt::test]
 async fn create_index_bad_uid() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
-    let (response, code) = server.create_index(json!({ "uid": "the best doggo" })).await;
+    let (response, code) = server.create_index_fail(json!({ "uid": "the best doggo" })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -82,7 +82,7 @@ async fn create_index_bad_uid() {
     }
     "###);
 
-    let (response, code) = server.create_index(json!({ "uid": true })).await;
+    let (response, code) = server.create_index_fail(json!({ "uid": true })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -96,10 +96,10 @@ async fn create_index_bad_uid() {
 
 #[actix_rt::test]
 async fn create_index_bad_primary_key() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server
-        .create_index(json!({ "uid": "doggo", "primaryKey": ["the", "best", "doggo"] }))
+        .create_index_fail(json!({ "uid": "doggo", "primaryKey": ["the", "best", "doggo"] }))
         .await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
@@ -114,9 +114,10 @@ async fn create_index_bad_primary_key() {
 
 #[actix_rt::test]
 async fn create_index_unknown_field() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
-    let (response, code) = server.create_index(json!({ "uid": "doggo", "doggo": "bernese" })).await;
+    let (response, code) =
+        server.create_index_fail(json!({ "uid": "doggo", "doggo": "bernese" })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -130,10 +131,8 @@ async fn create_index_unknown_field() {
 
 #[actix_rt::test]
 async fn get_index_bad_uid() {
-    let server = Server::new().await;
-    let index = server.index("the good doggo");
-
-    let (response, code) = index.get().await;
+    let server = Server::new_shared();
+    let (response, code) = server.get_index_fail("the good doggo").await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -147,9 +146,8 @@ async fn get_index_bad_uid() {
 
 #[actix_rt::test]
 async fn update_index_bad_primary_key() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.update_raw(json!({ "primaryKey": ["doggo"] })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
@@ -164,9 +162,8 @@ async fn update_index_bad_primary_key() {
 
 #[actix_rt::test]
 async fn update_index_immutable_uid() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.update_raw(json!({ "uid": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
@@ -181,9 +178,8 @@ async fn update_index_immutable_uid() {
 
 #[actix_rt::test]
 async fn update_index_immutable_created_at() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.update_raw(json!({ "createdAt": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
@@ -198,9 +194,8 @@ async fn update_index_immutable_created_at() {
 
 #[actix_rt::test]
 async fn update_index_immutable_updated_at() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.update_raw(json!({ "updatedAt": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
@@ -215,9 +210,8 @@ async fn update_index_immutable_updated_at() {
 
 #[actix_rt::test]
 async fn update_index_unknown_field() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
-
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (response, code) = index.update_raw(json!({ "doggo": "bork" })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
@@ -232,10 +226,9 @@ async fn update_index_unknown_field() {
 
 #[actix_rt::test]
 async fn update_index_bad_uid() {
-    let server = Server::new().await;
-    let index = server.index("the good doggo");
-
-    let (response, code) = index.update_raw(json!({ "primaryKey": "doggo" })).await;
+    let server = Server::new_shared();
+    let (response, code) =
+        server.update_raw_index_fail("the good doggo", json!({ "primaryKey": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -249,10 +242,8 @@ async fn update_index_bad_uid() {
 
 #[actix_rt::test]
 async fn delete_index_bad_uid() {
-    let server = Server::new().await;
-    let index = server.index("the good doggo");
-
-    let (response, code) = index.delete().await;
+    let server = Server::new_shared();
+    let (response, code) = server.delete_index_fail("the good doggo").await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {

meilisearch/tests/logs/error.rs

@@ -5,7 +5,7 @@ use crate::json;
 
 #[actix_rt::test]
 async fn logs_stream_bad_target() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     // Wrong type
     let (response, code) = server.service.post("/logs/stream", json!({ "target": true })).await;
@@ -58,7 +58,7 @@ async fn logs_stream_bad_target() {
 
 #[actix_rt::test]
 async fn logs_stream_bad_mode() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     // Wrong type
     let (response, code) = server.service.post("/logs/stream", json!({ "mode": true })).await;
@@ -99,7 +99,7 @@ async fn logs_stream_bad_mode() {
 
 #[actix_rt::test]
 async fn logs_stream_bad_profile_memory() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     // Wrong type
     let (response, code) =
@@ -156,7 +156,7 @@ async fn logs_stream_bad_profile_memory() {
 
 #[actix_rt::test]
 async fn logs_stream_without_enabling_the_route() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.service.post("/logs/stream", json!({})).await;
     snapshot!(code, @"400 Bad Request");

meilisearch/tests/logs/mod.rs

@@ -1,11 +1,15 @@
 mod error;
 
+use std::num::NonZeroUsize;
 use std::rc::Rc;
 use std::str::FromStr;
 
 use actix_web::http::header::ContentType;
+use actix_web::web::Data;
 use meili_snap::snapshot;
-use meilisearch::{analytics, create_app, Opt, SubscriberForSecondLayer};
+use meilisearch::analytics::Analytics;
+use meilisearch::search_queue::SearchQueue;
+use meilisearch::{create_app, Opt, SubscriberForSecondLayer};
 use tracing::level_filters::LevelFilter;
 use tracing_subscriber::layer::SubscriberExt;
 use tracing_subscriber::Layer;
@@ -40,13 +44,18 @@ async fn basic_test_log_stream_route() {
             .with_span_events(tracing_subscriber::fmt::format::FmtSpan::ACTIVE)
             .with_filter(tracing_subscriber::filter::LevelFilter::from_str("OFF").unwrap()),
     );
+    let search_queue = SearchQueue::new(
+        server.service.options.experimental_search_queue_size,
+        NonZeroUsize::new(1).unwrap(),
+    );
 
     let app = actix_web::test::init_service(create_app(
         server.service.index_scheduler.clone().into(),
         server.service.auth.clone().into(),
+        Data::new(search_queue),
         server.service.options.clone(),
         (route_layer_handle, stderr_layer_handle),
-        analytics::MockAnalytics::new(&server.service.options),
+        Data::new(Analytics::no_analytics()),
         true,
     ))
     .await;

meilisearch/tests/search/errors.rs

@@ -1,16 +1,13 @@
 use meili_snap::*;
 
-use super::DOCUMENTS;
-use crate::common::Server;
+use crate::common::{shared_does_not_exists_index, Server};
 use crate::json;
 
 #[actix_rt::test]
 async fn search_unexisting_index() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
+    let index = shared_does_not_exists_index().await;
     let expected_response = json!({
-        "message": "Index `test` not found.",
+        "message": "Index `DOES_NOT_EXISTS` not found.",
         "code": "index_not_found",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#index_not_found"
@@ -26,8 +23,8 @@ async fn search_unexisting_index() {
 
 #[actix_rt::test]
 async fn search_unexisting_parameter() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     index
         .search(json!({"marin": "hello"}), |response, code| {
@@ -39,8 +36,8 @@ async fn search_unexisting_parameter() {
 
 #[actix_rt::test]
 async fn search_bad_q() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"q": ["doggo"]})).await;
     snapshot!(code, @"400 Bad Request");
@@ -57,8 +54,8 @@ async fn search_bad_q() {
 
 #[actix_rt::test]
 async fn search_bad_offset() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"offset": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -85,8 +82,8 @@ async fn search_bad_offset() {
 
 #[actix_rt::test]
 async fn search_bad_limit() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"limit": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -113,8 +110,8 @@ async fn search_bad_limit() {
 
 #[actix_rt::test]
 async fn search_bad_page() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"page": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -141,8 +138,8 @@ async fn search_bad_page() {
 
 #[actix_rt::test]
 async fn search_bad_hits_per_page() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"hitsPerPage": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -169,8 +166,8 @@ async fn search_bad_hits_per_page() {
 
 #[actix_rt::test]
 async fn search_bad_attributes_to_retrieve() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"attributesToRetrieve": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -187,8 +184,8 @@ async fn search_bad_attributes_to_retrieve() {
 
 #[actix_rt::test]
 async fn search_bad_retrieve_vectors() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"retrieveVectors": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -237,8 +234,8 @@ async fn search_bad_retrieve_vectors() {
 
 #[actix_rt::test]
 async fn search_bad_attributes_to_crop() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"attributesToCrop": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -255,8 +252,8 @@ async fn search_bad_attributes_to_crop() {
 
 #[actix_rt::test]
 async fn search_bad_crop_length() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"cropLength": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -283,8 +280,8 @@ async fn search_bad_crop_length() {
 
 #[actix_rt::test]
 async fn search_bad_attributes_to_highlight() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"attributesToHighlight": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -303,14 +300,12 @@ async fn search_bad_attributes_to_highlight() {
 async fn search_bad_filter() {
     // Since a filter is deserialized as a json Value it will never fail to deserialize.
     // Thus the error message is not generated by deserr but written by us.
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
     // Also, to trigger the error message we need to effectively create the index or else it'll throw an
     // index does not exists error.
-    let (_, code) = index.create(None).await;
-    server.wait_task(0).await;
-
-    snapshot!(code, @"202 Accepted");
+    let (response, _code) = index.create(None).await;
+    server.wait_task(response.uid()).await.succeeded();
 
     let (response, code) = index.search_post(json!({ "filter": true })).await;
     snapshot!(code, @"400 Bad Request");
@@ -327,8 +322,8 @@ async fn search_bad_filter() {
 
 #[actix_rt::test]
 async fn search_bad_sort() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"sort": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -345,8 +340,8 @@ async fn search_bad_sort() {
 
 #[actix_rt::test]
 async fn search_bad_show_matches_position() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"showMatchesPosition": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -373,8 +368,8 @@ async fn search_bad_show_matches_position() {
 
 #[actix_rt::test]
 async fn search_bad_facets() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"facets": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -391,8 +386,8 @@ async fn search_bad_facets() {
 
 #[actix_rt::test]
 async fn search_bad_threshold() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"rankingScoreThreshold": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -408,8 +403,8 @@ async fn search_bad_threshold() {
 
 #[actix_rt::test]
 async fn search_invalid_threshold() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"rankingScoreThreshold": 42})).await;
     snapshot!(code, @"400 Bad Request");
@@ -425,11 +420,11 @@ async fn search_invalid_threshold() {
 
 #[actix_rt::test]
 async fn search_non_filterable_facets() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+    let server = Server::new_shared();
+    let index = server.unique_index();
+    let (response, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
     // Wait for the settings update to complete
-    index.wait_task(0).await;
+    index.wait_task(response.uid()).await.succeeded();
 
     let (response, code) = index.search_post(json!({"facets": ["doggo"]})).await;
     snapshot!(code, @"400 Bad Request");
@@ -456,10 +451,11 @@ async fn search_non_filterable_facets() {
 
 #[actix_rt::test]
 async fn search_non_filterable_facets_multiple_filterable() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    index.update_settings(json!({"filterableAttributes": ["title", "genres"]})).await;
-    index.wait_task(0).await;
+    let server = Server::new_shared();
+    let index = server.unique_index();
+    let (response, _code) =
+        index.update_settings(json!({"filterableAttributes": ["title", "genres"]})).await;
+    index.wait_task(response.uid()).await.succeeded();
 
     let (response, code) = index.search_post(json!({"facets": ["doggo"]})).await;
     snapshot!(code, @"400 Bad Request");
@@ -486,10 +482,10 @@ async fn search_non_filterable_facets_multiple_filterable() {
 
 #[actix_rt::test]
 async fn search_non_filterable_facets_no_filterable() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    index.update_settings(json!({"filterableAttributes": []})).await;
-    index.wait_task(0).await;
+    let server = Server::new_shared();
+    let index = server.unique_index();
+    let (response, _code) = index.update_settings(json!({"filterableAttributes": []})).await;
+    index.wait_task(response.uid()).await.succeeded();
 
     let (response, code) = index.search_post(json!({"facets": ["doggo"]})).await;
     snapshot!(code, @"400 Bad Request");
@@ -516,10 +512,11 @@ async fn search_non_filterable_facets_no_filterable() {
 
 #[actix_rt::test]
 async fn search_non_filterable_facets_multiple_facets() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    index.update_settings(json!({"filterableAttributes": ["title", "genres"]})).await;
-    index.wait_task(0).await;
+    let server = Server::new_shared();
+    let index = server.unique_index();
+    let (response, _uid) =
+        index.update_settings(json!({"filterableAttributes": ["title", "genres"]})).await;
+    index.wait_task(response.uid()).await.succeeded();
 
     let (response, code) = index.search_post(json!({"facets": ["doggo", "neko"]})).await;
     snapshot!(code, @"400 Bad Request");
@@ -546,8 +543,8 @@ async fn search_non_filterable_facets_multiple_facets() {
 
 #[actix_rt::test]
 async fn search_bad_highlight_pre_tag() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"highlightPreTag": ["doggo"]})).await;
     snapshot!(code, @"400 Bad Request");
@@ -564,8 +561,8 @@ async fn search_bad_highlight_pre_tag() {
 
 #[actix_rt::test]
 async fn search_bad_highlight_post_tag() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"highlightPostTag": ["doggo"]})).await;
     snapshot!(code, @"400 Bad Request");
@@ -582,8 +579,8 @@ async fn search_bad_highlight_post_tag() {
 
 #[actix_rt::test]
 async fn search_bad_crop_marker() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"cropMarker": ["doggo"]})).await;
     snapshot!(code, @"400 Bad Request");
@@ -600,8 +597,8 @@ async fn search_bad_crop_marker() {
 
 #[actix_rt::test]
 async fn search_bad_matching_strategy() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.search_post(json!({"matchingStrategy": "doggo"})).await;
     snapshot!(code, @"400 Bad Request");
@@ -639,20 +636,17 @@ async fn search_bad_matching_strategy() {
 
 #[actix_rt::test]
 async fn filter_invalid_syntax_object() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    let (task, _code) = index.add_documents(documents, None).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
     index.wait_task(task.uid()).await;
 
     index
         .search(json!({"filter": "title & Glass"}), |response, code| {
             snapshot!(response, @r###"
             {
-              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
               "code": "invalid_search_filter",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -665,20 +659,17 @@ async fn filter_invalid_syntax_object() {
 
 #[actix_rt::test]
 async fn filter_invalid_syntax_array() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    let (task, _code) = index.add_documents(documents, None).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
     index.wait_task(task.uid()).await;
 
     index
         .search(json!({"filter": ["title & Glass"]}), |response, code| {
             snapshot!(response, @r###"
             {
-              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
               "code": "invalid_search_filter",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -691,14 +682,11 @@ async fn filter_invalid_syntax_array() {
 
 #[actix_rt::test]
 async fn filter_invalid_syntax_string() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
         "message": "Found unexpected characters at the end of the filter: `XOR title = Glass`. You probably forgot an `OR` or an `AND` rule.\n15:32 title = Glass XOR title = Glass",
@@ -716,14 +704,11 @@ async fn filter_invalid_syntax_string() {
 
 #[actix_rt::test]
 async fn filter_invalid_attribute_array() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
         "message": "Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass",
@@ -741,14 +726,11 @@ async fn filter_invalid_attribute_array() {
 
 #[actix_rt::test]
 async fn filter_invalid_attribute_string() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
         "message": "Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass",
@@ -766,14 +748,11 @@ async fn filter_invalid_attribute_string() {
 
 #[actix_rt::test]
 async fn filter_reserved_geo_attribute_array() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
         "message": "`_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:13 _geo = Glass",
@@ -791,14 +770,11 @@ async fn filter_reserved_geo_attribute_array() {
 
 #[actix_rt::test]
 async fn filter_reserved_geo_attribute_string() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
         "message": "`_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:13 _geo = Glass",
@@ -816,14 +792,11 @@ async fn filter_reserved_geo_attribute_string() {
 
 #[actix_rt::test]
 async fn filter_reserved_attribute_array() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
         "message": "`_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:21 _geoDistance = Glass",
@@ -841,14 +814,11 @@ async fn filter_reserved_attribute_array() {
 
 #[actix_rt::test]
 async fn filter_reserved_attribute_string() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
        "message": "`_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:21 _geoDistance = Glass",
@@ -866,14 +836,11 @@ async fn filter_reserved_attribute_string() {
 
 #[actix_rt::test]
 async fn filter_reserved_geo_point_array() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
         "message": "`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:18 _geoPoint = Glass",
@@ -891,14 +858,11 @@ async fn filter_reserved_geo_point_array() {
 
 #[actix_rt::test]
 async fn filter_reserved_geo_point_string() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
        "message": "`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:18 _geoPoint = Glass",
@@ -916,14 +880,11 @@ async fn filter_reserved_geo_point_string() {
 
 #[actix_rt::test]
 async fn sort_geo_reserved_attribute() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"sortableAttributes": ["id"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"sortableAttributes": ["id"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
         "message": "`_geo` is a reserved keyword and thus can't be used as a sort expression. Use the _geoPoint(latitude, longitude) built-in rule to sort on _geo field coordinates.",
@@ -946,14 +907,11 @@ async fn sort_geo_reserved_attribute() {
 
 #[actix_rt::test]
 async fn sort_reserved_attribute() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"sortableAttributes": ["id"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.update_settings(json!({"sortableAttributes": ["id"]})).await;
+    index.wait_task(task.uid()).await;
 
     let expected_response = json!({
         "message": "`_geoDistance` is a reserved keyword and thus can't be used as a sort expression.",
@@ -976,14 +934,10 @@ async fn sort_reserved_attribute() {
 
 #[actix_rt::test]
 async fn sort_unsortable_attribute() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    index.update_settings(json!({"sortableAttributes": ["id"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let server = Server::new_shared();
+    let index = server.unique_index();
+    let (response, _code) = index.update_settings(json!({"sortableAttributes": ["id"]})).await;
+    index.wait_task(response.uid()).await.succeeded();
 
     let expected_response = json!({
         "message": "Attribute `title` is not sortable. Available sortable attributes are: `id`.",
@@ -1006,14 +960,11 @@ async fn sort_unsortable_attribute() {
 
 #[actix_rt::test]
 async fn sort_invalid_syntax() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index.update_settings(json!({"sortableAttributes": ["id"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (response, _code) = index.update_settings(json!({"sortableAttributes": ["id"]})).await;
+    index.wait_task(response.uid()).await.succeeded();
 
     let expected_response = json!({
         "message": "Invalid syntax for the sort parameter: expected expression ending by `:asc` or `:desc`, found `title`.",
@@ -1036,18 +987,15 @@ async fn sort_invalid_syntax() {
 
 #[actix_rt::test]
 async fn sort_unset_ranking_rule() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
-    index
+    let (response, _code) = index
         .update_settings(
             json!({"sortableAttributes": ["title"], "rankingRules": ["proximity", "exactness"]}),
         )
         .await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    index.wait_task(response.uid()).await.succeeded();
 
     let expected_response = json!({
         "message": "You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.",
@@ -1070,14 +1018,11 @@ async fn sort_unset_ranking_rule() {
 
 #[actix_rt::test]
 async fn search_on_unknown_field() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    index.update_settings_searchable_attributes(json!(["id", "title"])).await;
-    index.wait_task(0).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let server = Server::new_shared();
+    let index = server.unique_index();
+    let (response, _code) =
+        index.update_settings_searchable_attributes(json!(["id", "title"])).await;
+    index.wait_task(response.uid()).await.succeeded();
 
     index
         .search(
@@ -1099,14 +1044,11 @@ async fn search_on_unknown_field() {
 
 #[actix_rt::test]
 async fn search_on_unknown_field_plus_joker() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    index.update_settings_searchable_attributes(json!(["id", "title"])).await;
-    index.wait_task(0).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let server = Server::new_shared();
+    let index = server.unique_index();
+    let (response, _code) =
+        index.update_settings_searchable_attributes(json!(["id", "title"])).await;
+    index.wait_task(response.uid()).await.succeeded();
 
     index
         .search(
@@ -1145,11 +1087,10 @@ async fn search_on_unknown_field_plus_joker() {
 
 #[actix_rt::test]
 async fn distinct_at_search_time() {
-    let server = Server::new().await;
-    let index = server.index("tamo");
+    let server = Server::new_shared();
+    let index = server.unique_index();
     let (task, _) = index.create(None).await;
-    let task = index.wait_task(task.uid()).await;
-    snapshot!(task, name: "task-succeed");
+    index.wait_task(task.uid()).await.succeeded();
 
     let (response, code) =
         index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": "doggo.truc"})).await;
@@ -1210,8 +1151,8 @@ async fn distinct_at_search_time() {
 async fn search_with_contains_without_enabling_the_feature() {
     // Since a filter is deserialized as a json Value it will never fail to deserialize.
     // Thus the error message is not generated by deserr but written by us.
-    let server = Server::new().await;
-    let index = server.index("doggo");
+    let server = Server::new_shared();
+    let index = server.unique_index();
     // Also, to trigger the error message we need to effectively create the index or else it'll throw an
     // index does not exists error.
     let (task, _code) = index.create(None).await;
@@ -1222,7 +1163,7 @@ async fn search_with_contains_without_enabling_the_feature() {
             snapshot!(code, @"400 Bad Request");
             snapshot!(json_string!(response), @r###"
             {
-              "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
+              "message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
               "code": "feature_not_enabled",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
@@ -1235,7 +1176,7 @@ async fn search_with_contains_without_enabling_the_feature() {
             snapshot!(code, @"400 Bad Request");
             snapshot!(json_string!(response), @r###"
             {
-              "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n25:33 doggo != echo AND doggo CONTAINS kefir",
+              "message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n25:33 doggo != echo AND doggo CONTAINS kefir",
               "code": "feature_not_enabled",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
@@ -1251,7 +1192,7 @@ async fn search_with_contains_without_enabling_the_feature() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
+      "message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
       "code": "feature_not_enabled",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
@@ -1263,7 +1204,7 @@ async fn search_with_contains_without_enabling_the_feature() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
+      "message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
       "code": "feature_not_enabled",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#feature_not_enabled"

meilisearch/tests/search/hybrid.rs

@@ -128,7 +128,7 @@ async fn simple_search() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2}, "retrieveVectors": true}),
+            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2, "embedder": "default"}, "retrieveVectors": true}),
         )
         .await;
     snapshot!(code, @"200 OK");
@@ -137,7 +137,7 @@ async fn simple_search() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.5}, "showRankingScore": true, "retrieveVectors": true}),
+            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.5, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
         )
         .await;
     snapshot!(code, @"200 OK");
@@ -146,7 +146,7 @@ async fn simple_search() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.8}, "showRankingScore": true, "retrieveVectors": true}),
+            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.8, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
         )
         .await;
     snapshot!(code, @"200 OK");
@@ -161,7 +161,7 @@ async fn limit_offset() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2}, "retrieveVectors": true, "offset": 1, "limit": 1}),
+            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2, "embedder": "default"}, "retrieveVectors": true, "offset": 1, "limit": 1}),
         )
         .await;
     snapshot!(code, @"200 OK");
@@ -174,7 +174,7 @@ async fn limit_offset() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.9}, "retrieveVectors": true, "offset": 1, "limit": 1}),
+            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.9, "embedder": "default"}, "retrieveVectors": true, "offset": 1, "limit": 1}),
         )
         .await;
     snapshot!(code, @"200 OK");
@@ -188,8 +188,11 @@ async fn simple_search_hf() {
     let server = Server::new().await;
     let index = index_with_documents_hf(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
 
-    let (response, code) =
-        index.search_post(json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2}})).await;
+    let (response, code) = index
+        .search_post(
+            json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2, "embedder": "default"}}),
+        )
+        .await;
     snapshot!(code, @"200 OK");
     snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"}]"###);
     snapshot!(response["semanticHitCount"], @"0");
@@ -197,7 +200,7 @@ async fn simple_search_hf() {
     let (response, code) = index
         .search_post(
             // disable ranking score as the vectors between architectures are not equal
-            json!({"q": "Captain", "hybrid": {"semanticRatio": 0.55}, "showRankingScore": false}),
+            json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.55}, "showRankingScore": false}),
         )
         .await;
     snapshot!(code, @"200 OK");
@@ -206,7 +209,7 @@ async fn simple_search_hf() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "hybrid": {"semanticRatio": 0.8}, "showRankingScore": false}),
+            json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.8}, "showRankingScore": false}),
         )
         .await;
     snapshot!(code, @"200 OK");
@@ -215,7 +218,7 @@ async fn simple_search_hf() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Movie World", "hybrid": {"semanticRatio": 0.2}, "showRankingScore": false}),
+            json!({"q": "Movie World", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "showRankingScore": false}),
         )
         .await;
     snapshot!(code, @"200 OK");
@@ -224,7 +227,7 @@ async fn simple_search_hf() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Wonder replacement", "hybrid": {"semanticRatio": 0.2}, "showRankingScore": false}),
+            json!({"q": "Wonder replacement", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "showRankingScore": false}),
         )
         .await;
     snapshot!(code, @"200 OK");
@@ -237,7 +240,7 @@ async fn distribution_shift() {
     let server = Server::new().await;
     let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
 
-    let search = json!({"q": "Captain", "vector": [1.0, 1.0], "showRankingScore": true, "hybrid": {"semanticRatio": 1.0}, "retrieveVectors": true});
+    let search = json!({"q": "Captain", "vector": [1.0, 1.0], "showRankingScore": true, "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "retrieveVectors": true});
     let (response, code) = index.search_post(search.clone()).await;
     snapshot!(code, @"200 OK");
     snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.9472135901451112}]"###);
@@ -271,7 +274,7 @@ async fn highlighter() {
 
     let (response, code) = index
         .search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
-            "hybrid": {"semanticRatio": 0.2},
+            "hybrid": {"embedder": "default", "semanticRatio": 0.2},
            "retrieveVectors": true,
            "attributesToHighlight": [
                      "desc",
@@ -287,7 +290,7 @@ async fn highlighter() {
 
     let (response, code) = index
         .search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
-            "hybrid": {"semanticRatio": 0.8},
+            "hybrid": {"embedder": "default", "semanticRatio": 0.8},
             "retrieveVectors": true,
             "showRankingScore": true,
             "attributesToHighlight": [
@@ -304,7 +307,7 @@ async fn highlighter() {
     // no highlighting on full semantic
     let (response, code) = index
         .search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
-            "hybrid": {"semanticRatio": 1.0},
+            "hybrid": {"embedder": "default", "semanticRatio": 1.0},
             "retrieveVectors": true,
             "showRankingScore": true,
             "attributesToHighlight": [
@@ -326,7 +329,7 @@ async fn invalid_semantic_ratio() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 1.2}}),
+            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"embedder": "default", "semanticRatio": 1.2}}),
         )
         .await;
     snapshot!(code, @"400 Bad Request");
@@ -341,7 +344,7 @@ async fn invalid_semantic_ratio() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": -0.8}}),
+            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"embedder": "default", "semanticRatio": -0.8}}),
         )
         .await;
     snapshot!(code, @"400 Bad Request");
@@ -357,7 +360,7 @@ async fn invalid_semantic_ratio() {
     let (response, code) = index
         .search_get(
             &yaup::to_string(
-                &json!({"q": "Captain", "vector": [1.0, 1.0], "hybridSemanticRatio": 1.2}),
+                &json!({"q": "Captain", "vector": [1.0, 1.0], "hybridEmbedder": "default", "hybridSemanticRatio": 1.2}),
             )
             .unwrap(),
         )
@@ -375,7 +378,7 @@ async fn invalid_semantic_ratio() {
     let (response, code) = index
         .search_get(
             &yaup::to_string(
-                &json!({"q": "Captain", "vector": [1.0, 1.0], "hybridSemanticRatio": -0.2}),
+                &json!({"q": "Captain", "vector": [1.0, 1.0], "hybridEmbedder": "default", "hybridSemanticRatio": -0.2}),
             )
             .unwrap(),
         )
@@ -398,7 +401,7 @@ async fn single_document() {
 
     let (response, code) = index
     .search_post(
-        json!({"vector": [1.0, 3.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}),
+        json!({"vector": [1.0, 3.0], "hybrid": {"semanticRatio": 1.0, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
     )
     .await;
 
@@ -414,7 +417,7 @@ async fn query_combination() {
 
     // search without query and vector, but with hybrid => still placeholder
     let (response, code) = index
-        .search_post(json!({"hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
+        .search_post(json!({"hybrid": {"embedder": "default", "semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
         .await;
 
     snapshot!(code, @"200 OK");
@@ -423,7 +426,7 @@ async fn query_combination() {
 
     // same with a different semantic ratio
     let (response, code) = index
-        .search_post(json!({"hybrid": {"semanticRatio": 0.76}, "showRankingScore": true, "retrieveVectors": true}))
+        .search_post(json!({"hybrid": {"embedder": "default", "semanticRatio": 0.76}, "showRankingScore": true, "retrieveVectors": true}))
         .await;
 
     snapshot!(code, @"200 OK");
@@ -432,7 +435,7 @@ async fn query_combination() {
 
     // wrong vector dimensions
     let (response, code) = index
-    .search_post(json!({"vector": [1.0, 0.0, 1.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
+    .search_post(json!({"vector": [1.0, 0.0, 1.0], "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
     .await;
 
     snapshot!(code, @"400 Bad Request");
@@ -447,7 +450,7 @@ async fn query_combination() {
 
     // full vector
     let (response, code) = index
-    .search_post(json!({"vector": [1.0, 0.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
+    .search_post(json!({"vector": [1.0, 0.0], "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
     .await;
 
     snapshot!(code, @"200 OK");
@@ -456,7 +459,7 @@ async fn query_combination() {
 
     // full keyword, without a query
     let (response, code) = index
-    .search_post(json!({"vector": [1.0, 0.0], "hybrid": {"semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
+    .search_post(json!({"vector": [1.0, 0.0], "hybrid": {"embedder": "default", "semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
     .await;
 
     snapshot!(code, @"200 OK");
@@ -465,7 +468,7 @@ async fn query_combination() {
 
     // query + vector, full keyword => keyword
     let (response, code) = index
-    .search_post(json!({"q": "Captain", "vector": [1.0, 0.0], "hybrid": {"semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
+    .search_post(json!({"q": "Captain", "vector": [1.0, 0.0], "hybrid": {"embedder": "default", "semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
     .await;
 
     snapshot!(code, @"200 OK");
@@ -480,7 +483,7 @@ async fn query_combination() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(response, @r###"
     {
-      "message": "Invalid request: missing `hybrid` parameter when both `q` and `vector` are present.",
+      "message": "Invalid request: missing `hybrid` parameter when `vector` is present.",
       "code": "missing_search_hybrid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#missing_search_hybrid"
@@ -490,7 +493,7 @@ async fn query_combination() {
     // full vector, without a vector => error
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}),
+            json!({"q": "Captain", "hybrid": {"semanticRatio": 1.0, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
         )
         .await;
 
@@ -507,7 +510,7 @@ async fn query_combination() {
     // hybrid without a vector => full keyword
     let (response, code) = index
         .search_post(
-            json!({"q": "Planet", "hybrid": {"semanticRatio": 0.99}, "showRankingScore": true, "retrieveVectors": true}),
+            json!({"q": "Planet", "hybrid": {"semanticRatio": 0.99, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
         )
         .await;
 
@@ -523,7 +526,58 @@ async fn retrieve_vectors() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2}, "retrieveVectors": true}),
+            json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "retrieveVectors": true}),
+        )
+        .await;
+    snapshot!(code, @"200 OK");
+    insta::assert_json_snapshot!(response["hits"], {"[]._vectors.default.embeddings" => "[vectors]"},  @r###"
+    [
+      {
+        "title": "Captain Planet",
+        "desc": "He's not part of the Marvel Cinematic Universe",
+        "id": "2",
+        "_vectors": {
+          "default": {
+            "embeddings": "[vectors]",
+            "regenerate": true
+          }
+        }
+      },
+      {
+        "title": "Captain Marvel",
+        "desc": "a Shazam ersatz",
+        "id": "3",
+        "_vectors": {
+          "default": {
+            "embeddings": "[vectors]",
+            "regenerate": true
+          }
+        }
+      },
+      {
+        "title": "Shazam!",
+        "desc": "a Captain Marvel ersatz",
+        "id": "1",
+        "_vectors": {
+          "default": {
+            "embeddings": "[vectors]",
+            "regenerate": true
+          }
+        }
+      }
+    ]
+    "###);
+
+    // use explicit `_vectors` in displayed attributes
+    let (response, code) = index
+        .update_settings(json!({ "displayedAttributes": ["id", "title", "desc", "_vectors"]} ))
+        .await;
+    assert_eq!(202, code, "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    let (response, code) = index
+        .search_post(
+            json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "retrieveVectors": true}),
         )
         .await;
     snapshot!(code, @"200 OK");
@@ -573,7 +627,7 @@ async fn retrieve_vectors() {
 
     let (response, code) = index
         .search_post(
-            json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2}, "retrieveVectors": true}),
+            json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "retrieveVectors": true}),
         )
         .await;
     snapshot!(code, @"200 OK");

meilisearch/tests/search/locales.rs

@@ -103,41 +103,12 @@ async fn simple_search() {
 
     // english
     index
-        .search(json!({"q": "Atta", "attributesToHighlight": ["*"]}), |response, code| {
+        .search(json!({"q": "Atta", "attributesToRetrieve": ["id"]}), |response, code| {
             snapshot!(response, @r###"
             {
               "hits": [
                 {
-                  "name_en": "Attack on Titan",
-                  "name_ja": "進撃の巨人",
-                  "author_en": "Hajime Isayama",
-                  "author_ja": "諫山 創",
-                  "description_en": "Attack on Titan is a Japanese manga series written and illustrated by Hajime Isayama",
-                  "description_ja": "進撃の巨人は、日本の漫画シリーズであり、諫山 創によって作画されている。",
-                  "id": 852,
-                  "_vectors": {
-                    "manual": [
-                      1.0,
-                      2.0,
-                      3.0
-                    ]
-                  },
-                  "_formatted": {
-                    "name_en": "<em>Atta</em>ck on Titan",
-                    "name_ja": "進撃の巨人",
-                    "author_en": "Hajime Isayama",
-                    "author_ja": "諫山 創",
-                    "description_en": "<em>Atta</em>ck on Titan is a Japanese manga series written and illustrated by Hajime Isayama",
-                    "description_ja": "進撃の巨人は、日本の漫画シリーズであり、諫山 創によって作画されている。",
-                    "id": "852",
-                    "_vectors": {
-                      "manual": [
-                        "1.0",
-                        "2.0",
-                        "3.0"
-                      ]
-                    }
-                  }
+                  "id": 852
                 }
               ],
               "query": "Atta",
@@ -153,35 +124,12 @@ async fn simple_search() {
 
     // japanese
     index
-        .search(json!({"q": "進撃", "attributesToHighlight": ["*"]}), |response, code| {
+        .search(json!({"q": "進撃", "attributesToRetrieve": ["id"]}), |response, code| {
             snapshot!(response, @r###"
             {
               "hits": [
                 {
-                  "name_zh": "进击的巨人",
-                  "author_zh": "諫山創",
-                  "description_zh": "进击的巨人是日本的漫画系列，由諫山 創作画。",
-                  "id": 853,
-                  "_vectors": {
-                    "manual": [
-                      1.0,
-                      2.0,
-                      3.0
-                    ]
-                  },
-                  "_formatted": {
-                    "name_zh": "<em>进击</em>的巨人",
-                    "author_zh": "諫山創",
-                    "description_zh": "<em>进击</em>的巨人是日本的漫画系列，由諫山 創作画。",
-                    "id": "853",
-                    "_vectors": {
-                      "manual": [
-                        "1.0",
-                        "2.0",
-                        "3.0"
-                      ]
-                    }
-                  }
+                  "id": 853
                 }
               ],
               "query": "進撃",
@@ -197,68 +145,16 @@ async fn simple_search() {
 
     index
         .search(
-            json!({"q": "進撃", "locales": ["jpn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "進撃", "locales": ["jpn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
                   "hits": [
                     {
-                      "name_en": "Attack on Titan",
-                      "name_ja": "進撃の巨人",
-                      "author_en": "Hajime Isayama",
-                      "author_ja": "諫山 創",
-                      "description_en": "Attack on Titan is a Japanese manga series written and illustrated by Hajime Isayama",
-                      "description_ja": "進撃の巨人は、日本の漫画シリーズであり、諫山 創によって作画されている。",
-                      "id": 852,
-                      "_vectors": {
-                        "manual": [
-                          1.0,
-                          2.0,
-                          3.0
-                        ]
-                      },
-                      "_formatted": {
-                        "name_en": "Attack on Titan",
-                        "name_ja": "<em>進撃</em>の巨人",
-                        "author_en": "Hajime Isayama",
-                        "author_ja": "諫山 創",
-                        "description_en": "Attack on Titan is a Japanese manga series written and illustrated by Hajime Isayama",
-                        "description_ja": "<em>進撃</em>の巨人は、日本の漫画シリーズであり、諫山 創によって作画されている。",
-                        "id": "852",
-                        "_vectors": {
-                          "manual": [
-                            "1.0",
-                            "2.0",
-                            "3.0"
-                          ]
-                        }
-                      }
+                      "id": 852
                     },
                     {
-                      "name_zh": "进击的巨人",
-                      "author_zh": "諫山創",
-                      "description_zh": "进击的巨人是日本的漫画系列，由諫山 創作画。",
-                      "id": 853,
-                      "_vectors": {
-                        "manual": [
-                          1.0,
-                          2.0,
-                          3.0
-                        ]
-                      },
-                      "_formatted": {
-                        "name_zh": "进击的巨人",
-                        "author_zh": "諫山創",
-                        "description_zh": "进击的巨人是日本的漫画系列，由諫山 創作画。",
-                        "id": "853",
-                        "_vectors": {
-                          "manual": [
-                            "1.0",
-                            "2.0",
-                            "3.0"
-                          ]
-                        }
-                      }
+                      "id": 853
                     }
                   ],
                   "query": "進撃",
@@ -275,67 +171,15 @@ async fn simple_search() {
 
     // chinese
     index
-        .search(json!({"q": "进击", "attributesToHighlight": ["*"]}), |response, code| {
+        .search(json!({"q": "进击", "attributesToRetrieve": ["id"]}), |response, code| {
             snapshot!(response, @r###"
             {
               "hits": [
                 {
-                  "name_zh": "进击的巨人",
-                  "author_zh": "諫山創",
-                  "description_zh": "进击的巨人是日本的漫画系列，由諫山 創作画。",
-                  "id": 853,
-                  "_vectors": {
-                    "manual": [
-                      1.0,
-                      2.0,
-                      3.0
-                    ]
-                  },
-                  "_formatted": {
-                    "name_zh": "<em>进击</em>的巨人",
-                    "author_zh": "諫山創",
-                    "description_zh": "<em>进击</em>的巨人是日本的漫画系列，由諫山 創作画。",
-                    "id": "853",
-                    "_vectors": {
-                      "manual": [
-                        "1.0",
-                        "2.0",
-                        "3.0"
-                      ]
-                    }
-                  }
+                  "id": 853
                 },
                 {
-                  "name_en": "Attack on Titan",
-                  "name_ja": "進撃の巨人",
-                  "author_en": "Hajime Isayama",
-                  "author_ja": "諫山 創",
-                  "description_en": "Attack on Titan is a Japanese manga series written and illustrated by Hajime Isayama",
-                  "description_ja": "進撃の巨人は、日本の漫画シリーズであり、諫山 創によって作画されている。",
-                  "id": 852,
-                  "_vectors": {
-                    "manual": [
-                      1.0,
-                      2.0,
-                      3.0
-                    ]
-                  },
-                  "_formatted": {
-                    "name_en": "Attack on Titan",
-                    "name_ja": "<em>進撃</em>の巨人",
-                    "author_en": "Hajime Isayama",
-                    "author_ja": "諫山 創",
-                    "description_en": "Attack on Titan is a Japanese manga series written and illustrated by Hajime Isayama",
-                    "description_ja": "<em>進撃</em>の巨人は、日本の漫画シリーズであり、諫山 創によって作画されている。",
-                    "id": "852",
-                    "_vectors": {
-                      "manual": [
-                        "1.0",
-                        "2.0",
-                        "3.0"
-                      ]
-                    }
-                  }
+                  "id": 852
                 }
               ],
               "query": "进击",
@@ -382,16 +226,20 @@ async fn force_locales() {
     // chinese detection
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
-                  "hits": [],
+                  "hits": [
+                    {
+                      "id": 853
+                    }
+                  ],
                   "query": "\"进击的巨人\"",
                   "processingTimeMs": "[duration]",
                   "limit": 20,
                   "offset": 0,
-                  "estimatedTotalHits": 0
+                  "estimatedTotalHits": 1
                 }
                 "###);
                 snapshot!(code, @"200 OK");
@@ -402,36 +250,13 @@ async fn force_locales() {
     // force japanese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
                   "hits": [
                     {
-                      "name_zh": "进击的巨人",
-                      "author_zh": "諫山創",
-                      "description_zh": "进击的巨人是日本的漫画系列，由諫山 創作画。",
-                      "id": 853,
-                      "_vectors": {
-                        "manual": [
-                          1.0,
-                          2.0,
-                          3.0
-                        ]
-                      },
-                      "_formatted": {
-                        "name_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
-                        "author_zh": "諫山創",
-                        "description_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列，由諫山 創作画。",
-                        "id": "853",
-                        "_vectors": {
-                          "manual": [
-                            "1.0",
-                            "2.0",
-                            "3.0"
-                          ]
-                        }
-                      }
+                      "id": 853
                     }
                   ],
                   "query": "\"进击的巨人\"",
@@ -479,16 +304,20 @@ async fn force_locales_with_pattern() {
     // chinese detection
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
-                  "hits": [],
+                  "hits": [
+                    {
+                      "id": 853
+                    }
+                  ],
                   "query": "\"进击的巨人\"",
                   "processingTimeMs": "[duration]",
                   "limit": 20,
                   "offset": 0,
-                  "estimatedTotalHits": 0
+                  "estimatedTotalHits": 1
                 }
                 "###);
                 snapshot!(code, @"200 OK");
@@ -499,36 +328,13 @@ async fn force_locales_with_pattern() {
     // force japanese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
                   "hits": [
                     {
-                      "name_zh": "进击的巨人",
-                      "author_zh": "諫山創",
-                      "description_zh": "进击的巨人是日本的漫画系列，由諫山 創作画。",
-                      "id": 853,
-                      "_vectors": {
-                        "manual": [
-                          1.0,
-                          2.0,
-                          3.0
-                        ]
-                      },
-                      "_formatted": {
-                        "name_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
-                        "author_zh": "諫山創",
-                        "description_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列，由諫山 創作画。",
-                        "id": "853",
-                        "_vectors": {
-                          "manual": [
-                            "1.0",
-                            "2.0",
-                            "3.0"
-                          ]
-                        }
-                      }
+                      "id": 853
                     }
                   ],
                   "query": "\"进击的巨人\"",
@@ -574,7 +380,7 @@ async fn force_locales_with_pattern_nested() {
     // chinese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["cmn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["cmn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
@@ -594,60 +400,13 @@ async fn force_locales_with_pattern_nested() {
     // force japanese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
                   "hits": [
                     {
-                      "document_en": {
-                        "name": "Attack on Titan",
-                        "description": "Attack on Titan is a Japanese manga series written and illustrated by Hajime Isayama",
-                        "author": "Hajime Isayama"
-                      },
-                      "document_ja": {
-                        "name": "進撃の巨人",
-                        "description": "進撃の巨人は、日本の漫画シリーズであり、諫山 創によって作画されている。",
-                        "author": "諫山 創"
-                      },
-                      "document_zh": {
-                        "name": "进击的巨人",
-                        "description": "进击的巨人是日本的漫画系列，由諫山 創作画。",
-                        "author": "諫山創"
-                      },
-                      "id": 852,
-                      "_vectors": {
-                        "manual": [
-                          1.0,
-                          2.0,
-                          3.0
-                        ]
-                      },
-                      "_formatted": {
-                        "document_en": {
-                          "name": "Attack on Titan",
-                          "description": "Attack on Titan is a Japanese manga series written and illustrated by Hajime Isayama",
-                          "author": "Hajime Isayama"
-                        },
-                        "document_ja": {
-                          "name": "進撃の巨人",
-                          "description": "進撃の巨人は、日本の漫画シリーズであり、諫山 創によって作画されている。",
-                          "author": "諫山 創"
-                        },
-                        "document_zh": {
-                          "name": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
-                          "description": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列，由諫山 創作画。",
-                          "author": "諫山創"
-                        },
-                        "id": "852",
-                        "_vectors": {
-                          "manual": [
-                            "1.0",
-                            "2.0",
-                            "3.0"
-                          ]
-                        }
-                      }
+                      "id": 852
                     }
                   ],
                   "query": "\"进击的巨人\"",
@@ -696,7 +455,7 @@ async fn force_different_locales_with_pattern() {
     // force chinese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["cmn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["cmn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
@@ -716,36 +475,190 @@ async fn force_different_locales_with_pattern() {
     // force japanese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
                   "hits": [
                     {
-                      "name_zh": "进击的巨人",
-                      "author_zh": "諫山創",
-                      "description_zh": "进击的巨人是日本的漫画系列，由諫山 創作画。",
-                      "id": 853,
-                      "_vectors": {
-                        "manual": [
-                          1.0,
-                          2.0,
-                          3.0
-                        ]
-                      },
-                      "_formatted": {
-                        "name_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
-                        "author_zh": "諫山創",
-                        "description_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列，由諫山 創作画。",
-                        "id": "853",
-                        "_vectors": {
-                          "manual": [
-                            "1.0",
-                            "2.0",
-                            "3.0"
-                          ]
+                      "id": 853
+                    }
+                  ],
+                  "query": "\"进击的巨人\"",
+                  "processingTimeMs": "[duration]",
+                  "limit": 20,
+                  "offset": 0,
+                  "estimatedTotalHits": 1
+                }
+                "###);
+                snapshot!(code, @"200 OK");
+            },
+        )
+        .await;
+}
+
+#[actix_rt::test]
+async fn auto_infer_locales_at_search_with_attributes_to_search_on() {
+    let server = Server::new().await;
+
+    let index = server.index("test");
+    let documents = DOCUMENTS.clone();
+    let (response, _) = index
+        .update_settings(
+            json!({
+                "searchableAttributes": ["name_en", "name_ja", "name_zh", "author_en", "author_ja", "author_zh", "description_en", "description_ja", "description_zh"],
+                "localizedAttributes": [
+                    // force japanese
+                    {"attributePatterns": ["*_zh"], "locales": ["jpn"]},
+                    // force chinese
+                    {"attributePatterns": ["*_ja"], "locales": ["cmn"]},
+                    // any language
+                    {"attributePatterns": ["*_en"], "locales": []}
+                ]
+            }),
+        )
+        .await;
+    snapshot!(response, @r###"
+    {
+      "taskUid": 0,
+      "indexUid": "test",
+      "status": "enqueued",
+      "type": "settingsUpdate",
+      "enqueuedAt": "[date]"
+    }
+    "###);
+    index.add_documents(documents, None).await;
+    index.wait_task(1).await;
+
+    // auto infer any language
+    index
+        .search(
+            json!({"q": "\"进击的巨人\"", "attributesToRetrieve": ["id"]}),
+            |response, code| {
+                snapshot!(response, @r###"
+                {
+                  "hits": [],
+                  "query": "\"进击的巨人\"",
+                  "processingTimeMs": "[duration]",
+                  "limit": 20,
+                  "offset": 0,
+                  "estimatedTotalHits": 0
+                }
+                "###);
+                snapshot!(code, @"200 OK");
+            },
+        )
+        .await;
+
+    // should infer chinese
+    index
+            .search(
+                json!({"q": "\"进击的巨人\"", "attributesToRetrieve": ["id"], "attributesToSearchOn": ["name_zh", "description_zh"]}),
+                |response, code| {
+                    snapshot!(response, @r###"
+                    {
+                      "hits": [
+                        {
+                          "id": 853
                         }
-                      }
+                      ],
+                      "query": "\"进击的巨人\"",
+                      "processingTimeMs": "[duration]",
+                      "limit": 20,
+                      "offset": 0,
+                      "estimatedTotalHits": 1
+                    }
+                    "###);
+                    snapshot!(code, @"200 OK");
+                },
+            )
+            .await;
+}
+
+#[actix_rt::test]
+async fn auto_infer_locales_at_search() {
+    let server = Server::new().await;
+
+    let index = server.index("test");
+    let documents = DOCUMENTS.clone();
+    let (response, _) = index
+        .update_settings(
+            json!({
+                "searchableAttributes": ["name_en", "name_ja", "name_zh", "author_en", "author_ja", "author_zh", "description_en", "description_ja", "description_zh"],
+                "localizedAttributes": [
+                    // force japanese
+                    {"attributePatterns": ["*"], "locales": ["jpn"]},
+                ]
+            }),
+        )
+        .await;
+    snapshot!(response, @r###"
+    {
+      "taskUid": 0,
+      "indexUid": "test",
+      "status": "enqueued",
+      "type": "settingsUpdate",
+      "enqueuedAt": "[date]"
+    }
+    "###);
+    index.add_documents(documents, None).await;
+    index.wait_task(1).await;
+
+    index
+        .search(
+            json!({"q": "\"进击的巨人\"", "attributesToRetrieve": ["id"]}),
+            |response, code| {
+                snapshot!(response, @r###"
+                {
+                  "hits": [
+                    {
+                      "id": 853
+                    }
+                  ],
+                  "query": "\"进击的巨人\"",
+                  "processingTimeMs": "[duration]",
+                  "limit": 20,
+                  "offset": 0,
+                  "estimatedTotalHits": 1
+                }
+                "###);
+                snapshot!(code, @"200 OK");
+            },
+        )
+        .await;
+
+    index
+        .search(
+            json!({"q": "\"进击的巨人\"", "attributesToRetrieve": ["id"]}),
+            |response, code| {
+                snapshot!(response, @r###"
+                    {
+                      "hits": [
+                        {
+                          "id": 853
+                        }
+                      ],
+                      "query": "\"进击的巨人\"",
+                      "processingTimeMs": "[duration]",
+                      "limit": 20,
+                      "offset": 0,
+                      "estimatedTotalHits": 1
+                    }
+                    "###);
+                snapshot!(code, @"200 OK");
+            },
+        )
+        .await;
+
+    index
+        .search(
+            json!({"q": "\"进击的巨人\"", "attributesToRetrieve": ["id"]}),
+            |response, code| {
+                snapshot!(response, @r###"
+                {
+                  "hits": [
+                    {
+                      "id": 853
                     }
                   ],
                   "query": "\"进击的巨人\"",
@@ -793,7 +706,7 @@ async fn force_different_locales_with_pattern_nested() {
     // chinese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["cmn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["cmn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
@@ -813,60 +726,37 @@ async fn force_different_locales_with_pattern_nested() {
     // force japanese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToRetrieve": ["id"]}),
+            |response, code| {
+                snapshot!(response, @r###"
+                    {
+                      "hits": [
+                        {
+                          "id": 852
+                        }
+                      ],
+                      "query": "\"进击的巨人\"",
+                      "processingTimeMs": "[duration]",
+                      "limit": 20,
+                      "offset": 0,
+                      "estimatedTotalHits": 1
+                    }
+                    "###);
+                snapshot!(code, @"200 OK");
+            },
+        )
+        .await;
+
+    // force japanese
+    index
+        .search(
+            json!({"q": "\"进击的巨人\"", "locales": ["ja"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
                   "hits": [
                     {
-                      "document_en": {
-                        "name": "Attack on Titan",
-                        "description": "Attack on Titan is a Japanese manga series written and illustrated by Hajime Isayama",
-                        "author": "Hajime Isayama"
-                      },
-                      "document_ja": {
-                        "name": "進撃の巨人",
-                        "description": "進撃の巨人は、日本の漫画シリーズであり、諫山 創によって作画されている。",
-                        "author": "諫山 創"
-                      },
-                      "document_zh": {
-                        "name": "进击的巨人",
-                        "description": "进击的巨人是日本的漫画系列，由諫山 創作画。",
-                        "author": "諫山創"
-                      },
-                      "id": 852,
-                      "_vectors": {
-                        "manual": [
-                          1.0,
-                          2.0,
-                          3.0
-                        ]
-                      },
-                      "_formatted": {
-                        "document_en": {
-                          "name": "Attack on Titan",
-                          "description": "Attack on Titan is a Japanese manga series written and illustrated by Hajime Isayama",
-                          "author": "Hajime Isayama"
-                        },
-                        "document_ja": {
-                          "name": "進撃の巨人",
-                          "description": "進撃の巨人は、日本の漫画シリーズであり、諫山 創によって作画されている。",
-                          "author": "諫山 創"
-                        },
-                        "document_zh": {
-                          "name": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
-                          "description": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列，由諫山 創作画。",
-                          "author": "諫山創"
-                        },
-                        "id": "852",
-                        "_vectors": {
-                          "manual": [
-                            "1.0",
-                            "2.0",
-                            "3.0"
-                          ]
-                        }
-                      }
+                      "id": 852
                     }
                   ],
                   "query": "\"进击的巨人\"",
@@ -913,7 +803,7 @@ async fn settings_change() {
     // chinese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["cmn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["cmn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
@@ -933,7 +823,7 @@ async fn settings_change() {
     // force japanese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
@@ -976,7 +866,7 @@ async fn settings_change() {
     // chinese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["cmn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["cmn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
@@ -996,7 +886,7 @@ async fn settings_change() {
     // force japanese
     index
         .search(
-            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToHighlight": ["*"]}),
+            json!({"q": "\"进击的巨人\"", "locales": ["jpn"], "attributesToRetrieve": ["id"]}),
             |response, code| {
                 snapshot!(response, @r###"
                 {
@@ -1032,7 +922,7 @@ async fn invalid_locales() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Unknown value `invalid` at `.locales[0]`: expected one of `epo`, `eng`, `rus`, `cmn`, `spa`, `por`, `ita`, `ben`, `fra`, `deu`, `ukr`, `kat`, `ara`, `hin`, `jpn`, `heb`, `yid`, `pol`, `amh`, `jav`, `kor`, `nob`, `dan`, `swe`, `fin`, `tur`, `nld`, `hun`, `ces`, `ell`, `bul`, `bel`, `mar`, `kan`, `ron`, `slv`, `hrv`, `srp`, `mkd`, `lit`, `lav`, `est`, `tam`, `vie`, `urd`, `tha`, `guj`, `uzb`, `pan`, `aze`, `ind`, `tel`, `pes`, `mal`, `ori`, `mya`, `nep`, `sin`, `khm`, `tuk`, `aka`, `zul`, `sna`, `afr`, `lat`, `slk`, `cat`, `tgl`, `hye`",
+      "message": "Unknown value `invalid` at `.locales[0]`: expected one of `af`, `ak`, `am`, `ar`, `az`, `be`, `bn`, `bg`, `ca`, `cs`, `da`, `de`, `el`, `en`, `eo`, `et`, `fi`, `fr`, `gu`, `he`, `hi`, `hr`, `hu`, `hy`, `id`, `it`, `jv`, `ja`, `kn`, `ka`, `km`, `ko`, `la`, `lv`, `lt`, `ml`, `mr`, `mk`, `my`, `ne`, `nl`, `nb`, `or`, `pa`, `fa`, `pl`, `pt`, `ro`, `ru`, `si`, `sk`, `sl`, `sn`, `es`, `sr`, `sv`, `ta`, `te`, `tl`, `th`, `tk`, `tr`, `uk`, `ur`, `uz`, `vi`, `yi`, `zh`, `zu`, `afr`, `aka`, `amh`, `ara`, `aze`, `bel`, `ben`, `bul`, `cat`, `ces`, `dan`, `deu`, `ell`, `eng`, `epo`, `est`, `fin`, `fra`, `guj`, `heb`, `hin`, `hrv`, `hun`, `hye`, `ind`, `ita`, `jav`, `jpn`, `kan`, `kat`, `khm`, `kor`, `lat`, `lav`, `lit`, `mal`, `mar`, `mkd`, `mya`, `nep`, `nld`, `nob`, `ori`, `pan`, `pes`, `pol`, `por`, `ron`, `rus`, `sin`, `slk`, `slv`, `sna`, `spa`, `srp`, `swe`, `tam`, `tel`, `tgl`, `tha`, `tuk`, `tur`, `ukr`, `urd`, `uzb`, `vie`, `yid`, `zho`, `zul`, `cmn`",
       "code": "invalid_search_locales",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_locales"
@@ -1045,7 +935,7 @@ async fn invalid_locales() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value in parameter `locales`: Unsupported locale `invalid`, expected one of `epo`, `eng`, `rus`, `cmn`, `spa`, `por`, `ita`, `ben`, `fra`, `deu`, `ukr`, `kat`, `ara`, `hin`, `jpn`, `heb`, `yid`, `pol`, `amh`, `jav`, `kor`, `nob`, `dan`, `swe`, `fin`, `tur`, `nld`, `hun`, `ces`, `ell`, `bul`, `bel`, `mar`, `kan`, `ron`, `slv`, `hrv`, `srp`, `mkd`, `lit`, `lav`, `est`, `tam`, `vie`, `urd`, `tha`, `guj`, `uzb`, `pan`, `aze`, `ind`, `tel`, `pes`, `mal`, `ori`, `mya`, `nep`, `sin`, `khm`, `tuk`, `aka`, `zul`, `sna`, `afr`, `lat`, `slk`, `cat`, `tgl`, `hye`",
+      "message": "Invalid value in parameter `locales`: Unsupported locale `invalid`, expected one of af, ak, am, ar, az, be, bg, bn, ca, cs, da, de, el, en, eo, es, et, fa, fi, fr, gu, he, hi, hr, hu, hy, id, it, ja, jv, ka, km, kn, ko, la, lt, lv, mk, ml, mr, my, nb, ne, nl, or, pa, pl, pt, ro, ru, si, sk, sl, sn, sr, sv, ta, te, th, tk, tl, tr, uk, ur, uz, vi, yi, zh, zu, afr, aka, amh, ara, aze, bel, ben, bul, cat, ces, cmn, dan, deu, ell, eng, epo, est, fin, fra, guj, heb, hin, hrv, hun, hye, ind, ita, jav, jpn, kan, kat, khm, kor, lat, lav, lit, mal, mar, mkd, mya, nep, nld, nob, ori, pan, pes, pol, por, ron, rus, sin, slk, slv, sna, spa, srp, swe, tam, tel, tgl, tha, tuk, tur, ukr, urd, uzb, vie, yid, zho, zul",
       "code": "invalid_search_locales",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_locales"
@@ -1067,7 +957,7 @@ async fn invalid_localized_attributes_rules() {
         .await;
     snapshot!(response, @r###"
     {
-      "message": "Unknown value `japan` at `.localizedAttributes[0].locales[0]`: expected one of `epo`, `eng`, `rus`, `cmn`, `spa`, `por`, `ita`, `ben`, `fra`, `deu`, `ukr`, `kat`, `ara`, `hin`, `jpn`, `heb`, `yid`, `pol`, `amh`, `jav`, `kor`, `nob`, `dan`, `swe`, `fin`, `tur`, `nld`, `hun`, `ces`, `ell`, `bul`, `bel`, `mar`, `kan`, `ron`, `slv`, `hrv`, `srp`, `mkd`, `lit`, `lav`, `est`, `tam`, `vie`, `urd`, `tha`, `guj`, `uzb`, `pan`, `aze`, `ind`, `tel`, `pes`, `mal`, `ori`, `mya`, `nep`, `sin`, `khm`, `tuk`, `aka`, `zul`, `sna`, `afr`, `lat`, `slk`, `cat`, `tgl`, `hye`",
+      "message": "Unknown value `japan` at `.localizedAttributes[0].locales[0]`: expected one of `af`, `ak`, `am`, `ar`, `az`, `be`, `bn`, `bg`, `ca`, `cs`, `da`, `de`, `el`, `en`, `eo`, `et`, `fi`, `fr`, `gu`, `he`, `hi`, `hr`, `hu`, `hy`, `id`, `it`, `jv`, `ja`, `kn`, `ka`, `km`, `ko`, `la`, `lv`, `lt`, `ml`, `mr`, `mk`, `my`, `ne`, `nl`, `nb`, `or`, `pa`, `fa`, `pl`, `pt`, `ro`, `ru`, `si`, `sk`, `sl`, `sn`, `es`, `sr`, `sv`, `ta`, `te`, `tl`, `th`, `tk`, `tr`, `uk`, `ur`, `uz`, `vi`, `yi`, `zh`, `zu`, `afr`, `aka`, `amh`, `ara`, `aze`, `bel`, `ben`, `bul`, `cat`, `ces`, `dan`, `deu`, `ell`, `eng`, `epo`, `est`, `fin`, `fra`, `guj`, `heb`, `hin`, `hrv`, `hun`, `hye`, `ind`, `ita`, `jav`, `jpn`, `kan`, `kat`, `khm`, `kor`, `lat`, `lav`, `lit`, `mal`, `mar`, `mkd`, `mya`, `nep`, `nld`, `nob`, `ori`, `pan`, `pes`, `pol`, `por`, `ron`, `rus`, `sin`, `slk`, `slv`, `sna`, `spa`, `srp`, `swe`, `tam`, `tel`, `tgl`, `tha`, `tuk`, `tur`, `ukr`, `urd`, `uzb`, `vie`, `yid`, `zho`, `zul`, `cmn`",
       "code": "invalid_settings_localized_attributes",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_settings_localized_attributes"
@@ -1253,3 +1143,195 @@ async fn facet_search_with_localized_attributes() {
     }
     "###);
 }
+
+#[actix_rt::test]
+async fn swedish_search() {
+    let server = Server::new().await;
+
+    let index = server.index("test");
+    let documents = json!([
+      {"id": "tra1-1", "product": "trä"},
+      {"id": "tra2-1", "product": "traktor"},
+      {"id": "tra1-2", "product": "träbjälke"},
+      {"id": "tra2-2", "product": "trafiksignal"},
+    ]);
+    index.add_documents(documents, None).await;
+    let (_response, _) = index
+        .update_settings(json!({
+            "searchableAttributes": ["product"],
+            "localizedAttributes": [
+                // force swedish
+                {"attributePatterns": ["product"], "locales": ["swe"]}
+            ]
+        }))
+        .await;
+    index.wait_task(1).await;
+
+    // infer swedish
+    index
+        .search(json!({"q": "trä", "attributesToRetrieve": ["product"]}), |response, code| {
+            snapshot!(response, @r###"
+            {
+              "hits": [
+                {
+                  "product": "trä"
+                },
+                {
+                  "product": "träbjälke"
+                }
+              ],
+              "query": "trä",
+              "processingTimeMs": "[duration]",
+              "limit": 20,
+              "offset": 0,
+              "estimatedTotalHits": 2
+            }
+            "###);
+            snapshot!(code, @"200 OK");
+        })
+        .await;
+
+    index
+        .search(json!({"q": "tra", "attributesToRetrieve": ["product"]}), |response, code| {
+            snapshot!(response, @r###"
+            {
+              "hits": [
+                {
+                  "product": "traktor"
+                },
+                {
+                  "product": "trafiksignal"
+                }
+              ],
+              "query": "tra",
+              "processingTimeMs": "[duration]",
+              "limit": 20,
+              "offset": 0,
+              "estimatedTotalHits": 2
+            }
+            "###);
+            snapshot!(code, @"200 OK");
+        })
+        .await;
+
+    // force swedish
+    index
+        .search(
+            json!({"q": "trä", "locales": ["swe"], "attributesToRetrieve": ["product"]}),
+            |response, code| {
+                snapshot!(response, @r###"
+                {
+                  "hits": [
+                    {
+                      "product": "trä"
+                    },
+                    {
+                      "product": "träbjälke"
+                    }
+                  ],
+                  "query": "trä",
+                  "processingTimeMs": "[duration]",
+                  "limit": 20,
+                  "offset": 0,
+                  "estimatedTotalHits": 2
+                }
+                "###);
+                snapshot!(code, @"200 OK");
+            },
+        )
+        .await;
+    index
+        .search(
+            json!({"q": "tra", "locales": ["swe"], "attributesToRetrieve": ["product"]}),
+            |response, code| {
+                snapshot!(response, @r###"
+                {
+                  "hits": [
+                    {
+                      "product": "traktor"
+                    },
+                    {
+                      "product": "trafiksignal"
+                    }
+                  ],
+                  "query": "tra",
+                  "processingTimeMs": "[duration]",
+                  "limit": 20,
+                  "offset": 0,
+                  "estimatedTotalHits": 2
+                }
+                "###);
+                snapshot!(code, @"200 OK");
+            },
+        )
+        .await;
+}
+
+#[actix_rt::test]
+async fn german_search() {
+    let server = Server::new().await;
+
+    let index = server.index("test");
+    let documents = json!([
+      {"id": 1, "product": "Interkulturalität"},
+      {"id": 2, "product": "Wissensorganisation"},
+    ]);
+    index.add_documents(documents, None).await;
+    let (_response, _) = index
+        .update_settings(json!({
+            "searchableAttributes": ["product"],
+            "localizedAttributes": [
+                // force swedish
+                {"attributePatterns": ["product"], "locales": ["deu"]}
+            ]
+        }))
+        .await;
+    index.wait_task(1).await;
+
+    // infer swedish
+    index
+        .search(
+            json!({"q": "kulturalität", "attributesToRetrieve": ["product"]}),
+            |response, code| {
+                snapshot!(response, @r###"
+            {
+              "hits": [
+                {
+                  "product": "Interkulturalität"
+                }
+              ],
+              "query": "kulturalität",
+              "processingTimeMs": "[duration]",
+              "limit": 20,
+              "offset": 0,
+              "estimatedTotalHits": 1
+            }
+            "###);
+                snapshot!(code, @"200 OK");
+            },
+        )
+        .await;
+
+    index
+        .search(
+            json!({"q": "organisation", "attributesToRetrieve": ["product"]}),
+            |response, code| {
+                snapshot!(response, @r###"
+            {
+              "hits": [
+                {
+                  "product": "Wissensorganisation"
+                }
+              ],
+              "query": "organisation",
+              "processingTimeMs": "[duration]",
+              "limit": 20,
+              "offset": 0,
+              "estimatedTotalHits": 1
+            }
+            "###);
+                snapshot!(code, @"200 OK");
+            },
+        )
+        .await;
+}

meilisearch/tests/search/mod.rs

@@ -7,6 +7,7 @@ mod facet_search;
 mod formatted;
 mod geo;
 mod hybrid;
+#[cfg(not(feature = "chinese-pinyin"))]
 mod locales;
 mod matching_strategy;
 mod multi;
@@ -15,208 +16,17 @@ mod restrict_searchable;
 mod search_queue;
 
 use meilisearch::Opt;
-use once_cell::sync::Lazy;
 use tempfile::TempDir;
 
-use crate::common::{default_settings, Server, Value};
+use crate::common::{
+    default_settings, shared_index_with_documents, shared_index_with_nested_documents, Server,
+    DOCUMENTS, FRUITS_DOCUMENTS, NESTED_DOCUMENTS, SCORE_DOCUMENTS, VECTOR_DOCUMENTS,
+};
 use crate::json;
 
-static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "title": "Shazam!",
-            "id": "287947",
-            "_vectors": { "manual": [1, 2, 3]},
-        },
-        {
-            "title": "Captain Marvel",
-            "id": "299537",
-            "_vectors": { "manual": [1, 2, 54] },
-        },
-        {
-            "title": "Escape Room",
-            "id": "522681",
-            "_vectors": { "manual": [10, -23, 32] },
-        },
-        {
-            "title": "How to Train Your Dragon: The Hidden World",
-            "id": "166428",
-            "_vectors": { "manual": [-100, 231, 32] },
-        },
-        {
-            "title": "Gläss",
-            "id": "450465",
-            "_vectors": { "manual": [-100, 340, 90] },
-        }
-    ])
-});
-
-static SCORE_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "title": "Batman the dark knight returns: Part 1",
-            "id": "A",
-        },
-        {
-            "title": "Batman the dark knight returns: Part 2",
-            "id": "B",
-        },
-        {
-            "title": "Batman Returns",
-            "id": "C",
-        },
-        {
-            "title": "Batman",
-            "id": "D",
-        },
-        {
-            "title": "Badman",
-            "id": "E",
-        }
-    ])
-});
-
-static NESTED_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "id": 852,
-            "father": "jean",
-            "mother": "michelle",
-            "doggos": [
-                {
-                    "name": "bobby",
-                    "age": 2,
-                },
-                {
-                    "name": "buddy",
-                    "age": 4,
-                },
-            ],
-            "cattos": "pésti",
-            "_vectors": { "manual": [1, 2, 3]},
-        },
-        {
-            "id": 654,
-            "father": "pierre",
-            "mother": "sabine",
-            "doggos": [
-                {
-                    "name": "gros bill",
-                    "age": 8,
-                },
-            ],
-            "cattos": ["simba", "pestiféré"],
-            "_vectors": { "manual": [1, 2, 54] },
-        },
-        {
-            "id": 750,
-            "father": "romain",
-            "mother": "michelle",
-            "cattos": ["enigma"],
-            "_vectors": { "manual": [10, 23, 32] },
-        },
-        {
-            "id": 951,
-            "father": "jean-baptiste",
-            "mother": "sophie",
-            "doggos": [
-                {
-                    "name": "turbo",
-                    "age": 5,
-                },
-                {
-                    "name": "fast",
-                    "age": 6,
-                },
-            ],
-            "cattos": ["moumoute", "gomez"],
-            "_vectors": { "manual": [10, 23, 32] },
-        },
-    ])
-});
-
-static FRUITS_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "name": "Exclusive sale: green apple",
-            "id": "green-apple-boosted",
-            "BOOST": true
-        },
-        {
-            "name": "Pear",
-            "id": "pear",
-        },
-        {
-            "name": "Red apple gala",
-            "id": "red-apple-gala",
-        },
-        {
-            "name": "Exclusive sale: Red Tomato",
-            "id": "red-tomatoes-boosted",
-            "BOOST": true
-        },
-        {
-            "name": "Exclusive sale: Red delicious apple",
-            "id": "red-delicious-boosted",
-            "BOOST": true,
-        }
-    ])
-});
-
-static VECTOR_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-      {
-        "id": "A",
-        "description": "the dog barks at the cat",
-        "_vectors": {
-          // dimensions [canine, feline, young]
-          "animal": [0.9, 0.8, 0.05],
-          // dimensions [negative/positive, energy]
-          "sentiment": [-0.1, 0.55]
-        }
-      },
-      {
-        "id": "B",
-        "description": "the kitten scratched the beagle",
-        "_vectors": {
-          // dimensions [canine, feline, young]
-          "animal": [0.8, 0.9, 0.5],
-          // dimensions [negative/positive, energy]
-          "sentiment": [-0.2, 0.65]
-        }
-      },
-      {
-        "id": "C",
-        "description": "the dog had to stay alone today",
-        "_vectors": {
-          // dimensions [canine, feline, young]
-          "animal": [0.85, 0.02, 0.1],
-          // dimensions [negative/positive, energy]
-          "sentiment": [-1.0, 0.1]
-        }
-      },
-      {
-        "id": "D",
-        "description": "the little boy pets the puppy",
-        "_vectors": {
-          // dimensions [canine, feline, young]
-          "animal": [0.8, 0.09, 0.8],
-          // dimensions [negative/positive, energy]
-          "sentiment": [0.8, 0.3]
-        }
-      },
-    ])
-});
-
 #[actix_rt::test]
 async fn simple_placeholder_search() {
-    let server = Server::new().await;
-    let index = server.index("basic");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(json!({}), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -224,11 +34,7 @@ async fn simple_placeholder_search() {
         })
         .await;
 
-    let index = server.index("nested");
-    let documents = NESTED_DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
+    let index = shared_index_with_nested_documents().await;
     index
         .search(json!({}), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -239,13 +45,7 @@ async fn simple_placeholder_search() {
 
 #[actix_rt::test]
 async fn simple_search() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(json!({"q": "glass"}), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -253,11 +53,7 @@ async fn simple_search() {
         })
         .await;
 
-    let index = server.index("nested");
-    let documents = NESTED_DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
+    let index = shared_index_with_nested_documents().await;
     index
         .search(json!({"q": "pésti"}), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -289,13 +85,7 @@ async fn phrase_search_with_stop_word() {
 
 #[actix_rt::test]
 async fn negative_phrase_search() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(json!({"q": "-\"train your dragon\"" }), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -311,13 +101,7 @@ async fn negative_phrase_search() {
 
 #[actix_rt::test]
 async fn negative_word_search() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(json!({"q": "-escape" }), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -342,13 +126,7 @@ async fn negative_word_search() {
 
 #[actix_rt::test]
 async fn non_negative_search() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(json!({"q": "- escape" }), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -392,6 +170,7 @@ async fn negative_special_cases_search() {
 }
 
 #[cfg(feature = "default")]
+#[cfg(not(feature = "chinese-pinyin"))]
 #[actix_rt::test]
 async fn test_kanji_language_detection() {
     let server = Server::new().await;
@@ -440,13 +219,7 @@ async fn test_thai_language() {
 
 #[actix_rt::test]
 async fn search_multiple_params() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(
             json!({
@@ -463,11 +236,7 @@ async fn search_multiple_params() {
         )
         .await;
 
-    let index = server.index("nested");
-    let documents = NESTED_DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
+    let index = shared_index_with_nested_documents().await;
     index
         .search(
             json!({
@@ -553,15 +322,7 @@ async fn search_with_filter_string_notation() {
 
 #[actix_rt::test]
 async fn search_with_filter_array_notation() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
+    let index = shared_index_with_documents().await;
     let (response, code) = index
         .search_post(json!({
             "filter": ["title = Gläss"]
@@ -607,15 +368,7 @@ async fn search_with_contains_filter() {
 
 #[actix_rt::test]
 async fn search_with_sort_on_numbers() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    index.update_settings(json!({"sortableAttributes": ["id"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(
             json!({
@@ -628,14 +381,7 @@ async fn search_with_sort_on_numbers() {
         )
         .await;
 
-    let index = server.index("nested");
-
-    index.update_settings(json!({"sortableAttributes": ["doggos.age"]})).await;
-
-    let documents = NESTED_DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(3).await;
-
+    let index = shared_index_with_nested_documents().await;
     index
         .search(
             json!({
@@ -651,15 +397,7 @@ async fn search_with_sort_on_numbers() {
 
 #[actix_rt::test]
 async fn search_with_sort_on_strings() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    index.update_settings(json!({"sortableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(
             json!({
@@ -672,14 +410,7 @@ async fn search_with_sort_on_strings() {
         )
         .await;
 
-    let index = server.index("nested");
-
-    index.update_settings(json!({"sortableAttributes": ["doggos.name"]})).await;
-
-    let documents = NESTED_DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(3).await;
-
+    let index = shared_index_with_nested_documents().await;
     index
         .search(
             json!({
@@ -695,15 +426,7 @@ async fn search_with_sort_on_strings() {
 
 #[actix_rt::test]
 async fn search_with_multiple_sort() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    index.update_settings(json!({"sortableAttributes": ["id", "title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
+    let index = shared_index_with_documents().await;
     let (response, code) = index
         .search_post(json!({
             "sort": ["id:asc", "title:desc"]
@@ -715,15 +438,7 @@ async fn search_with_multiple_sort() {
 
 #[actix_rt::test]
 async fn search_facet_distribution() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(
             json!({
@@ -738,13 +453,7 @@ async fn search_facet_distribution() {
         )
         .await;
 
-    let index = server.index("nested");
-
-    index.update_settings(json!({"filterableAttributes": ["father", "doggos.name"]})).await;
-
-    let documents = NESTED_DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(3).await;
+    let index = shared_index_with_nested_documents().await;
 
     // TODO: TAMO: fix the test
     index
@@ -771,9 +480,6 @@ async fn search_facet_distribution() {
         )
         .await;
 
-    index.update_settings(json!({"filterableAttributes": ["doggos"]})).await;
-    index.wait_task(4).await;
-
     index
         .search(
             json!({
@@ -809,9 +515,6 @@ async fn search_facet_distribution() {
         )
         .await;
 
-    index.update_settings(json!({"filterableAttributes": ["doggos.name"]})).await;
-    index.wait_task(5).await;
-
     index
         .search(
             json!({
@@ -1041,6 +744,10 @@ async fn test_score_details() {
                   {
                     "title": "How to Train Your Dragon: The Hidden World",
                     "id": "166428",
+                    "color": [
+                      "green",
+                      "red"
+                    ],
                     "_vectors": {
                       "manual": [
                         -100.0,
@@ -1392,22 +1099,28 @@ async fn experimental_feature_vector_store() {
     index.add_documents(json!(documents), None).await;
     index.wait_task(0).await;
 
-    index
-        .search(json!({
+    let (response, code) = index
+        .search_post(json!({
             "vector": [1.0, 2.0, 3.0],
+            "hybrid": {
+              "embedder": "manual",
+            },
             "showRankingScore": true
-        }), |response, code|{
-            meili_snap::snapshot!(code, @"400 Bad Request");
-            meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
-            {
-              "message": "Passing `vector` as a parameter requires enabling the `vector store` experimental feature. See https://github.com/meilisearch/product/discussions/677",
-              "code": "feature_not_enabled",
-              "type": "invalid_request",
-              "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
-            }
-            "###);
-        })
+        }))
         .await;
+
+    {
+        meili_snap::snapshot!(code, @"400 Bad Request");
+        meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
+          {
+            "message": "Passing `vector` as a parameter requires enabling the `vector store` experimental feature. See https://github.com/meilisearch/product/discussions/677",
+            "code": "feature_not_enabled",
+            "type": "invalid_request",
+            "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
+          }
+          "###);
+    }
+
     index
         .search(json!({
             "retrieveVectors": true,
@@ -1455,6 +1168,9 @@ async fn experimental_feature_vector_store() {
     let (response, code) = index
         .search_post(json!({
             "vector": [1.0, 2.0, 3.0],
+            "hybrid": {
+              "embedder": "manual",
+            },
             "showRankingScore": true,
             "retrieveVectors": true,
         }))
@@ -1467,6 +1183,10 @@ async fn experimental_feature_vector_store() {
       {
         "title": "Shazam!",
         "id": "287947",
+        "color": [
+          "green",
+          "blue"
+        ],
         "_vectors": {
           "manual": {
             "embeddings": [
@@ -1484,6 +1204,10 @@ async fn experimental_feature_vector_store() {
       {
         "title": "Captain Marvel",
         "id": "299537",
+        "color": [
+          "yellow",
+          "blue"
+        ],
         "_vectors": {
           "manual": {
             "embeddings": [
@@ -1501,6 +1225,10 @@ async fn experimental_feature_vector_store() {
       {
         "title": "Gläss",
         "id": "450465",
+        "color": [
+          "blue",
+          "red"
+        ],
         "_vectors": {
           "manual": {
             "embeddings": [
@@ -1518,6 +1246,10 @@ async fn experimental_feature_vector_store() {
       {
         "title": "How to Train Your Dragon: The Hidden World",
         "id": "166428",
+        "color": [
+          "green",
+          "red"
+        ],
         "_vectors": {
           "manual": {
             "embeddings": [
@@ -1535,6 +1267,10 @@ async fn experimental_feature_vector_store() {
       {
         "title": "Escape Room",
         "id": "522681",
+        "color": [
+          "yellow",
+          "red"
+        ],
         "_vectors": {
           "manual": {
             "embeddings": [
@@ -1801,6 +1537,10 @@ async fn simple_search_with_strange_synonyms() {
               {
                 "title": "How to Train Your Dragon: The Hidden World",
                 "id": "166428",
+                "color": [
+                  "green",
+                  "red"
+                ],
                 "_vectors": {
                   "manual": [
                     -100.0,
@@ -1822,6 +1562,10 @@ async fn simple_search_with_strange_synonyms() {
               {
                 "title": "How to Train Your Dragon: The Hidden World",
                 "id": "166428",
+                "color": [
+                  "green",
+                  "red"
+                ],
                 "_vectors": {
                   "manual": [
                     -100.0,
@@ -1843,6 +1587,10 @@ async fn simple_search_with_strange_synonyms() {
               {
                 "title": "How to Train Your Dragon: The Hidden World",
                 "id": "166428",
+                "color": [
+                  "green",
+                  "red"
+                ],
                 "_vectors": {
                   "manual": [
                     -100.0,

meilisearch/tests/search/pagination.rs

@@ -1,16 +1,10 @@
+use super::shared_index_with_documents;
 use crate::common::Server;
 use crate::json;
-use crate::search::DOCUMENTS;
 
 #[actix_rt::test]
 async fn default_search_should_return_estimated_total_hit() {
-    let server = Server::new().await;
-    let index = server.index("basic");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(json!({}), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -28,13 +22,7 @@ async fn default_search_should_return_estimated_total_hit() {
 
 #[actix_rt::test]
 async fn simple_search() {
-    let server = Server::new().await;
-    let index = server.index("basic");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(json!({"page": 1}), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -53,13 +41,7 @@ async fn simple_search() {
 
 #[actix_rt::test]
 async fn page_zero_should_not_return_any_result() {
-    let server = Server::new().await;
-    let index = server.index("basic");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(json!({"page": 0}), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -73,13 +55,7 @@ async fn page_zero_should_not_return_any_result() {
 
 #[actix_rt::test]
 async fn hits_per_page_1() {
-    let server = Server::new().await;
-    let index = server.index("basic");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(json!({"hitsPerPage": 1}), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -93,13 +69,7 @@ async fn hits_per_page_1() {
 
 #[actix_rt::test]
 async fn hits_per_page_0_should_not_return_any_result() {
-    let server = Server::new().await;
-    let index = server.index("basic");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
+    let index = shared_index_with_documents().await;
     index
         .search(json!({"hitsPerPage": 0}), |response, code| {
             assert_eq!(code, 200, "{}", response);
@@ -113,8 +83,8 @@ async fn hits_per_page_0_should_not_return_any_result() {
 
 #[actix_rt::test]
 async fn ensure_placeholder_search_hit_count_valid() {
-    let server = Server::new().await;
-    let index = server.index("basic");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let documents = json!([
         {
@@ -143,15 +113,15 @@ async fn ensure_placeholder_search_hit_count_valid() {
             "distinct": 3,
         }
     ]);
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
+    let (task, _code) = index.add_documents(documents, None).await;
+    index.wait_task(task.uid()).await.succeeded();
 
-    let (_response, _code) = index
+    let (response, _code) = index
         .update_settings(
             json!({ "rankingRules": ["distinct:asc"], "distinctAttribute": "distinct"}),
         )
         .await;
-    index.wait_task(1).await;
+    index.wait_task(response.uid()).await.succeeded();
 
     for page in 0..=4 {
         index

meilisearch/tests/search/restrict_searchable.rs

@@ -8,8 +8,8 @@ use crate::json;
 async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
     let index = server.index("test");
 
-    index.add_documents(documents.clone(), None).await;
-    index.wait_task(0).await;
+    let (task, _code) = index.add_documents(documents.clone(), None).await;
+    index.wait_task(task.uid()).await.succeeded();
     index
 }
 

meilisearch/tests/search/search_queue.rs

@@ -37,6 +37,43 @@ async fn search_queue_register() {
         .unwrap();
 }
 
+#[actix_rt::test]
+async fn search_queue_register_with_explicit_drop() {
+    let queue = SearchQueue::new(4, NonZeroUsize::new(2).unwrap());
+
+    // First, use all the cores
+    let permit1 = queue.try_get_search_permit().await.unwrap();
+    let _permit2 = queue.try_get_search_permit().await.unwrap();
+
+    // If we free one spot we should be able to register one new search
+    permit1.drop().await;
+
+    let permit3 = queue.try_get_search_permit().await.unwrap();
+
+    // And again
+    permit3.drop().await;
+
+    let _permit4 = queue.try_get_search_permit().await.unwrap();
+}
+
+#[actix_rt::test]
+async fn search_queue_register_with_time_to_abort() {
+    let queue = Arc::new(
+        SearchQueue::new(1, NonZeroUsize::new(1).unwrap())
+            .with_time_to_abort(Duration::from_secs(1)),
+    );
+
+    // First, use all the cores
+    let permit1 = queue.try_get_search_permit().await.unwrap();
+    let q = queue.clone();
+    let permit2 = tokio::task::spawn(async move { q.try_get_search_permit().await });
+    tokio::time::sleep(Duration::from_secs(1)).await;
+    permit1.drop().await;
+    let ret = permit2.await.unwrap();
+
+    snapshot!(ret.unwrap_err(), @"Too many search requests running at the same time: 1. Retry after 10s.");
+}
+
 #[actix_rt::test]
 async fn wait_till_cores_are_available() {
     let queue = Arc::new(SearchQueue::new(4, NonZeroUsize::new(1).unwrap()));

meilisearch/tests/search/snapshots/distinct.rs/distinct_at_search_time/succeed.snap

@@ -2,7 +2,7 @@
 source: meilisearch/tests/search/distinct.rs
 ---
 {
-  "uid": 1,
+  "uid": "[uid]",
   "indexUid": "tamo",
   "status": "succeeded",
   "type": "settingsUpdate",

meilisearch/tests/search/snapshots/errors.rs/distinct_at_search_time/task-succeed.snap

@@ -2,7 +2,7 @@
 source: meilisearch/tests/search/errors.rs
 ---
 {
-  "uid": 0,
+  "uid": "[uid]",
   "indexUid": "tamo",
   "status": "succeeded",
   "type": "indexCreation",

meilisearch/tests/settings/errors.rs

@@ -5,8 +5,8 @@ use crate::json;
 
 #[actix_rt::test]
 async fn settings_bad_displayed_attributes() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "displayedAttributes": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
@@ -33,8 +33,8 @@ async fn settings_bad_displayed_attributes() {
 
 #[actix_rt::test]
 async fn settings_bad_searchable_attributes() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "searchableAttributes": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
@@ -61,8 +61,8 @@ async fn settings_bad_searchable_attributes() {
 
 #[actix_rt::test]
 async fn settings_bad_filterable_attributes() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "filterableAttributes": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
@@ -89,8 +89,8 @@ async fn settings_bad_filterable_attributes() {
 
 #[actix_rt::test]
 async fn settings_bad_sortable_attributes() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "sortableAttributes": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
@@ -117,8 +117,8 @@ async fn settings_bad_sortable_attributes() {
 
 #[actix_rt::test]
 async fn settings_bad_ranking_rules() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "rankingRules": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
@@ -145,8 +145,8 @@ async fn settings_bad_ranking_rules() {
 
 #[actix_rt::test]
 async fn settings_bad_stop_words() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "stopWords": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
@@ -173,8 +173,8 @@ async fn settings_bad_stop_words() {
 
 #[actix_rt::test]
 async fn settings_bad_synonyms() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "synonyms": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
@@ -201,8 +201,8 @@ async fn settings_bad_synonyms() {
 
 #[actix_rt::test]
 async fn settings_bad_distinct_attribute() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "distinctAttribute": ["doggo"] })).await;
     snapshot!(code, @"400 Bad Request");
@@ -229,8 +229,8 @@ async fn settings_bad_distinct_attribute() {
 
 #[actix_rt::test]
 async fn settings_bad_typo_tolerance() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "typoTolerance": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
@@ -284,8 +284,8 @@ async fn settings_bad_typo_tolerance() {
 
 #[actix_rt::test]
 async fn settings_bad_faceting() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "faceting": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
@@ -312,8 +312,8 @@ async fn settings_bad_faceting() {
 
 #[actix_rt::test]
 async fn settings_bad_pagination() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "pagination": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");
@@ -340,8 +340,8 @@ async fn settings_bad_pagination() {
 
 #[actix_rt::test]
 async fn settings_bad_search_cutoff_ms() {
-    let server = Server::new().await;
-    let index = server.index("test");
+    let server = Server::new_shared();
+    let index = server.unique_index();
 
     let (response, code) = index.update_settings(json!({ "searchCutoffMs": "doggo" })).await;
     snapshot!(code, @"400 Bad Request");

meilisearch/tests/settings/get_settings.rs

@@ -9,6 +9,7 @@ static DEFAULT_SETTINGS_VALUES: Lazy<HashMap<&'static str, Value>> = Lazy::new(|
     let mut map = HashMap::new();
     map.insert("displayed_attributes", json!(["*"]));
     map.insert("searchable_attributes", json!(["*"]));
+    map.insert("localized_attributes", json!(null));
     map.insert("filterable_attributes", json!([]));
     map.insert("distinct_attribute", json!(null));
     map.insert(
@@ -189,7 +190,8 @@ async fn secrets_are_hidden_in_settings() {
           "source": "rest",
           "apiKey": "My suXXXXXX...",
           "dimensions": 4,
-          "documentTemplate": "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}",
+          "documentTemplate": "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
+          "documentTemplateMaxBytes": 400,
           "url": "https://localhost:7777",
           "request": "{{text}}",
           "response": "{{embedding}}",
@@ -409,6 +411,7 @@ macro_rules! test_setting_routes {
 test_setting_routes!(
     filterable_attributes put,
     displayed_attributes put,
+    localized_attributes put,
     searchable_attributes put,
     distinct_attribute put,
     stop_words put,

meilisearch/tests/similar/errors.rs

@@ -18,7 +18,7 @@ async fn similar_unexisting_index() {
     });
 
     index
-        .similar(json!({"id": 287947}), |response, code| {
+        .similar(json!({"id": 287947, "embedder": "manual"}), |response, code| {
             assert_eq!(code, 404);
             assert_eq!(response, expected_response);
         })
@@ -44,7 +44,7 @@ async fn similar_feature_not_enabled() {
     let server = Server::new().await;
     let index = server.index("test");
 
-    let (response, code) = index.similar_post(json!({"id": 287947})).await;
+    let (response, code) = index.similar_post(json!({"id": 287947, "embedder": "manual"})).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -199,7 +199,8 @@ async fn similar_not_found_id() {
     snapshot!(code, @"202 Accepted");
     server.wait_task(response.uid()).await;
 
-    let (response, code) = index.similar_post(json!({"id": "definitely-doesnt-exist"})).await;
+    let (response, code) =
+        index.similar_post(json!({"id": "definitely-doesnt-exist", "embedder": "manual"})).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -230,7 +231,8 @@ async fn similar_bad_offset() {
     snapshot!(code, @"202 Accepted");
     server.wait_task(response.uid()).await;
 
-    let (response, code) = index.similar_post(json!({"id": 287947, "offset": "doggo"})).await;
+    let (response, code) =
+        index.similar_post(json!({"id": 287947, "offset": "doggo", "embedder": "manual"})).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -241,7 +243,7 @@ async fn similar_bad_offset() {
     }
     "###);
 
-    let (response, code) = index.similar_get("?id=287947&offset=doggo").await;
+    let (response, code) = index.similar_get("?id=287947&offset=doggo&embedder=manual").await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -272,7 +274,8 @@ async fn similar_bad_limit() {
     snapshot!(code, @"202 Accepted");
     server.wait_task(response.uid()).await;
 
-    let (response, code) = index.similar_post(json!({"id": 287947, "limit": "doggo"})).await;
+    let (response, code) =
+        index.similar_post(json!({"id": 287947, "limit": "doggo", "embedder": "manual"})).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -283,7 +286,7 @@ async fn similar_bad_limit() {
     }
     "###);
 
-    let (response, code) = index.similar_get("?id=287946&limit=doggo").await;
+    let (response, code) = index.similar_get("?id=287946&limit=doggo&embedder=manual").await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -323,7 +326,8 @@ async fn similar_bad_filter() {
     snapshot!(code, @"202 Accepted");
     index.wait_task(value.uid()).await;
 
-    let (response, code) = index.similar_post(json!({ "id": 287947, "filter": true })).await;
+    let (response, code) =
+        index.similar_post(json!({ "id": 287947, "filter": true, "embedder": "manual" })).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -361,10 +365,10 @@ async fn filter_invalid_syntax_object() {
     index.wait_task(value.uid()).await;
 
     index
-        .similar(json!({"id": 287947, "filter": "title & Glass"}), |response, code| {
+        .similar(json!({"id": 287947, "filter": "title & Glass", "embedder": "manual"}), |response, code| {
             snapshot!(response, @r###"
             {
-              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
               "code": "invalid_similar_filter",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
@@ -400,10 +404,10 @@ async fn filter_invalid_syntax_array() {
     index.wait_task(value.uid()).await;
 
     index
-        .similar(json!({"id": 287947, "filter": ["title & Glass"]}), |response, code| {
+        .similar(json!({"id": 287947, "filter": ["title & Glass"], "embedder": "manual"}), |response, code| {
             snapshot!(response, @r###"
             {
-              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
               "code": "invalid_similar_filter",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
@@ -446,7 +450,7 @@ async fn filter_invalid_syntax_string() {
     });
     index
         .similar(
-            json!({"id": 287947, "filter": "title = Glass XOR title = Glass"}),
+            json!({"id": 287947, "filter": "title = Glass XOR title = Glass", "embedder": "manual"}),
             |response, code| {
                 assert_eq!(response, expected_response);
                 assert_eq!(code, 400);
@@ -486,10 +490,13 @@ async fn filter_invalid_attribute_array() {
         "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
     });
     index
-        .similar(json!({"id": 287947, "filter": ["many = Glass"]}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
-        })
+        .similar(
+            json!({"id": 287947, "filter": ["many = Glass"], "embedder": "manual"}),
+            |response, code| {
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
+            },
+        )
         .await;
 }
 
@@ -524,10 +531,13 @@ async fn filter_invalid_attribute_string() {
         "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
     });
     index
-        .similar(json!({"id": 287947, "filter": "many = Glass"}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
-        })
+        .similar(
+            json!({"id": 287947, "filter": "many = Glass", "embedder": "manual"}),
+            |response, code| {
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
+            },
+        )
         .await;
 }
 
@@ -562,10 +572,13 @@ async fn filter_reserved_geo_attribute_array() {
         "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
     });
     index
-        .similar(json!({"id": 287947, "filter": ["_geo = Glass"]}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
-        })
+        .similar(
+            json!({"id": 287947, "filter": ["_geo = Glass"], "embedder": "manual"}),
+            |response, code| {
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
+            },
+        )
         .await;
 }
 
@@ -600,10 +613,13 @@ async fn filter_reserved_geo_attribute_string() {
         "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
     });
     index
-        .similar(json!({"id": 287947, "filter": "_geo = Glass"}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
-        })
+        .similar(
+            json!({"id": 287947, "filter": "_geo = Glass", "embedder": "manual"}),
+            |response, code| {
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
+            },
+        )
         .await;
 }
 
@@ -638,10 +654,13 @@ async fn filter_reserved_attribute_array() {
         "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
     });
     index
-        .similar(json!({"id": 287947, "filter": ["_geoDistance = Glass"]}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
-        })
+        .similar(
+            json!({"id": 287947, "filter": ["_geoDistance = Glass"], "embedder": "manual"}),
+            |response, code| {
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
+            },
+        )
         .await;
 }
 
@@ -676,10 +695,13 @@ async fn filter_reserved_attribute_string() {
         "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
     });
     index
-        .similar(json!({"id": 287947, "filter": "_geoDistance = Glass"}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
-        })
+        .similar(
+            json!({"id": 287947, "filter": "_geoDistance = Glass", "embedder": "manual"}),
+            |response, code| {
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
+            },
+        )
         .await;
 }
 
@@ -714,10 +736,13 @@ async fn filter_reserved_geo_point_array() {
         "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
     });
     index
-        .similar(json!({"id": 287947, "filter": ["_geoPoint = Glass"]}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
-        })
+        .similar(
+            json!({"id": 287947, "filter": ["_geoPoint = Glass"], "embedder": "manual"}),
+            |response, code| {
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
+            },
+        )
         .await;
 }
 
@@ -752,10 +777,13 @@ async fn filter_reserved_geo_point_string() {
         "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
     });
     index
-        .similar(json!({"id": 287947, "filter": "_geoPoint = Glass"}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
-        })
+        .similar(
+            json!({"id": 287947, "filter": "_geoPoint = Glass", "embedder": "manual"}),
+            |response, code| {
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
+            },
+        )
         .await;
 }
 
@@ -765,7 +793,8 @@ async fn similar_bad_retrieve_vectors() {
     server.set_features(json!({"vectorStore": true})).await;
     let index = server.index("test");
 
-    let (response, code) = index.similar_post(json!({"retrieveVectors": "doggo"})).await;
+    let (response, code) =
+        index.similar_post(json!({"retrieveVectors": "doggo", "embedder": "manual"})).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
@@ -776,7 +805,8 @@ async fn similar_bad_retrieve_vectors() {
     }
     "###);
 
-    let (response, code) = index.similar_post(json!({"retrieveVectors": [true]})).await;
+    let (response, code) =
+        index.similar_post(json!({"retrieveVectors": [true], "embedder": "manual"})).await;
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {

meilisearch/tests/similar/mod.rs

@@ -80,9 +80,11 @@ async fn basic() {
     index.wait_task(value.uid()).await;
 
     index
-        .similar(json!({"id": 143, "retrieveVectors": true}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
+        .similar(
+            json!({"id": 143, "retrieveVectors": true, "embedder": "manual"}),
+            |response, code| {
+                snapshot!(code, @"200 OK");
+                snapshot!(json_string!(response["hits"]), @r###"
             [
               {
                 "title": "Escape Room",
@@ -154,13 +156,16 @@ async fn basic() {
               }
             ]
             "###);
-        })
+            },
+        )
         .await;
 
     index
-        .similar(json!({"id": "299537", "retrieveVectors": true}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
+        .similar(
+            json!({"id": "299537", "retrieveVectors": true, "embedder": "manual"}),
+            |response, code| {
+                snapshot!(code, @"200 OK");
+                snapshot!(json_string!(response["hits"]), @r###"
             [
               {
                 "title": "How to Train Your Dragon: The Hidden World",
@@ -232,7 +237,8 @@ async fn basic() {
               }
             ]
             "###);
-        })
+            },
+        )
         .await;
 }
 
@@ -272,7 +278,7 @@ async fn ranking_score_threshold() {
 
     index
         .similar(
-            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0, "retrieveVectors": true}),
+            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0, "retrieveVectors": true, "embedder": "manual"}),
             |response, code| {
                 snapshot!(code, @"200 OK");
                 meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"4");
@@ -358,7 +364,7 @@ async fn ranking_score_threshold() {
 
     index
         .similar(
-            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.2, "retrieveVectors": true}),
+            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.2, "retrieveVectors": true, "embedder": "manual"}),
             |response, code| {
                 snapshot!(code, @"200 OK");
                 meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"3");
@@ -426,7 +432,7 @@ async fn ranking_score_threshold() {
 
     index
         .similar(
-            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.3, "retrieveVectors": true}),
+            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.3, "retrieveVectors": true, "embedder": "manual"}),
             |response, code| {
                 snapshot!(code, @"200 OK");
                 meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"2");
@@ -476,7 +482,7 @@ async fn ranking_score_threshold() {
 
     index
         .similar(
-            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.6, "retrieveVectors": true}),
+            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.6, "retrieveVectors": true, "embedder": "manual"}),
             |response, code| {
                 snapshot!(code, @"200 OK");
                 meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"1");
@@ -508,7 +514,7 @@ async fn ranking_score_threshold() {
 
     index
         .similar(
-            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.9, "retrieveVectors": true}),
+            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.9, "retrieveVectors": true, "embedder": "manual"}),
             |response, code| {
                 snapshot!(code, @"200 OK");
                 snapshot!(json_string!(response["hits"]), @"[]");
@@ -553,7 +559,7 @@ async fn filter() {
 
     index
         .similar(
-            json!({"id": 522681, "filter": "release_year = 2019", "retrieveVectors": true}),
+            json!({"id": 522681, "filter": "release_year = 2019", "retrieveVectors": true, "embedder": "manual"}),
             |response, code| {
                 snapshot!(code, @"200 OK");
                 snapshot!(json_string!(response["hits"]), @r###"
@@ -617,7 +623,7 @@ async fn filter() {
 
     index
         .similar(
-            json!({"id": 522681, "filter": "release_year < 2000", "retrieveVectors": true}),
+            json!({"id": 522681, "filter": "release_year < 2000", "retrieveVectors": true, "embedder": "manual"}),
             |response, code| {
                 snapshot!(code, @"200 OK");
                 snapshot!(json_string!(response["hits"]), @r###"
@@ -681,9 +687,11 @@ async fn limit_and_offset() {
     index.wait_task(value.uid()).await;
 
     index
-        .similar(json!({"id": 143, "limit": 1, "retrieveVectors": true}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]), @r###"
+        .similar(
+            json!({"id": 143, "limit": 1, "retrieveVectors": true, "embedder": "manual"}),
+            |response, code| {
+                snapshot!(code, @"200 OK");
+                snapshot!(json_string!(response["hits"]), @r###"
             [
               {
                 "title": "Escape Room",
@@ -704,12 +712,13 @@ async fn limit_and_offset() {
               }
             ]
             "###);
-        })
+            },
+        )
         .await;
 
     index
         .similar(
-            json!({"id": 143, "limit": 1, "offset": 1, "retrieveVectors": true}),
+            json!({"id": 143, "limit": 1, "offset": 1, "retrieveVectors": true, "embedder": "manual"}),
             |response, code| {
                 snapshot!(code, @"200 OK");
                 snapshot!(json_string!(response["hits"]), @r###"

meilisearch/tests/swap_indexes/errors.rs

@@ -5,7 +5,7 @@ use crate::json;
 
 #[actix_rt::test]
 async fn swap_indexes_bad_format() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.index_swap(json!("doggo")).await;
     snapshot!(code, @"400 Bad Request");
@@ -32,7 +32,7 @@ async fn swap_indexes_bad_format() {
 
 #[actix_rt::test]
 async fn swap_indexes_bad_indexes() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.index_swap(json!([{ "indexes": "doggo"}])).await;
     snapshot!(code, @"400 Bad Request");

meilisearch/tests/tasks/errors.rs

@@ -4,7 +4,7 @@ use crate::common::Server;
 
 #[actix_rt::test]
 async fn task_bad_uids() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("uids=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -53,7 +53,7 @@ async fn task_bad_uids() {
 
 #[actix_rt::test]
 async fn task_bad_canceled_by() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("canceledBy=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -91,7 +91,7 @@ async fn task_bad_canceled_by() {
 
 #[actix_rt::test]
 async fn task_bad_types() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("types=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -129,7 +129,7 @@ async fn task_bad_types() {
 
 #[actix_rt::test]
 async fn task_bad_statuses() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("statuses=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -167,7 +167,7 @@ async fn task_bad_statuses() {
 
 #[actix_rt::test]
 async fn task_bad_index_uids() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("indexUids=the%20good%20doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -205,7 +205,7 @@ async fn task_bad_index_uids() {
 
 #[actix_rt::test]
 async fn task_bad_limit() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("limit=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -243,7 +243,7 @@ async fn task_bad_limit() {
 
 #[actix_rt::test]
 async fn task_bad_from() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("from=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -281,7 +281,7 @@ async fn task_bad_from() {
 
 #[actix_rt::test]
 async fn task_bad_after_enqueued_at() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("afterEnqueuedAt=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -319,7 +319,7 @@ async fn task_bad_after_enqueued_at() {
 
 #[actix_rt::test]
 async fn task_bad_before_enqueued_at() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("beforeEnqueuedAt=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -357,7 +357,7 @@ async fn task_bad_before_enqueued_at() {
 
 #[actix_rt::test]
 async fn task_bad_after_started_at() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("afterStartedAt=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -395,7 +395,7 @@ async fn task_bad_after_started_at() {
 
 #[actix_rt::test]
 async fn task_bad_before_started_at() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("beforeStartedAt=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -433,7 +433,7 @@ async fn task_bad_before_started_at() {
 
 #[actix_rt::test]
 async fn task_bad_after_finished_at() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("afterFinishedAt=doggo").await;
     snapshot!(code, @"400 Bad Request");
@@ -471,7 +471,7 @@ async fn task_bad_after_finished_at() {
 
 #[actix_rt::test]
 async fn task_bad_before_finished_at() {
-    let server = Server::new().await;
+    let server = Server::new_shared();
 
     let (response, code) = server.tasks_filter("beforeFinishedAt=doggo").await;
     snapshot!(code, @"400 Bad Request");