Add spans

4943: Correct broken links in README r=curquiza a=iornstein

# Pull Request

## Related issue
Fixes #4942

## What does this PR do?
- Corrects some broken links in the README. My suspicion is that some of these documentation articles were moved around without someone updating links in the README.

## PR checklist
Please check if your PR fulfills the following requirements:
- [x] Does this PR fix an existing issue, or have you listed the changes applied in the PR description (and why they are needed)? _(well the contributing guidelines led me to create an issue first)_
- [x] Have you read the contributing guidelines? _yes_
- [x] Have you made sure that the title is accurate and descriptive of the changes? _yes_

Thank you so much for contributing to Meilisearch!


Co-authored-by: Ian Ornstein <ian.ornstein@gmail.com>

Cargo.lock

@@ -387,14 +387,14 @@ checksum = "96d30a06541fbafbc7f82ed10c06164cfbd2c401138f6addd8404629c4b16711"
 [[package]]
 name = "arroy"
 version = "0.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2ece9e5347e7fdaaea3181dec7f916677ad5f3fcbac183648ce1924eb4aeef9a"
+source = "git+https://github.com/meilisearch/arroy/?rev=2386594dfb009ce08821a925ccc89fb8e30bf73d#2386594dfb009ce08821a925ccc89fb8e30bf73d"
 dependencies = [
  "bytemuck",
  "byteorder",
  "heed",
  "log",
  "memmap2",
+ "nohash",
  "ordered-float",
  "rand",
  "rayon",
@@ -471,7 +471,7 @@ checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
 [[package]]
 name = "benchmarks"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "anyhow",
  "bytes",
@@ -652,7 +652,7 @@ dependencies = [
 
 [[package]]
 name = "build-info"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "anyhow",
  "time",
@@ -933,9 +933,8 @@ dependencies = [
 
 [[package]]
 name = "charabia"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03cd8f290cae94934cdd0103c14c2de9faf2d7d85be0d24d511af2bf1b14119d"
+version = "0.9.1"
+source = "git+https://github.com/meilisearch/charabia?branch=mutualize-char-normalizer#f8d8308cdb8db80819be7eeed5652cc4a995cc71"
 dependencies = [
  "aho-corasick",
  "csv",
@@ -1622,7 +1621,7 @@ dependencies = [
 
 [[package]]
 name = "dump"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "anyhow",
  "big_s",
@@ -1834,7 +1833,7 @@ checksum = "9fc0510504f03c51ada170672ac806f1f105a88aa97a5281117e1ddc3368e51a"
 
 [[package]]
 name = "file-store"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "tempfile",
  "thiserror",
@@ -1856,7 +1855,7 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "insta",
  "nom",
@@ -1876,7 +1875,7 @@ dependencies = [
 
 [[package]]
 name = "flatten-serde-json"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "criterion",
  "serde_json",
@@ -2000,7 +1999,7 @@ dependencies = [
 
 [[package]]
 name = "fuzzers"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "arbitrary",
  "clap",
@@ -2221,11 +2220,11 @@ checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
 [[package]]
 name = "grenad"
 version = "0.4.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "350d89047298d3b1b40050acd11ab76e487b854a104b760ebc5a7f375093de77"
+source = "git+https://github.com/meilisearch/grenad?branch=various-improvements#58ac87d852413571102f44c5e55ca13509a3f1a0"
 dependencies = [
  "bytemuck",
  "byteorder",
+ "either",
  "rayon",
  "tempfile",
 ]
@@ -2308,9 +2307,9 @@ dependencies = [
 
 [[package]]
 name = "hashbrown"
-version = "0.14.3"
+version = "0.14.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "290f1a1d9242c78d09ce40a5e87e7554ee637af1351968159f4952f028f75604"
+checksum = "e5274423e17b7c9fc20b6e7e208532f9b19825d82dfd615708b70edd83df41f1"
 dependencies = [
  "ahash 0.8.11",
  "allocator-api2",
@@ -2552,7 +2551,7 @@ checksum = "206ca75c9c03ba3d4ace2460e57b189f39f43de612c2f85836e65c929701bb2d"
 
 [[package]]
 name = "index-scheduler"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "anyhow",
  "arroy",
@@ -2570,6 +2569,7 @@ dependencies = [
  "meili-snap",
  "meilisearch-auth",
  "meilisearch-types",
+ "memmap2",
  "page_size",
  "rayon",
  "roaring",
@@ -2591,7 +2591,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "168fb715dda47215e360912c096649d23d58bf392ac62f73919e831745e40f26"
 dependencies = [
  "equivalent",
- "hashbrown 0.14.3",
+ "hashbrown 0.14.5",
  "serde",
 ]
 
@@ -2650,8 +2650,7 @@ checksum = "28b29a3cd74f0f4598934efe3aeba42bae0eb4680554128851ebbecb02af14e6"
 [[package]]
 name = "irg-kvariants"
 version = "0.1.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ef2af7c331f2536964a32b78a7d2e0963d78b42f4a76323b16cc7d94b1ddce26"
+source = "git+https://github.com/meilisearch/charabia?branch=mutualize-char-normalizer#f8d8308cdb8db80819be7eeed5652cc4a995cc71"
 dependencies = [
  "csv",
  "once_cell",
@@ -2746,7 +2745,7 @@ dependencies = [
 
 [[package]]
 name = "json-depth-checker"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "criterion",
  "serde_json",
@@ -3365,7 +3364,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
 
 [[package]]
 name = "meili-snap"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "insta",
  "md5",
@@ -3374,7 +3373,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "actix-cors",
  "actix-http",
@@ -3463,7 +3462,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-auth"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "base64 0.22.1",
  "enum-iterator",
@@ -3482,7 +3481,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-types"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "actix-web",
  "anyhow",
@@ -3512,7 +3511,7 @@ dependencies = [
 
 [[package]]
 name = "meilitool"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "anyhow",
  "clap",
@@ -3520,6 +3519,7 @@ dependencies = [
  "file-store",
  "meilisearch-auth",
  "meilisearch-types",
+ "serde",
  "time",
  "uuid",
 ]
@@ -3542,7 +3542,7 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "arroy",
  "big_s",
@@ -3566,6 +3566,7 @@ dependencies = [
  "fxhash",
  "geoutils",
  "grenad",
+ "hashbrown 0.14.5",
  "heed",
  "hf-hub",
  "indexmap",
@@ -3685,6 +3686,12 @@ 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"
@@ -3829,9 +3836,8 @@ dependencies = [
 
 [[package]]
 name = "obkv"
-version = "0.2.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a2e27bcfe835a379d32352112f6b8dbae2d99d16a5fff42abe6e5ba5386c1e5a"
+version = "0.3.0"
+source = "git+https://github.com/kerollmops/obkv?branch=unsized-kvreader#ce535874008ecac554f02e0c670e6caf62134d6b"
 
 [[package]]
 name = "once_cell"
@@ -3976,7 +3982,7 @@ checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
 
 [[package]]
 name = "permissive-json-pointer"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "big_s",
  "serde_json",
@@ -4648,8 +4654,7 @@ dependencies = [
 [[package]]
 name = "roaring"
 version = "0.10.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f4b84ba6e838ceb47b41de5194a60244fac43d9fe03b71dbe8c5a201081d6d1"
+source = "git+https://github.com/RoaringBitmap/roaring-rs?branch=clone-iter-slice#6bba84b1a47da1d6e52d5c4dc0ce8593ae4646a5"
 dependencies = [
  "bytemuck",
  "byteorder",
@@ -4834,9 +4839,9 @@ checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
 
 [[package]]
 name = "serde"
-version = "1.0.204"
+version = "1.0.210"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bc76f558e0cbb2a839d37354c575f1dc3fdc6546b5be373ba43d95f231bf7c12"
+checksum = "c8e3592472072e6e22e0a54d5904d9febf8508f65fb8552499a1abc7d1078c3a"
 dependencies = [
  "serde_derive",
 ]
@@ -4852,9 +4857,9 @@ dependencies = [
 
 [[package]]
 name = "serde_derive"
-version = "1.0.204"
+version = "1.0.210"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e0cd7e117be63d3c3678776753929474f3b04a43a080c744d6b0ae2a8c28e222"
+checksum = "243902eda00fad750862fc144cea25caca5e20d615af0a81bee94ca738f1df1f"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -6035,7 +6040,7 @@ version = "0.16.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "471d1c1645d361eb782a1650b1786a8fb58dd625e681a04c09f5ff7c8764a7b0"
 dependencies = [
- "hashbrown 0.14.3",
+ "hashbrown 0.14.5",
  "once_cell",
 ]
 
@@ -6361,7 +6366,7 @@ dependencies = [
 
 [[package]]
 name = "xtask"
-version = "1.10.0"
+version = "1.11.0"
 dependencies = [
  "anyhow",
  "build-info",

Cargo.toml

@@ -22,7 +22,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.10.0"
+version = "1.11.0"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",
@@ -44,23 +44,5 @@ opt-level = 3
 [profile.dev.package.roaring]
 opt-level = 3
 
-[profile.dev.package.lindera-ipadic-builder]
-opt-level = 3
-[profile.dev.package.encoding]
-opt-level = 3
-[profile.dev.package.yada]
-opt-level = 3
-
-[profile.release.package.lindera-ipadic-builder]
-opt-level = 3
-[profile.release.package.encoding]
-opt-level = 3
-[profile.release.package.yada]
-opt-level = 3
-
-[profile.bench.package.lindera-ipadic-builder]
-opt-level = 3
-[profile.bench.package.encoding]
-opt-level = 3
-[profile.bench.package.yada]
-opt-level = 3
+[patch.crates-io]
+roaring = { git = "https://github.com/RoaringBitmap/roaring-rs", branch = "clone-iter-slice" }

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

@@ -29,6 +29,7 @@ serde_json = { version = "1.0.120", features = ["preserve_order"] }
 synchronoise = "1.0.1"
 tempfile = "3.10.1"
 thiserror = "1.0.61"
+memmap2 = "0.9.4"
 time = { version = "0.3.36", features = [
     "serde-well-known",
     "formatting",
@@ -40,7 +41,7 @@ ureq = "2.10.0"
 uuid = { version = "1.10.0", features = ["serde", "v4"] }
 
 [dev-dependencies]
-arroy = "0.4.0"
+arroy = { git = "https://github.com/meilisearch/arroy/", rev = "2386594dfb009ce08821a925ccc89fb8e30bf73d" }
 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

@@ -28,6 +28,9 @@ use meilisearch_types::error::Code;
 use meilisearch_types::heed::{RoTxn, RwTxn};
 use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader};
 use meilisearch_types::milli::heed::CompactionOption;
+use meilisearch_types::milli::update::new::indexer::{
+    self, retrieve_or_guess_primary_key, DocumentChanges,
+};
 use meilisearch_types::milli::update::{
     IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings as MilliSettings,
 };
@@ -110,9 +113,9 @@ 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 +168,11 @@ 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 +237,7 @@ 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 +255,8 @@ 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 +292,6 @@ 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 +354,11 @@ 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,
                 }))
             }
@@ -909,10 +878,8 @@ impl IndexScheduler {
                             while let Some(doc) =
                                 cursor.next_document().map_err(milli::Error::from)?
                             {
-                                dump_content_file.push_document(&obkv_to_object(
-                                    &doc,
-                                    &documents_batch_index,
-                                )?)?;
+                                dump_content_file
+                                    .push_document(&obkv_to_object(doc, &documents_batch_index)?)?;
                             }
                             dump_content_file.flush()?;
                         }
@@ -1286,58 +1253,52 @@ impl IndexScheduler {
                 let must_stop_processing = self.must_stop_processing.clone();
                 let indexer_config = self.index_mapper.indexer_config();
 
-                if let Some(primary_key) = primary_key {
-                    match index.primary_key(index_wtxn)? {
-                        // if a primary key was set AND had already been defined in the index
-                        // but to a different value, we can make the whole batch fail.
-                        Some(pk) => {
-                            if primary_key != pk {
-                                return Err(milli::Error::from(
-                                    milli::UserError::PrimaryKeyCannotBeChanged(pk.to_string()),
-                                )
-                                .into());
-                            }
-                        }
-                        // if the primary key was set and there was no primary key set for this index
-                        // we set it to the received value before starting the indexing process.
-                        None => {
-                            let mut builder =
-                                milli::update::Settings::new(index_wtxn, index, indexer_config);
-                            builder.set_primary_key(primary_key);
-                            builder.execute(
-                                |indexing_step| tracing::debug!(update = ?indexing_step),
-                                || must_stop_processing.clone().get(),
-                            )?;
-                            primary_key_has_been_set = true;
+                /// TODO manage errors correctly
+                let rtxn = index.read_txn()?;
+                let first_addition_uuid = operations
+                    .iter()
+                    .find_map(|op| match op {
+                        DocumentOperation::Add(content_uuid) => Some(content_uuid),
+                        _ => None,
+                    })
+                    .unwrap();
+
+                let mut content_files = Vec::new();
+                for operation in &operations {
+                    if let DocumentOperation::Add(content_uuid) = operation {
+                        let content_file = self.file_store.get_update(*content_uuid)?;
+                        let mmap = unsafe { memmap2::Mmap::map(&content_file)? };
+                        if !mmap.is_empty() {
+                            content_files.push(mmap);
                         }
                     }
                 }
 
-                let config = IndexDocumentsConfig { update_method: method, ..Default::default() };
+                let mut fields_ids_map = index.fields_ids_map(&rtxn)?;
+                let first_document = match content_files.first() {
+                    Some(mmap) => {
+                        let mut iter = serde_json::Deserializer::from_slice(mmap).into_iter();
+                        iter.next().transpose().map_err(|e| e.into()).map_err(Error::IoError)?
+                    }
+                    None => None,
+                };
 
-                let embedder_configs = index.embedding_configs(index_wtxn)?;
-                // TODO: consider Arc'ing the map too (we only need read access + we'll be cloning it multiple times, so really makes sense)
-                let embedders = self.embedders(embedder_configs)?;
-
-                let mut builder = milli::update::IndexDocuments::new(
-                    index_wtxn,
+                let primary_key = retrieve_or_guess_primary_key(
+                    &rtxn,
                     index,
-                    indexer_config,
-                    config,
-                    |indexing_step| tracing::trace!(?indexing_step, "Update"),
-                    || must_stop_processing.get(),
-                )?;
+                    &mut fields_ids_map,
+                    first_document.as_ref(),
+                )?
+                .unwrap();
 
+                let mut content_files_iter = content_files.iter();
+                let mut indexer = indexer::DocumentOperation::new(method);
                 for (operation, task) in operations.into_iter().zip(tasks.iter_mut()) {
                     match operation {
-                        DocumentOperation::Add(content_uuid) => {
-                            let content_file = self.file_store.get_update(content_uuid)?;
-                            let reader = DocumentsBatchReader::from_reader(content_file)
-                                .map_err(milli::Error::from)?;
-                            let (new_builder, user_result) = builder.add_documents(reader)?;
-                            builder = new_builder;
-
-                            builder = builder.with_embedders(embedders.clone());
+                        DocumentOperation::Add(_content_uuid) => {
+                            let mmap = content_files_iter.next().unwrap();
+                            let stats = indexer.add_documents(mmap)?;
+                            // builder = builder.with_embedders(embedders.clone());
 
                             let received_documents =
                                 if let Some(Details::DocumentAdditionOrUpdate {
@@ -1351,30 +1312,17 @@ impl IndexScheduler {
                                     unreachable!();
                                 };
 
-                            match user_result {
-                                Ok(count) => {
-                                    task.status = Status::Succeeded;
-                                    task.details = Some(Details::DocumentAdditionOrUpdate {
-                                        received_documents,
-                                        indexed_documents: Some(count),
-                                    })
-                                }
-                                Err(e) => {
-                                    task.status = Status::Failed;
-                                    task.details = Some(Details::DocumentAdditionOrUpdate {
-                                        received_documents,
-                                        indexed_documents: Some(0),
-                                    });
-                                    task.error = Some(milli::Error::from(e).into());
-                                }
-                            }
+                            task.status = Status::Succeeded;
+                            task.details = Some(Details::DocumentAdditionOrUpdate {
+                                received_documents,
+                                indexed_documents: Some(stats.document_count as u64),
+                            })
                         }
                         DocumentOperation::Delete(document_ids) => {
-                            let (new_builder, user_result) =
-                                builder.remove_documents(document_ids)?;
-                            builder = new_builder;
+                            let count = document_ids.len();
+                            indexer.delete_documents(document_ids);
                             // Uses Invariant: remove documents actually always returns Ok for the inner result
-                            let count = user_result.unwrap();
+                            // let count = user_result.unwrap();
                             let provided_ids =
                                 if let Some(Details::DocumentDeletion { provided_ids, .. }) =
                                     task.details
@@ -1388,26 +1336,35 @@ impl IndexScheduler {
                             task.status = Status::Succeeded;
                             task.details = Some(Details::DocumentDeletion {
                                 provided_ids,
-                                deleted_documents: Some(count),
+                                deleted_documents: Some(count as u64),
                             });
                         }
                     }
                 }
 
                 if !tasks.iter().all(|res| res.error.is_some()) {
-                    let addition = builder.execute()?;
-                    tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
-                } else if primary_key_has_been_set {
-                    // Everything failed but we've set a primary key.
-                    // We need to remove it.
-                    let mut builder =
-                        milli::update::Settings::new(index_wtxn, index, indexer_config);
-                    builder.reset_primary_key();
-                    builder.execute(
-                        |indexing_step| tracing::trace!(update = ?indexing_step),
-                        || must_stop_processing.clone().get(),
-                    )?;
+                    /// TODO create a pool if needed
+                    // let pool = indexer_config.thread_pool.unwrap();
+                    let pool = rayon::ThreadPoolBuilder::new().build().unwrap();
+
+                    let param = (index, &rtxn, &primary_key);
+                    let document_changes = indexer.document_changes(&mut fields_ids_map, param)?;
+                    /// TODO pass/write the FieldsIdsMap
+                    indexer::index(index_wtxn, index, fields_ids_map, &pool, document_changes)?;
+
+                    // tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 }
+                // else if primary_key_has_been_set {
+                //     // Everything failed but we've set a primary key.
+                //     // We need to remove it.
+                //     let mut builder =
+                //         milli::update::Settings::new(index_wtxn, index, indexer_config);
+                //     builder.reset_primary_key();
+                //     builder.execute(
+                //         |indexing_step| tracing::trace!(update = ?indexing_step),
+                //         || must_stop_processing.clone().get(),
+                //     )?;
+                // }
 
                 Ok(tasks)
             }
@@ -1439,7 +1396,7 @@ 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 +1426,102 @@ 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 +1725,6 @@ 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/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.");
+
+                        }
                     }
                 }
             })
@@ -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![]);
@@ -5079,7 +5200,7 @@ 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 (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();
@@ -5397,7 +5518,11 @@ mod tests {
                     ),
                     prompt: PromptData {
                         template: "{{doc.doggo}}",
+                        max_bytes: Some(
+                            400,
+                        ),
                     },
+                    quantized: None,
                 },
                 user_provided: RoaringBitmap<[1, 2]>,
             },
@@ -5410,28 +5535,8 @@ 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 +5716,12 @@ 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 +5760,12 @@ 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 +66,5 @@ khmer = ["milli/khmer"]
 vietnamese = ["milli/vietnamese"]
 # force swedish character recomposition
 swedish-recomposition = ["milli/swedish-recomposition"]
+# force german character recomposition
+german = ["milli/german"]

meilisearch-types/src/document_formats.rs

@@ -1,20 +1,22 @@
 use std::fmt::{self, Debug, Display};
 use std::fs::File;
-use std::io::{self, BufWriter, Write};
+use std::io::{self, BufWriter};
 use std::marker::PhantomData;
 
-use memmap2::MmapOptions;
-use milli::documents::{DocumentsBatchBuilder, Error};
+use memmap2::Mmap;
+use milli::documents::Error;
+use milli::update::new::TopLevelMap;
 use milli::Object;
 use serde::de::{SeqAccess, Visitor};
 use serde::{Deserialize, Deserializer};
 use serde_json::error::Category;
+use serde_json::{to_writer, Map, Value};
 
 use crate::error::{Code, ErrorCode};
 
 type Result<T> = std::result::Result<T, DocumentFormatError>;
 
-#[derive(Debug)]
+#[derive(Debug, Clone, Copy)]
 pub enum PayloadType {
     Ndjson,
     Json,
@@ -88,6 +90,26 @@ impl From<(PayloadType, Error)> for DocumentFormatError {
     }
 }
 
+impl From<(PayloadType, serde_json::Error)> for DocumentFormatError {
+    fn from((ty, error): (PayloadType, serde_json::Error)) -> Self {
+        if error.classify() == Category::Data {
+            Self::Io(error.into())
+        } else {
+            Self::MalformedPayload(Error::Json(error), ty)
+        }
+    }
+}
+
+impl From<(PayloadType, csv::Error)> for DocumentFormatError {
+    fn from((ty, error): (PayloadType, csv::Error)) -> Self {
+        if error.is_io_error() {
+            Self::Io(error.into())
+        } else {
+            Self::MalformedPayload(Error::Csv(error), ty)
+        }
+    }
+}
+
 impl From<io::Error> for DocumentFormatError {
     fn from(error: io::Error) -> Self {
         Self::Io(error)
@@ -103,67 +125,140 @@ impl ErrorCode for DocumentFormatError {
     }
 }
 
-/// Reads CSV from input and write an obkv batch to writer.
-pub fn read_csv(file: &File, writer: impl Write, delimiter: u8) -> Result<u64> {
-    let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
-    let mmap = unsafe { MmapOptions::new().map(file)? };
-    let csv = csv::ReaderBuilder::new().delimiter(delimiter).from_reader(mmap.as_ref());
-    builder.append_csv(csv).map_err(|e| (PayloadType::Csv { delimiter }, e))?;
-
-    let count = builder.documents_count();
-    let _ = builder.into_inner().map_err(DocumentFormatError::Io)?;
-
-    Ok(count as u64)
+// TODO remove that from the place I've borrowed it
+#[derive(Debug)]
+enum AllowedType {
+    String,
+    Boolean,
+    Number,
 }
 
-/// Reads JSON from temporary file and write an obkv batch to writer.
-pub fn read_json(file: &File, writer: impl Write) -> Result<u64> {
-    let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
-    let mmap = unsafe { MmapOptions::new().map(file)? };
-    let mut deserializer = serde_json::Deserializer::from_slice(&mmap);
+fn parse_csv_header(header: &str) -> (&str, AllowedType) {
+    // if there are several separators we only split on the last one.
+    match header.rsplit_once(':') {
+        Some((field_name, field_type)) => match field_type {
+            "string" => (field_name, AllowedType::String),
+            "boolean" => (field_name, AllowedType::Boolean),
+            "number" => (field_name, AllowedType::Number),
+            // if the pattern isn't recognized, we keep the whole field.
+            _otherwise => (header, AllowedType::String),
+        },
+        None => (header, AllowedType::String),
+    }
+}
 
-    match array_each(&mut deserializer, |obj| builder.append_json_object(&obj)) {
+/// Reads CSV from file and write it in NDJSON in a file checking it along the way.
+pub fn read_csv(input: &File, output: impl io::Write, delimiter: u8) -> Result<u64> {
+    let ptype = PayloadType::Csv { delimiter };
+    let mut output = BufWriter::new(output);
+    let mut reader = csv::ReaderBuilder::new().delimiter(delimiter).from_reader(input);
+
+    let headers = reader.headers().map_err(|e| DocumentFormatError::from((ptype, e)))?.clone();
+    let typed_fields: Vec<_> = headers.iter().map(parse_csv_header).collect();
+    let mut object: Map<_, _> =
+        typed_fields.iter().map(|(k, _)| (k.to_string(), Value::Null)).collect();
+
+    let mut line = 0;
+    let mut record = csv::StringRecord::new();
+    while reader.read_record(&mut record).map_err(|e| DocumentFormatError::from((ptype, e)))? {
+        // We increment here and not at the end of the loop
+        // to take the header offset into account.
+        line += 1;
+
+        // Reset the document values
+        object.iter_mut().for_each(|(_, v)| *v = Value::Null);
+
+        for (i, (name, atype)) in typed_fields.iter().enumerate() {
+            let value = &record[i];
+            let trimmed_value = value.trim();
+            let value = match atype {
+                AllowedType::Number if trimmed_value.is_empty() => Value::Null,
+                AllowedType::Number => match trimmed_value.parse::<i64>() {
+                    Ok(integer) => Value::from(integer),
+                    Err(_) => match trimmed_value.parse::<f64>() {
+                        Ok(float) => Value::from(float),
+                        Err(error) => {
+                            return Err(DocumentFormatError::MalformedPayload(
+                                Error::ParseFloat { error, line, value: value.to_string() },
+                                ptype,
+                            ))
+                        }
+                    },
+                },
+                AllowedType::Boolean if trimmed_value.is_empty() => Value::Null,
+                AllowedType::Boolean => match trimmed_value.parse::<bool>() {
+                    Ok(bool) => Value::from(bool),
+                    Err(error) => {
+                        return Err(DocumentFormatError::MalformedPayload(
+                            Error::ParseBool { error, line, value: value.to_string() },
+                            ptype,
+                        ))
+                    }
+                },
+                AllowedType::String if value.is_empty() => Value::Null,
+                AllowedType::String => Value::from(value),
+            };
+
+            *object.get_mut(*name).expect("encountered an unknown field") = value;
+        }
+
+        to_writer(&mut output, &object).map_err(|e| DocumentFormatError::from((ptype, e)))?;
+    }
+
+    Ok(line as u64)
+}
+
+/// Reads JSON from file and write it in NDJSON in a file checking it along the way.
+pub fn read_json(input: &File, output: impl io::Write) -> Result<u64> {
+    // We memory map to be able to deserailize into a TopLevelMap<'pl> that
+    // does not allocate when possible and only materialize the first/top level.
+    let input = unsafe { Mmap::map(input).map_err(DocumentFormatError::Io)? };
+
+    let mut out = BufWriter::new(output);
+    let mut deserializer = serde_json::Deserializer::from_slice(&input);
+    let count = match array_each(&mut deserializer, |obj: TopLevelMap| to_writer(&mut out, &obj)) {
         // The json data has been deserialized and does not need to be processed again.
         // The data has been transferred to the writer during the deserialization process.
-        Ok(Ok(_)) => (),
-        Ok(Err(e)) => return Err(DocumentFormatError::Io(e)),
+        Ok(Ok(count)) => count,
+        Ok(Err(e)) => return Err(DocumentFormatError::from((PayloadType::Json, e))),
         Err(e) => {
             // Attempt to deserialize a single json string when the cause of the exception is not Category.data
             // Other types of deserialisation exceptions are returned directly to the front-end
-            if e.classify() != serde_json::error::Category::Data {
-                return Err(DocumentFormatError::MalformedPayload(
-                    Error::Json(e),
-                    PayloadType::Json,
-                ));
+            if e.classify() != Category::Data {
+                return Err(DocumentFormatError::from((PayloadType::Json, e)));
             }
 
-            let content: Object = serde_json::from_slice(&mmap)
+            let content: Object = serde_json::from_slice(&input)
                 .map_err(Error::Json)
                 .map_err(|e| (PayloadType::Json, e))?;
-            builder.append_json_object(&content).map_err(DocumentFormatError::Io)?;
+            to_writer(&mut out, &content)
+                .map(|_| 1)
+                .map_err(|e| DocumentFormatError::from((PayloadType::Json, e)))?
         }
+    };
+
+    match out.into_inner() {
+        Ok(_) => Ok(count),
+        Err(ie) => Err(DocumentFormatError::Io(ie.into_error())),
     }
-
-    let count = builder.documents_count();
-    let _ = builder.into_inner().map_err(DocumentFormatError::Io)?;
-
-    Ok(count as u64)
 }
 
-/// Reads JSON from temporary file  and write an obkv batch to writer.
-pub fn read_ndjson(file: &File, writer: impl Write) -> Result<u64> {
-    let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
-    let mmap = unsafe { MmapOptions::new().map(file)? };
+/// Reads NDJSON from file and write it in NDJSON in a file checking it along the way.
+pub fn read_ndjson(input: &File, output: impl io::Write) -> Result<u64> {
+    // We memory map to be able to deserailize into a TopLevelMap<'pl> that
+    // does not allocate when possible and only materialize the first/top level.
+    let input = unsafe { Mmap::map(input).map_err(DocumentFormatError::Io)? };
+    let mut output = BufWriter::new(output);
 
-    for result in serde_json::Deserializer::from_slice(&mmap).into_iter() {
-        let object = result.map_err(Error::Json).map_err(|e| (PayloadType::Ndjson, e))?;
-        builder.append_json_object(&object).map_err(Into::into).map_err(DocumentFormatError::Io)?;
+    let mut count = 0;
+    for result in serde_json::Deserializer::from_slice(&input).into_iter() {
+        count += 1;
+        result
+            .and_then(|map: TopLevelMap| to_writer(&mut output, &map))
+            .map_err(|e| DocumentFormatError::from((PayloadType::Ndjson, e)))?;
     }
 
-    let count = builder.documents_count();
-    let _ = builder.into_inner().map_err(Into::into).map_err(DocumentFormatError::Io)?;
-
-    Ok(count as u64)
+    Ok(count)
 }
 
 /// The actual handling of the deserialization process in serde
@@ -172,20 +267,23 @@ pub fn read_ndjson(file: &File, writer: impl Write) -> Result<u64> {
 /// ## References
 /// <https://serde.rs/stream-array.html>
 /// <https://github.com/serde-rs/json/issues/160>
-fn array_each<'de, D, T, F>(deserializer: D, f: F) -> std::result::Result<io::Result<u64>, D::Error>
+fn array_each<'de, D, T, F>(
+    deserializer: D,
+    f: F,
+) -> std::result::Result<serde_json::Result<u64>, D::Error>
 where
     D: Deserializer<'de>,
     T: Deserialize<'de>,
-    F: FnMut(T) -> io::Result<()>,
+    F: FnMut(T) -> serde_json::Result<()>,
 {
     struct SeqVisitor<T, F>(F, PhantomData<T>);
 
     impl<'de, T, F> Visitor<'de> for SeqVisitor<T, F>
     where
         T: Deserialize<'de>,
-        F: FnMut(T) -> io::Result<()>,
+        F: FnMut(T) -> serde_json::Result<()>,
     {
-        type Value = io::Result<u64>;
+        type Value = serde_json::Result<u64>;
 
         fn expecting(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
             formatter.write_str("a nonempty sequence")
@@ -194,7 +292,7 @@ where
         fn visit_seq<A>(
             mut self,
             mut seq: A,
-        ) -> std::result::Result<io::Result<u64>, <A as SeqAccess<'de>>::Error>
+        ) -> std::result::Result<serde_json::Result<u64>, <A as SeqAccess<'de>>::Error>
         where
             A: SeqAccess<'de>,
         {
@@ -203,7 +301,7 @@ where
                 match self.0(value) {
                     Ok(()) => max += 1,
                     Err(e) => return Ok(Err(e)),
-                };
+                }
             }
             Ok(Ok(max))
         }

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

@@ -57,7 +57,7 @@ meilisearch-types = { path = "../meilisearch-types" }
 mimalloc = { version = "0.1.43", default-features = false }
 mime = "0.3.17"
 num_cpus = "1.16.0"
-obkv = "0.2.2"
+obkv = { git = "https://github.com/kerollmops/obkv", branch = "unsized-kvreader" }
 once_cell = "1.19.0"
 ordered-float = "4.2.1"
 parking_lot = "0.12.3"
@@ -153,6 +153,7 @@ greek = ["meilisearch-types/greek"]
 khmer = ["meilisearch-types/khmer"]
 vietnamese = ["meilisearch-types/vietnamese"]
 swedish-recomposition = ["meilisearch-types/swedish-recomposition"]
+german = ["meilisearch-types/german"]
 
 [package.metadata.mini-dashboard]
 assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.14/build.zip"

meilisearch/src/analytics/segment_analytics.rs

@@ -646,8 +646,6 @@ pub struct SearchAggregator {
     max_vector_size: usize,
     // Whether the semantic ratio passed to a hybrid search equals the default ratio.
     semantic_ratio: bool,
-    // Whether a non-default embedder was specified
-    embedder: bool,
     hybrid: bool,
     retrieve_vectors: bool,
 
@@ -795,7 +793,6 @@ impl SearchAggregator {
 
         if let Some(hybrid) = hybrid {
             ret.semantic_ratio = hybrid.semantic_ratio != DEFAULT_SEMANTIC_RATIO();
-            ret.embedder = hybrid.embedder.is_some();
             ret.hybrid = true;
         }
 
@@ -863,7 +860,6 @@ impl SearchAggregator {
             show_ranking_score,
             show_ranking_score_details,
             semantic_ratio,
-            embedder,
             hybrid,
             total_degraded,
             total_used_negative_operator,
@@ -923,7 +919,6 @@ impl SearchAggregator {
         self.retrieve_vectors |= retrieve_vectors;
         self.semantic_ratio |= semantic_ratio;
         self.hybrid |= hybrid;
-        self.embedder |= embedder;
 
         // pagination
         self.max_limit = self.max_limit.max(max_limit);
@@ -999,7 +994,6 @@ impl SearchAggregator {
             show_ranking_score,
             show_ranking_score_details,
             semantic_ratio,
-            embedder,
             hybrid,
             total_degraded,
             total_used_negative_operator,
@@ -1051,7 +1045,6 @@ impl SearchAggregator {
                 "hybrid": {
                     "enabled": hybrid,
                     "semantic_ratio": semantic_ratio,
-                    "embedder": embedder,
                 },
                 "pagination": {
                    "max_limit": max_limit,
@@ -1782,7 +1775,6 @@ pub struct SimilarAggregator {
     used_syntax: HashMap<String, usize>,
 
     // Whether a non-default embedder was specified
-    embedder: bool,
     retrieve_vectors: bool,
 
     // pagination
@@ -1803,7 +1795,7 @@ impl SimilarAggregator {
     pub fn from_query(query: &SimilarQuery, request: &HttpRequest) -> Self {
         let SimilarQuery {
             id: _,
-            embedder,
+            embedder: _,
             offset,
             limit,
             attributes_to_retrieve: _,
@@ -1851,7 +1843,6 @@ impl SimilarAggregator {
         ret.show_ranking_score_details = *show_ranking_score_details;
         ret.ranking_score_threshold = ranking_score_threshold.is_some();
 
-        ret.embedder = embedder.is_some();
         ret.retrieve_vectors = *retrieve_vectors;
 
         ret
@@ -1883,7 +1874,6 @@ impl SimilarAggregator {
             max_attributes_to_retrieve,
             show_ranking_score,
             show_ranking_score_details,
-            embedder,
             ranking_score_threshold,
             retrieve_vectors,
         } = other;
@@ -1914,7 +1904,6 @@ impl SimilarAggregator {
             *used_syntax = used_syntax.saturating_add(value);
         }
 
-        self.embedder |= embedder;
         self.retrieve_vectors |= retrieve_vectors;
 
         // pagination
@@ -1948,7 +1937,6 @@ impl SimilarAggregator {
             max_attributes_to_retrieve,
             show_ranking_score,
             show_ranking_score_details,
-            embedder,
             ranking_score_threshold,
             retrieve_vectors,
         } = self;
@@ -1980,9 +1968,6 @@ impl SimilarAggregator {
                 "vector": {
                     "retrieve_vectors": retrieve_vectors,
                 },
-                "hybrid": {
-                    "embedder": embedder,
-                },
                 "pagination": {
                    "max_limit": max_limit,
                    "max_offset": max_offset,

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;
@@ -118,6 +117,7 @@ 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>,
@@ -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)) => {
@@ -469,19 +470,16 @@ 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>,
 ) {
-    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(search_queue)
         .app_data(web::Data::from(analytics))
         .app_data(web::Data::new(logs_route))
         .app_data(web::Data::new(logs_stderr))

meilisearch/src/main.rs

@@ -1,8 +1,10 @@
 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 actix_web::http::KeepAlive;
 use actix_web::web::Data;
@@ -11,6 +13,7 @@ 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,
@@ -148,11 +151,17 @@ async fn run_http(
     let opt_clone = opt.clone();
     let index_scheduler = Data::from(index_scheduler);
     let auth_controller = Data::from(auth_controller);
+    let search_queue = SearchQueue::new(
+        opt.experimental_search_queue_size,
+        available_parallelism().unwrap_or(NonZeroUsize::new(2).unwrap()),
+    );
+    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(),

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/routes/indexes/facet_search.rs

@@ -81,7 +81,7 @@ 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,
@@ -93,7 +93,9 @@ 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);

meilisearch/src/routes/indexes/search.rs

@@ -128,8 +128,10 @@ 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 +142,28 @@ 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 +190,7 @@ 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()),
-        }
+        })
     }
 }
 
@@ -219,7 +230,7 @@ pub async fn search_with_url_query(
     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) {
@@ -233,11 +244,13 @@ pub async fn search_with_url_query(
 
     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);
     }
@@ -276,11 +289,13 @@ 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 {
@@ -308,44 +323,36 @@ 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/settings.rs

@@ -636,11 +636,26 @@ fn embedder_analytics(
             .any(|config| config.document_template.set().is_some())
     });
 
+    let 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()
+    });
+
+    let binary_quantization_used = setting.as_ref().map(|map| {
+        map.values()
+            .filter_map(|config| config.clone().set())
+            .any(|config| config.binary_quantized.set().is_some())
+    });
+
     json!(
         {
             "total": setting.as_ref().map(|s| s.len()),
             "sources": sources,
             "document_template_used": document_template_used,
+            "document_template_max_bytes": document_template_max_bytes,
+            "binary_quantization_used": binary_quantization_used,
         }
     )
 }

meilisearch/src/routes/indexes/similar.rs

@@ -102,8 +102,8 @@ 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 +111,7 @@ async fn similar(
             query,
             embedder_name,
             embedder,
+            quantized,
             retrieve_vectors,
             index_scheduler.features(),
         )
@@ -139,8 +140,8 @@ 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/multi_search.rs

@@ -39,7 +39,7 @@ pub async fn multi_search_with_post(
 ) -> 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();
 
@@ -81,6 +81,7 @@ 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();
@@ -143,6 +144,7 @@ pub async fn multi_search_with_post(
                 Ok(search_results)
             }
             .await;
+            permit.drop().await;
 
             if search_results.is_ok() {
                 multi_aggregate.succeed();

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>)]
@@ -792,7 +789,7 @@ 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 => {
@@ -806,14 +803,19 @@ fn prepare_search<'t>(
                 }
             };
 
-            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 +989,13 @@ 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 +1011,61 @@ 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<'_>,
@@ -1413,6 +1444,7 @@ pub fn perform_similar(
     query: SimilarQuery,
     embedder_name: String,
     embedder: Arc<Embedder>,
+    quantized: bool,
     retrieve_vectors: RetrieveVectors,
     features: RoFeatures,
 ) -> Result<SimilarResult, ResponseError> {
@@ -1441,8 +1473,16 @@ 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)? {
@@ -1642,7 +1682,7 @@ fn add_non_formatted_ids_to_formatted_options(
 fn make_document(
     displayed_attributes: &BTreeSet<FieldId>,
     field_ids_map: &FieldsIdsMap,
-    obkv: obkv::KvReaderU16,
+    obkv: &obkv::KvReaderU16,
 ) -> Result<Document, MeilisearchHttpError> {
     let mut document = serde_json::Map::new();
 

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
@@ -122,3 +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 {
@@ -240,7 +391,8 @@ 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

@@ -1,10 +1,15 @@
+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::search_queue::SearchQueue;
 use meilisearch::{analytics, create_app, Opt, SubscriberForSecondLayer};
 use meilisearch_auth::AuthController;
 use tracing::level_filters::LevelFilter;
@@ -106,7 +111,13 @@ 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 +130,25 @@ 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),
             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/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/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

@@ -1,10 +1,13 @@
 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::search_queue::SearchQueue;
 use meilisearch::{analytics, create_app, Opt, SubscriberForSecondLayer};
 use tracing::level_filters::LevelFilter;
 use tracing_subscriber::layer::SubscriberExt;
@@ -40,10 +43,15 @@ 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),

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 +526,7 @@ 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");
@@ -573,7 +576,7 @@ 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/mod.rs

@@ -16,208 +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);
@@ -225,11 +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);
@@ -240,13 +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);
@@ -254,11 +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);
@@ -290,13 +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);
@@ -312,13 +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);
@@ -343,13 +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);
@@ -442,13 +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!({
@@ -465,11 +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!({
@@ -555,15 +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"]
@@ -609,15 +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!({
@@ -630,14 +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!({
@@ -653,15 +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!({
@@ -674,14 +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!({
@@ -697,15 +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"]
@@ -717,15 +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!({
@@ -740,13 +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
@@ -773,9 +480,6 @@ async fn search_facet_distribution() {
         )
         .await;
 
-    index.update_settings(json!({"filterableAttributes": ["doggos"]})).await;
-    index.wait_task(4).await;
-
     index
         .search(
             json!({
@@ -811,9 +515,6 @@ async fn search_facet_distribution() {
         )
         .await;
 
-    index.update_settings(json!({"filterableAttributes": ["doggos.name"]})).await;
-    index.wait_task(5).await;
-
     index
         .search(
             json!({
@@ -1043,6 +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,
@@ -1394,22 +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,
@@ -1457,6 +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,
         }))
@@ -1469,6 +1183,10 @@ async fn experimental_feature_vector_store() {
       {
         "title": "Shazam!",
         "id": "287947",
+        "color": [
+          "green",
+          "blue"
+        ],
         "_vectors": {
           "manual": {
             "embeddings": [
@@ -1486,6 +1204,10 @@ async fn experimental_feature_vector_store() {
       {
         "title": "Captain Marvel",
         "id": "299537",
+        "color": [
+          "yellow",
+          "blue"
+        ],
         "_vectors": {
           "manual": {
             "embeddings": [
@@ -1503,6 +1225,10 @@ async fn experimental_feature_vector_store() {
       {
         "title": "Gläss",
         "id": "450465",
+        "color": [
+          "blue",
+          "red"
+        ],
         "_vectors": {
           "manual": {
             "embeddings": [
@@ -1520,6 +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": [
@@ -1537,6 +1267,10 @@ async fn experimental_feature_vector_store() {
       {
         "title": "Escape Room",
         "id": "522681",
+        "color": [
+          "yellow",
+          "red"
+        ],
         "_vectors": {
           "manual": {
             "embeddings": [
@@ -1803,6 +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,
@@ -1824,6 +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,
@@ -1845,6 +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/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

@@ -190,7 +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}}",

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");

meilisearch/tests/tasks/mod.rs

@@ -66,8 +66,8 @@ async fn list_tasks() {
 async fn list_tasks_with_star_filters() {
     let server = Server::new().await;
     let index = server.index("test");
-    index.create(None).await;
-    index.wait_task(0).await;
+    let (task, _code) = index.create(None).await;
+    index.wait_task(task.uid()).await;
     index
         .add_documents(serde_json::from_str(include_str!("../assets/test_set.json")).unwrap(), None)
         .await;

meilisearch/tests/vector/binary_quantized.rs

@@ -0,0 +1,380 @@
+use meili_snap::{json_string, snapshot};
+
+use crate::common::{GetAllDocumentsOptions, Server};
+use crate::json;
+use crate::vector::generate_default_user_provided_documents;
+
+#[actix_rt::test]
+async fn retrieve_binary_quantize_status_in_the_settings() {
+    let server = Server::new().await;
+    let index = server.index("doggo");
+    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(value, @r###"
+    {
+      "vectorStore": true,
+      "metrics": false,
+      "logsRoute": false,
+      "editDocumentsByFunction": false,
+      "containsFilter": false
+    }
+    "###);
+
+    let (response, code) = index
+        .update_settings(json!({
+          "embedders": {
+              "manual": {
+                  "source": "userProvided",
+                  "dimensions": 3,
+              }
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await.succeeded();
+
+    let (settings, code) = index.settings().await;
+    snapshot!(code, @"200 OK");
+    snapshot!(settings["embedders"]["manual"], @r###"{"source":"userProvided","dimensions":3}"###);
+
+    let (response, code) = index
+        .update_settings(json!({
+          "embedders": {
+              "manual": {
+                  "source": "userProvided",
+                  "dimensions": 3,
+                  "binaryQuantized": false,
+              }
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await.succeeded();
+
+    let (settings, code) = index.settings().await;
+    snapshot!(code, @"200 OK");
+    snapshot!(settings["embedders"]["manual"], @r###"{"source":"userProvided","dimensions":3,"binaryQuantized":false}"###);
+
+    let (response, code) = index
+        .update_settings(json!({
+          "embedders": {
+              "manual": {
+                  "source": "userProvided",
+                  "dimensions": 3,
+                  "binaryQuantized": true,
+              }
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await.succeeded();
+
+    let (settings, code) = index.settings().await;
+    snapshot!(code, @"200 OK");
+    snapshot!(settings["embedders"]["manual"], @r###"{"source":"userProvided","dimensions":3,"binaryQuantized":true}"###);
+}
+
+#[actix_rt::test]
+async fn binary_quantize_before_sending_documents() {
+    let server = Server::new().await;
+    let index = server.index("doggo");
+    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(value, @r###"
+    {
+      "vectorStore": true,
+      "metrics": false,
+      "logsRoute": false,
+      "editDocumentsByFunction": false,
+      "containsFilter": false
+    }
+    "###);
+
+    let (response, code) = index
+        .update_settings(json!({
+          "embedders": {
+              "manual": {
+                  "source": "userProvided",
+                  "dimensions": 3,
+                  "binaryQuantized": true,
+              }
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await.succeeded();
+
+    let documents = json!([
+      {"id": 0, "name": "kefir", "_vectors": { "manual": [-1.2, -2.3, 3.2] }},
+      {"id": 1, "name": "echo", "_vectors": { "manual": [2.5, 1.5, -130] }},
+    ]);
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await.succeeded();
+
+    // Make sure the documents are binary quantized
+    let (documents, _code) = index
+        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
+        .await;
+    snapshot!(json_string!(documents), @r###"
+    {
+      "results": [
+        {
+          "id": 0,
+          "name": "kefir",
+          "_vectors": {
+            "manual": {
+              "embeddings": [
+                [
+                  -1.0,
+                  -1.0,
+                  1.0
+                ]
+              ],
+              "regenerate": false
+            }
+          }
+        },
+        {
+          "id": 1,
+          "name": "echo",
+          "_vectors": {
+            "manual": {
+              "embeddings": [
+                [
+                  1.0,
+                  1.0,
+                  -1.0
+                ]
+              ],
+              "regenerate": false
+            }
+          }
+        }
+      ],
+      "offset": 0,
+      "limit": 20,
+      "total": 2
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn binary_quantize_after_sending_documents() {
+    let server = Server::new().await;
+    let index = server.index("doggo");
+    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(value, @r###"
+    {
+      "vectorStore": true,
+      "metrics": false,
+      "logsRoute": false,
+      "editDocumentsByFunction": false,
+      "containsFilter": false
+    }
+    "###);
+
+    let (response, code) = index
+        .update_settings(json!({
+          "embedders": {
+              "manual": {
+                  "source": "userProvided",
+                  "dimensions": 3,
+              }
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await.succeeded();
+
+    let documents = json!([
+      {"id": 0, "name": "kefir", "_vectors": { "manual": [-1.2, -2.3, 3.2] }},
+      {"id": 1, "name": "echo", "_vectors": { "manual": [2.5, 1.5, -130] }},
+    ]);
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await.succeeded();
+
+    let (response, code) = index
+        .update_settings(json!({
+          "embedders": {
+              "manual": {
+                  "source": "userProvided",
+                  "dimensions": 3,
+                  "binaryQuantized": true,
+              }
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await.succeeded();
+
+    // Make sure the documents are binary quantized
+    let (documents, _code) = index
+        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
+        .await;
+    snapshot!(json_string!(documents), @r###"
+    {
+      "results": [
+        {
+          "id": 0,
+          "name": "kefir",
+          "_vectors": {
+            "manual": {
+              "embeddings": [
+                [
+                  -1.0,
+                  -1.0,
+                  1.0
+                ]
+              ],
+              "regenerate": false
+            }
+          }
+        },
+        {
+          "id": 1,
+          "name": "echo",
+          "_vectors": {
+            "manual": {
+              "embeddings": [
+                [
+                  1.0,
+                  1.0,
+                  -1.0
+                ]
+              ],
+              "regenerate": false
+            }
+          }
+        }
+      ],
+      "offset": 0,
+      "limit": 20,
+      "total": 2
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn try_to_disable_binary_quantization() {
+    let server = Server::new().await;
+    let index = server.index("doggo");
+    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(value, @r###"
+    {
+      "vectorStore": true,
+      "metrics": false,
+      "logsRoute": false,
+      "editDocumentsByFunction": false,
+      "containsFilter": false
+    }
+    "###);
+
+    let (response, code) = index
+        .update_settings(json!({
+          "embedders": {
+              "manual": {
+                  "source": "userProvided",
+                  "dimensions": 3,
+                  "binaryQuantized": true,
+              }
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await.succeeded();
+
+    let (response, code) = index
+        .update_settings(json!({
+          "embedders": {
+              "manual": {
+                  "source": "userProvided",
+                  "dimensions": 3,
+                  "binaryQuantized": false,
+              }
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    let ret = server.wait_task(response.uid()).await;
+    snapshot!(ret, @r###"
+    {
+      "uid": "[uid]",
+      "indexUid": "doggo",
+      "status": "failed",
+      "type": "settingsUpdate",
+      "canceledBy": null,
+      "details": {
+        "embedders": {
+          "manual": {
+            "source": "userProvided",
+            "dimensions": 3,
+            "binaryQuantized": false
+          }
+        }
+      },
+      "error": {
+        "message": "`.embedders.manual.binaryQuantized`: Cannot disable the binary quantization.\n - Note: Binary quantization is a lossy operation that cannot be reverted.\n - Hint: Add a new embedder that is non-quantized and regenerate the vectors.",
+        "code": "invalid_settings_embedders",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
+      },
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn binary_quantize_clear_documents() {
+    let server = Server::new().await;
+    let index = generate_default_user_provided_documents(&server).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+          "embedders": {
+              "manual": {
+                  "binaryQuantized": true,
+              }
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await.succeeded();
+
+    let (value, _code) = index.clear_all_documents().await;
+    index.wait_task(value.uid()).await.succeeded();
+
+    // Make sure the documents DB has been cleared
+    let (documents, _code) = index
+        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
+        .await;
+    snapshot!(json_string!(documents), @r###"
+    {
+      "results": [],
+      "offset": 0,
+      "limit": 20,
+      "total": 0
+    }
+    "###);
+
+    // Make sure the arroy DB has been cleared
+    let (documents, _code) =
+        index.search_post(json!({ "hybrid": { "embedder": "manual" }, "vector": [1, 1, 1] })).await;
+    snapshot!(documents, @r###"
+    {
+      "hits": [],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 0,
+      "semanticHitCount": 0
+    }
+    "###);
+}

meilisearch/tests/vector/mod.rs

@@ -1,11 +1,15 @@
+mod binary_quantized;
 mod openai;
 mod rest;
 mod settings;
 
+use std::str::FromStr;
+
 use meili_snap::{json_string, snapshot};
+use meilisearch::option::MaxThreads;
 
 use crate::common::index::Index;
-use crate::common::{GetAllDocumentsOptions, Server};
+use crate::common::{default_settings, GetAllDocumentsOptions, Server};
 use crate::json;
 
 async fn get_server_vector() -> Server {
@@ -503,7 +507,11 @@ async fn user_provided_embeddings_error() {
 
 #[actix_rt::test]
 async fn user_provided_vectors_error() {
-    let server = Server::new().await;
+    let temp = tempfile::tempdir().unwrap();
+    let mut options = default_settings(temp.path());
+    // If we have more than one indexing thread the error messages below may become inconsistent
+    options.indexer_options.max_indexing_threads = MaxThreads::from_str("1").unwrap();
+    let server = Server::new_with_options(options).await.unwrap();
 
     let index = generate_default_user_provided_documents(&server).await;
 
@@ -617,7 +625,8 @@ async fn clear_documents() {
     "###);
 
     // Make sure the arroy DB has been cleared
-    let (documents, _code) = index.search_post(json!({ "vector": [1, 1, 1] })).await;
+    let (documents, _code) =
+        index.search_post(json!({ "vector": [1, 1, 1], "hybrid": {"embedder": "manual"} })).await;
     snapshot!(documents, @r###"
     {
       "hits": [],
@@ -678,7 +687,11 @@ async fn add_remove_one_vector_4588() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, name: "document-deleted");
 
-    let (documents, _code) = index.search_post(json!({"vector": [1, 1, 1] })).await;
+    let (documents, _code) = index
+        .search_post(
+            json!({"vector": [1, 1, 1], "hybrid": {"semanticRatio": 1.0, "embedder": "manual"} }),
+        )
+        .await;
     snapshot!(documents, @r###"
     {
       "hits": [

meilisearch/tests/vector/openai.rs

@@ -302,7 +302,8 @@ async fn create_mock_with_template(
         "source": "openAi",
         "url": url,
         "apiKey": API_KEY,
-        "documentTemplate": document_template
+        "documentTemplate": document_template,
+        "documentTemplateMaxBytes": 8000000,
     });
 
     model_dimensions.add_to_settings(&mut embedder_settings);
@@ -448,7 +449,7 @@ async fn it_works() {
     let (response, code) = index
         .search_post(json!({
             "q": "chien de chasse",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"},
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -488,7 +489,7 @@ async fn it_works() {
     let (response, code) = index
         .search_post(json!({
             "q": "petit chien",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -528,7 +529,7 @@ async fn it_works() {
     let (response, code) = index
         .search_post(json!({
             "q": "grand chien de berger des montagnes",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -615,7 +616,7 @@ async fn tokenize_long_text() {
             "q": "grand chien de berger des montagnes",
             "showRankingScore": true,
             "attributesToRetrieve": ["id"],
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -693,6 +694,7 @@ async fn bad_api_key() {
             "model": "text-embedding-3-large",
             "apiKey": "XXX...",
             "documentTemplate": "{%- if doc.gender == \"F\" -%}Une chienne nommée {{doc.name}}, née en {{doc.birthyear}}\n        {%- else -%}\n        Un chien nommé {{doc.name}}, né en {{doc.birthyear}}\n        {%- endif %}, de race {{doc.breed}}.",
+            "documentTemplateMaxBytes": 8000000,
             "url": "[url]"
           }
         }
@@ -735,6 +737,7 @@ async fn bad_api_key() {
             "source": "openAi",
             "model": "text-embedding-3-large",
             "documentTemplate": "{%- if doc.gender == \"F\" -%}Une chienne nommée {{doc.name}}, née en {{doc.birthyear}}\n        {%- else -%}\n        Un chien nommé {{doc.name}}, né en {{doc.birthyear}}\n        {%- endif %}, de race {{doc.breed}}.",
+            "documentTemplateMaxBytes": 8000000,
             "url": "[url]"
           }
         }
@@ -1061,7 +1064,7 @@ async fn smaller_dimensions() {
     let (response, code) = index
         .search_post(json!({
             "q": "chien de chasse",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1101,7 +1104,7 @@ async fn smaller_dimensions() {
     let (response, code) = index
         .search_post(json!({
             "q": "petit chien",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1141,7 +1144,7 @@ async fn smaller_dimensions() {
     let (response, code) = index
         .search_post(json!({
             "q": "grand chien de berger des montagnes",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1292,7 +1295,7 @@ async fn small_embedding_model() {
     let (response, code) = index
         .search_post(json!({
             "q": "chien de chasse",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1332,7 +1335,7 @@ async fn small_embedding_model() {
     let (response, code) = index
         .search_post(json!({
             "q": "petit chien",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1372,7 +1375,7 @@ async fn small_embedding_model() {
     let (response, code) = index
         .search_post(json!({
             "q": "grand chien de berger des montagnes",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1522,7 +1525,7 @@ async fn legacy_embedding_model() {
     let (response, code) = index
         .search_post(json!({
             "q": "chien de chasse",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1562,7 +1565,7 @@ async fn legacy_embedding_model() {
     let (response, code) = index
         .search_post(json!({
             "q": "petit chien",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1602,7 +1605,7 @@ async fn legacy_embedding_model() {
     let (response, code) = index
         .search_post(json!({
             "q": "grand chien de berger des montagnes",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1753,7 +1756,7 @@ async fn it_still_works() {
     let (response, code) = index
         .search_post(json!({
             "q": "chien de chasse",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1793,7 +1796,7 @@ async fn it_still_works() {
     let (response, code) = index
         .search_post(json!({
             "q": "petit chien",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");
@@ -1833,7 +1836,7 @@ async fn it_still_works() {
     let (response, code) = index
         .search_post(json!({
             "q": "grand chien de berger des montagnes",
-            "hybrid": {"semanticRatio": 1.0}
+            "hybrid": {"semanticRatio": 1.0, "embedder": "default"}
         }))
         .await;
     snapshot!(code, @"200 OK");

meilisearch/tests/vector/rest.rs

@@ -1,3 +1,4 @@
+use std::collections::BTreeMap;
 use std::sync::atomic::{AtomicUsize, Ordering};
 
 use meili_snap::{json_string, snapshot};
@@ -37,6 +38,46 @@ async fn create_mock() -> (MockServer, Value) {
     (mock_server, embedder_settings)
 }
 
+async fn create_mock_map() -> (MockServer, Value) {
+    let mock_server = MockServer::start().await;
+
+    let text_to_embedding: BTreeMap<_, _> = vec![
+        // text -> embedding
+        ("name: kefir\n", [0.0, 0.1, 0.2]),
+    ]
+    // turn into btree
+    .into_iter()
+    .collect();
+
+    Mock::given(method("POST"))
+        .and(path("/"))
+        .respond_with(move |req: &Request| {
+            let text: String = req.body_json().unwrap();
+            match text_to_embedding.get(text.as_str()) {
+                Some(embedding) => {
+                    ResponseTemplate::new(200).set_body_json(json!({ "data": embedding }))
+                }
+                None => ResponseTemplate::new(404)
+                    .set_body_json(json!({"error": "text not found", "text": text})),
+            }
+        })
+        .mount(&mock_server)
+        .await;
+    let url = mock_server.uri();
+
+    let embedder_settings = json!({
+        "source": "rest",
+        "url": url,
+        "dimensions": 3,
+        "request": "{{text}}",
+        "response": {
+          "data": "{{embedding}}"
+        }
+    });
+
+    (mock_server, embedder_settings)
+}
+
 #[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
 struct MultipleRequest {
     input: Vec<String>,
@@ -1100,6 +1141,7 @@ async fn server_returns_bad_request() {
 
     let (response, code) = index
         .update_settings(json!({
+          "searchableAttributes": ["name", "missing_field"],
           "embedders": {
               "rest": json!({ "source": "rest", "url": mock.uri(), "request": "{{text}}", "response": "{{embedding}}", "dimensions": 3 }),
           },
@@ -1115,6 +1157,10 @@ async fn server_returns_bad_request() {
       "type": "settingsUpdate",
       "canceledBy": null,
       "details": {
+        "searchableAttributes": [
+          "name",
+          "missing_field"
+        ],
         "embedders": {
           "rest": {
             "source": "rest",
@@ -1148,7 +1194,7 @@ async fn server_returns_bad_request() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `rest`: user error: sent a bad request to embedding server\n  - Hint: check that the `request` in the embedder configuration matches the remote server's API\n  - server replied with `{\"error\":\"Invalid request: invalid type: string \\\" id: 1\\\\n name: kefir\\\\n\\\", expected struct MultipleRequest at line 1 column 24\"}`",
+        "message": "While embedding documents for embedder `rest`: user error: sent a bad request to embedding server\n  - Hint: check that the `request` in the embedder configuration matches the remote server's API\n  - server replied with `{\"error\":\"Invalid request: invalid type: string \\\"name: kefir\\\\n\\\", expected struct MultipleRequest at line 1 column 15\"}`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1891,3 +1937,109 @@ async fn server_custom_header() {
     }
     "###);
 }
+
+#[actix_rt::test]
+async fn searchable_reindex() {
+    let (_mock, setting) = create_mock_map().await;
+    let server = get_server_vector().await;
+    let index = server.index("doggo");
+
+    let (response, code) = index
+        .update_settings(json!({
+          "searchableAttributes": ["name", "missing_field"],
+          "embedders": {
+              "rest": setting,
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    let task = server.wait_task(response.uid()).await;
+    snapshot!(task, @r###"
+    {
+      "uid": "[uid]",
+      "indexUid": "doggo",
+      "status": "succeeded",
+      "type": "settingsUpdate",
+      "canceledBy": null,
+      "details": {
+        "searchableAttributes": [
+          "name",
+          "missing_field"
+        ],
+        "embedders": {
+          "rest": {
+            "source": "rest",
+            "dimensions": 3,
+            "url": "[url]",
+            "request": "{{text}}",
+            "response": {
+              "data": "{{embedding}}"
+            }
+          }
+        }
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    let (response, code) =
+        index.add_documents(json!( { "id": 1, "name": "kefir", "breed": "patou" }), None).await;
+    snapshot!(code, @"202 Accepted");
+    let task = server.wait_task(response.uid()).await;
+    snapshot!(task, @r###"
+    {
+      "uid": "[uid]",
+      "indexUid": "doggo",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    // triggers reindexing with the new searchable attribute.
+    // as the mock intentionally doesn't know of this text, the task will fail, outputting the putative rendered text.
+    let (response, code) = index
+        .update_settings(json!({
+          "searchableAttributes": ["breed"],
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    let task = server.wait_task(response.uid()).await;
+    snapshot!(task, @r###"
+    {
+      "uid": "[uid]",
+      "indexUid": "doggo",
+      "status": "failed",
+      "type": "settingsUpdate",
+      "canceledBy": null,
+      "details": {
+        "searchableAttributes": [
+          "breed"
+        ]
+      },
+      "error": {
+        "message": "While embedding documents for embedder `rest`: error: received unexpected HTTP 404 from embedding server\n  - server replied with `{\"error\":\"text not found\",\"text\":\"breed: patou\\n\"}`",
+        "code": "vector_embedding_error",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
+      },
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+}

meilisearch/tests/vector/settings.rs

@@ -218,7 +218,8 @@ async fn reset_embedder_documents() {
     "###);
 
     // Make sure the arroy DB has been cleared
-    let (documents, _code) = index.search_post(json!({ "vector": [1, 1, 1] })).await;
+    let (documents, _code) =
+        index.search_post(json!({ "vector": [1, 1, 1], "hybrid": {"embedder": "default"} })).await;
     snapshot!(json_string!(documents), @r###"
     {
       "message": "Cannot find embedder with name `default`.",

meilitool/Cargo.toml

@@ -15,5 +15,6 @@ dump = { path = "../dump" }
 file-store = { path = "../file-store" }
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
+serde = { version = "1.0.209", features = ["derive"] }
 time = { version = "0.3.36", features = ["formatting"] }
 uuid = { version = "1.10.0", features = ["v4"], default-features = false }

meilitool/src/main.rs

@@ -2,7 +2,7 @@ use std::fs::{read_dir, read_to_string, remove_file, File};
 use std::io::BufWriter;
 use std::path::PathBuf;
 
-use anyhow::Context;
+use anyhow::{bail, Context};
 use clap::{Parser, Subcommand};
 use dump::{DumpWriter, IndexMetadata};
 use file_store::FileStore;
@@ -10,9 +10,10 @@ use meilisearch_auth::AuthController;
 use meilisearch_types::heed::types::{SerdeJson, Str};
 use meilisearch_types::heed::{Database, Env, EnvOpenOptions, RoTxn, RwTxn, Unspecified};
 use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader};
+use meilisearch_types::milli::index::{db_name, main_key};
 use meilisearch_types::milli::{obkv_to_json, BEU32};
 use meilisearch_types::tasks::{Status, Task};
-use meilisearch_types::versioning::check_version_file;
+use meilisearch_types::versioning::{create_version_file, get_version, parse_version};
 use meilisearch_types::Index;
 use time::macros::format_description;
 use time::OffsetDateTime;
@@ -62,21 +63,458 @@ enum Command {
         #[arg(long)]
         skip_enqueued_tasks: bool,
     },
+
+    /// Attempts to upgrade from one major version to the next without a dump.
+    ///
+    /// Make sure to run this commmand when Meilisearch is not running!
+    /// If Meilisearch is running while executing this command, the database could be corrupted
+    /// (contain data from both the old and the new versions)
+    ///
+    /// Supported upgrade paths:
+    ///
+    /// - v1.9.0 -> v1.10.0
+    OfflineUpgrade {
+        #[arg(long)]
+        target_version: String,
+    },
 }
 
 fn main() -> anyhow::Result<()> {
     let Cli { db_path, command } = Cli::parse();
 
-    check_version_file(&db_path).context("While checking the version file")?;
+    let detected_version = get_version(&db_path).context("While checking the version file")?;
 
     match command {
         Command::ClearTaskQueue => clear_task_queue(db_path),
         Command::ExportADump { dump_dir, skip_enqueued_tasks } => {
             export_a_dump(db_path, dump_dir, skip_enqueued_tasks)
         }
+        Command::OfflineUpgrade { target_version } => {
+            let target_version = parse_version(&target_version).context("While parsing `--target-version`. Make sure `--target-version` is in the format MAJOR.MINOR.PATCH")?;
+            OfflineUpgrade { db_path, current_version: detected_version, target_version }.upgrade()
+        }
     }
 }
 
+struct OfflineUpgrade {
+    db_path: PathBuf,
+    current_version: (String, String, String),
+    target_version: (String, String, String),
+}
+
+impl OfflineUpgrade {
+    fn upgrade(self) -> anyhow::Result<()> {
+        // TODO: if we make this process support more versions, introduce a more flexible way of checking for the version
+        // currently only supports v1.9 to v1.10
+        let (current_major, current_minor, current_patch) = &self.current_version;
+
+        match (current_major.as_str(), current_minor.as_str(), current_patch.as_str()) {
+            ("1", "9", _) => {}
+            _ => {
+                bail!("Unsupported current version {current_major}.{current_minor}.{current_patch}. Can only upgrade from v1.9")
+            }
+        }
+
+        let (target_major, target_minor, target_patch) = &self.target_version;
+
+        match (target_major.as_str(), target_minor.as_str(), target_patch.as_str()) {
+            ("1", "10", _) => {}
+            _ => {
+                bail!("Unsupported target version {target_major}.{target_minor}.{target_patch}. Can only upgrade to v1.10")
+            }
+        }
+
+        println!("Upgrading from {current_major}.{current_minor}.{current_patch} to {target_major}.{target_minor}.{target_patch}");
+
+        self.v1_9_to_v1_10()?;
+
+        println!("Writing VERSION file");
+
+        create_version_file(&self.db_path, target_major, target_minor, target_patch)
+            .context("while writing VERSION file after the upgrade")?;
+
+        println!("Success");
+
+        Ok(())
+    }
+
+    fn v1_9_to_v1_10(&self) -> anyhow::Result<()> {
+        // 2 changes here
+
+        // 1. date format. needs to be done before opening the Index
+        // 2. REST embedders. We don't support this case right now, so bail
+
+        let index_scheduler_path = self.db_path.join("tasks");
+        let env = unsafe { EnvOpenOptions::new().max_dbs(100).open(&index_scheduler_path) }
+            .with_context(|| {
+                format!("While trying to open {:?}", index_scheduler_path.display())
+            })?;
+
+        let mut sched_wtxn = env.write_txn()?;
+
+        let index_mapping: Database<Str, UuidCodec> =
+            try_opening_database(&env, &sched_wtxn, "index-mapping")?;
+
+        let index_stats: Database<UuidCodec, Unspecified> =
+            try_opening_database(&env, &sched_wtxn, "index-stats").with_context(|| {
+                format!("While trying to open {:?}", index_scheduler_path.display())
+            })?;
+
+        let index_count =
+            index_mapping.len(&sched_wtxn).context("while reading the number of indexes")?;
+
+        // FIXME: not ideal, we have to pre-populate all indexes to prevent double borrow of sched_wtxn
+        // 1. immutably for the iteration
+        // 2. mutably for updating index stats
+        let indexes: Vec<_> = index_mapping
+            .iter(&sched_wtxn)?
+            .map(|res| res.map(|(uid, uuid)| (uid.to_owned(), uuid)))
+            .collect();
+
+        let mut rest_embedders = Vec::new();
+
+        let mut unwrapped_indexes = Vec::new();
+
+        // check that update can take place
+        for (index_index, result) in indexes.into_iter().enumerate() {
+            let (uid, uuid) = result?;
+            let index_path = self.db_path.join("indexes").join(uuid.to_string());
+
+            println!(
+                "[{}/{index_count}]Checking that update can take place for  `{uid}` at `{}`",
+                index_index + 1,
+                index_path.display()
+            );
+
+            let index_env = unsafe {
+                // FIXME: fetch the 25 magic number from the index file
+                EnvOpenOptions::new().max_dbs(25).open(&index_path).with_context(|| {
+                    format!("while opening index {uid} at '{}'", index_path.display())
+                })?
+            };
+
+            let index_txn = index_env.read_txn().with_context(|| {
+                format!(
+                    "while obtaining a write transaction for index {uid} at {}",
+                    index_path.display()
+                )
+            })?;
+
+            println!("\t- Checking for incompatible embedders (REST embedders)");
+            let rest_embedders_for_index = find_rest_embedders(&uid, &index_env, &index_txn)?;
+
+            if rest_embedders_for_index.is_empty() {
+                unwrapped_indexes.push((uid, uuid));
+            } else {
+                // no need to add to unwrapped indexes because we'll exit early
+                rest_embedders.push((uid, rest_embedders_for_index));
+            }
+        }
+
+        if !rest_embedders.is_empty() {
+            let rest_embedders = rest_embedders
+                .into_iter()
+                .flat_map(|(index, embedders)| std::iter::repeat(index.clone()).zip(embedders))
+                .map(|(index, embedder)| format!("\t- embedder `{embedder}` in index `{index}`"))
+                .collect::<Vec<_>>()
+                .join("\n");
+            bail!("The update cannot take place because there are REST embedder(s). Remove them before proceeding with the update:\n{rest_embedders}\n\n\
+            The database has not been modified and is still a valid v1.9 database.");
+        }
+
+        println!("Update can take place, updating");
+
+        for (index_index, (uid, uuid)) in unwrapped_indexes.into_iter().enumerate() {
+            let index_path = self.db_path.join("indexes").join(uuid.to_string());
+
+            println!(
+                "[{}/{index_count}]Updating index `{uid}` at `{}`",
+                index_index + 1,
+                index_path.display()
+            );
+
+            let index_env = unsafe {
+                // FIXME: fetch the 25 magic number from the index file
+                EnvOpenOptions::new().max_dbs(25).open(&index_path).with_context(|| {
+                    format!("while opening index {uid} at '{}'", index_path.display())
+                })?
+            };
+
+            let mut index_wtxn = index_env.write_txn().with_context(|| {
+                format!(
+                    "while obtaining a write transaction for index `{uid}` at `{}`",
+                    index_path.display()
+                )
+            })?;
+
+            println!("\t- Updating index stats");
+            update_index_stats(index_stats, &uid, uuid, &mut sched_wtxn)?;
+            println!("\t- Updating date format");
+            update_date_format(&uid, &index_env, &mut index_wtxn)?;
+
+            index_wtxn.commit().with_context(|| {
+                format!(
+                    "while committing the write txn for index `{uid}` at {}",
+                    index_path.display()
+                )
+            })?;
+        }
+
+        sched_wtxn.commit().context("while committing the write txn for the index-scheduler")?;
+
+        println!("Upgrading database succeeded");
+
+        Ok(())
+    }
+}
+
+pub mod v1_9 {
+    pub type FieldDistribution = std::collections::BTreeMap<String, u64>;
+
+    /// The statistics that can be computed from an `Index` object.
+    #[derive(serde::Serialize, serde::Deserialize, Debug)]
+    pub struct IndexStats {
+        /// Number of documents in the index.
+        pub number_of_documents: u64,
+        /// Size taken up by the index' DB, in bytes.
+        ///
+        /// This includes the size taken by both the used and free pages of the DB, and as the free pages
+        /// are not returned to the disk after a deletion, this number is typically larger than
+        /// `used_database_size` that only includes the size of the used pages.
+        pub database_size: u64,
+        /// Size taken by the used pages of the index' DB, in bytes.
+        ///
+        /// As the DB backend does not return to the disk the pages that are not currently used by the DB,
+        /// this value is typically smaller than `database_size`.
+        pub used_database_size: u64,
+        /// Association of every field name with the number of times it occurs in the documents.
+        pub field_distribution: FieldDistribution,
+        /// Creation date of the index.
+        pub created_at: time::OffsetDateTime,
+        /// Date of the last update of the index.
+        pub updated_at: time::OffsetDateTime,
+    }
+
+    use serde::{Deserialize, Serialize};
+
+    #[derive(Debug, Deserialize, Serialize)]
+    pub struct IndexEmbeddingConfig {
+        pub name: String,
+        pub config: EmbeddingConfig,
+    }
+
+    #[derive(Debug, Clone, Default, serde::Deserialize, serde::Serialize)]
+    pub struct EmbeddingConfig {
+        /// Options of the embedder, specific to each kind of embedder
+        pub embedder_options: EmbedderOptions,
+    }
+
+    /// Options of an embedder, specific to each kind of embedder.
+    #[derive(Debug, Clone, Hash, PartialEq, Eq, serde::Deserialize, serde::Serialize)]
+    pub enum EmbedderOptions {
+        HuggingFace(hf::EmbedderOptions),
+        OpenAi(openai::EmbedderOptions),
+        Ollama(ollama::EmbedderOptions),
+        UserProvided(manual::EmbedderOptions),
+        Rest(rest::EmbedderOptions),
+    }
+
+    impl Default for EmbedderOptions {
+        fn default() -> Self {
+            Self::OpenAi(openai::EmbedderOptions { api_key: None, dimensions: None })
+        }
+    }
+
+    mod hf {
+        #[derive(Debug, Clone, Hash, PartialEq, Eq, serde::Deserialize, serde::Serialize)]
+        pub struct EmbedderOptions {
+            pub model: String,
+            pub revision: Option<String>,
+        }
+    }
+    mod openai {
+
+        #[derive(Debug, Clone, Hash, PartialEq, Eq, serde::Deserialize, serde::Serialize)]
+        pub struct EmbedderOptions {
+            pub api_key: Option<String>,
+            pub dimensions: Option<usize>,
+        }
+    }
+    mod ollama {
+        #[derive(Debug, Clone, Hash, PartialEq, Eq, serde::Deserialize, serde::Serialize)]
+        pub struct EmbedderOptions {
+            pub embedding_model: String,
+            pub url: Option<String>,
+            pub api_key: Option<String>,
+        }
+    }
+    mod manual {
+        #[derive(Debug, Clone, Hash, PartialEq, Eq, serde::Deserialize, serde::Serialize)]
+        pub struct EmbedderOptions {
+            pub dimensions: usize,
+        }
+    }
+    mod rest {
+        #[derive(Debug, Clone, PartialEq, Eq, serde::Deserialize, serde::Serialize, Hash)]
+        pub struct EmbedderOptions {
+            pub api_key: Option<String>,
+            pub dimensions: Option<usize>,
+            pub url: String,
+            pub input_field: Vec<String>,
+            // path to the array of embeddings
+            pub path_to_embeddings: Vec<String>,
+            // shape of a single embedding
+            pub embedding_object: Vec<String>,
+        }
+    }
+
+    pub type OffsetDateTime = time::OffsetDateTime;
+}
+
+pub mod v1_10 {
+    use crate::v1_9;
+
+    pub type FieldDistribution = std::collections::BTreeMap<String, u64>;
+
+    /// The statistics that can be computed from an `Index` object.
+    #[derive(serde::Serialize, serde::Deserialize, Debug)]
+    pub struct IndexStats {
+        /// Number of documents in the index.
+        pub number_of_documents: u64,
+        /// Size taken up by the index' DB, in bytes.
+        ///
+        /// This includes the size taken by both the used and free pages of the DB, and as the free pages
+        /// are not returned to the disk after a deletion, this number is typically larger than
+        /// `used_database_size` that only includes the size of the used pages.
+        pub database_size: u64,
+        /// Size taken by the used pages of the index' DB, in bytes.
+        ///
+        /// As the DB backend does not return to the disk the pages that are not currently used by the DB,
+        /// this value is typically smaller than `database_size`.
+        pub used_database_size: u64,
+        /// 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: time::OffsetDateTime,
+        /// Date of the last update of the index.
+        #[serde(with = "time::serde::rfc3339")]
+        pub updated_at: time::OffsetDateTime,
+    }
+
+    impl From<v1_9::IndexStats> for IndexStats {
+        fn from(
+            v1_9::IndexStats {
+                number_of_documents,
+                database_size,
+                used_database_size,
+                field_distribution,
+                created_at,
+                updated_at,
+            }: v1_9::IndexStats,
+        ) -> Self {
+            IndexStats {
+                number_of_documents,
+                database_size,
+                used_database_size,
+                field_distribution,
+                created_at,
+                updated_at,
+            }
+        }
+    }
+
+    #[derive(serde::Serialize, serde::Deserialize)]
+    #[serde(transparent)]
+    pub struct OffsetDateTime(#[serde(with = "time::serde::rfc3339")] pub time::OffsetDateTime);
+}
+
+fn update_index_stats(
+    index_stats: Database<UuidCodec, Unspecified>,
+    index_uid: &str,
+    index_uuid: uuid::Uuid,
+    sched_wtxn: &mut RwTxn,
+) -> anyhow::Result<()> {
+    let ctx = || format!("while updating index stats for index `{index_uid}`");
+
+    let stats: Option<v1_9::IndexStats> = index_stats
+        .remap_data_type::<SerdeJson<v1_9::IndexStats>>()
+        .get(sched_wtxn, &index_uuid)
+        .with_context(ctx)?;
+
+    if let Some(stats) = stats {
+        let stats: v1_10::IndexStats = stats.into();
+
+        index_stats
+            .remap_data_type::<SerdeJson<v1_10::IndexStats>>()
+            .put(sched_wtxn, &index_uuid, &stats)
+            .with_context(ctx)?;
+    }
+
+    Ok(())
+}
+
+fn update_date_format(
+    index_uid: &str,
+    index_env: &Env,
+    index_wtxn: &mut RwTxn,
+) -> anyhow::Result<()> {
+    let main = try_opening_poly_database(index_env, index_wtxn, db_name::MAIN)
+        .with_context(|| format!("while updating date format for index `{index_uid}`"))?;
+
+    date_round_trip(index_wtxn, index_uid, main, main_key::CREATED_AT_KEY)?;
+    date_round_trip(index_wtxn, index_uid, main, main_key::UPDATED_AT_KEY)?;
+
+    Ok(())
+}
+
+fn find_rest_embedders(
+    index_uid: &str,
+    index_env: &Env,
+    index_txn: &RoTxn,
+) -> anyhow::Result<Vec<String>> {
+    let main = try_opening_poly_database(index_env, index_txn, db_name::MAIN)
+        .with_context(|| format!("while checking REST embedders for index `{index_uid}`"))?;
+
+    let mut rest_embedders = vec![];
+
+    for config in main
+        .remap_types::<Str, SerdeJson<Vec<v1_9::IndexEmbeddingConfig>>>()
+        .get(index_txn, main_key::EMBEDDING_CONFIGS)?
+        .unwrap_or_default()
+    {
+        if let v1_9::EmbedderOptions::Rest(_) = config.config.embedder_options {
+            rest_embedders.push(config.name);
+        }
+    }
+
+    Ok(rest_embedders)
+}
+
+fn date_round_trip(
+    wtxn: &mut RwTxn,
+    index_uid: &str,
+    db: Database<Unspecified, Unspecified>,
+    key: &str,
+) -> anyhow::Result<()> {
+    let datetime =
+        db.remap_types::<Str, SerdeJson<v1_9::OffsetDateTime>>().get(wtxn, key).with_context(
+            || format!("could not read `{key}` while updating date format for index `{index_uid}`"),
+        )?;
+
+    if let Some(datetime) = datetime {
+        db.remap_types::<Str, SerdeJson<v1_10::OffsetDateTime>>()
+            .put(wtxn, key, &v1_10::OffsetDateTime(datetime))
+            .with_context(|| {
+                format!(
+                    "could not write `{key}` while updating date format for index `{index_uid}`"
+                )
+            })?;
+    }
+
+    Ok(())
+}
+
 /// Clears the task queue located at `db_path`.
 fn clear_task_queue(db_path: PathBuf) -> anyhow::Result<()> {
     let path = db_path.join("tasks");
@@ -244,7 +682,7 @@ fn export_a_dump(
                         format!("While iterating on content file {:?}", content_file_uuid)
                     })? {
                         dump_content_file
-                            .push_document(&obkv_to_object(&doc, &documents_batch_index)?)?;
+                            .push_document(&obkv_to_object(doc, &documents_batch_index)?)?;
                     }
                     dump_content_file.flush()?;
                     count += 1;

milli/Cargo.toml

@@ -12,12 +12,14 @@ readme.workspace = true
 license.workspace = true
 
 [dependencies]
+big_s = "1.0.2"
 bimap = { version = "0.6.3", features = ["serde"] }
 bincode = "1.3.3"
 bstr = "1.9.1"
 bytemuck = { version = "1.16.1", features = ["extern_crate_alloc"] }
 byteorder = "1.5.0"
-charabia = { version = "0.9.0", default-features = false }
+# charabia = { version = "0.9.0", default-features = false }
+charabia = { git = "https://github.com/meilisearch/charabia", branch = "mutualize-char-normalizer", default-features = false }
 concat-arrays = "0.1.2"
 crossbeam-channel = "0.5.13"
 deserr = "0.6.2"
@@ -27,9 +29,9 @@ fst = "0.4.7"
 fxhash = "0.2.1"
 geoutils = "0.5.1"
 grenad = { version = "0.4.7", default-features = false, features = [
-    "rayon",
-    "tempfile",
-] }
+    "rayon", # TODO Should we keep this feature
+    "tempfile"
+], git = "https://github.com/meilisearch/grenad", branch = "various-improvements" }
 heed = { version = "0.20.3", default-features = false, features = [
     "serde-json",
     "serde-bincode",
@@ -40,14 +42,14 @@ json-depth-checker = { path = "../json-depth-checker" }
 levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
 memchr = "2.5.0"
 memmap2 = "0.9.4"
-obkv = "0.2.2"
+obkv = { git = "https://github.com/kerollmops/obkv", branch = "unsized-kvreader" }
 once_cell = "1.19.0"
 ordered-float = "4.2.1"
 rayon = "1.10.0"
 roaring = { version = "0.10.6", features = ["serde"] }
 rstar = { version = "0.12.0", features = ["serde"] }
 serde = { version = "1.0.204", features = ["derive"] }
-serde_json = { version = "1.0.120", features = ["preserve_order"] }
+serde_json = { version = "1.0.120", features = ["preserve_order", "raw_value"] }
 slice-group-by = "0.3.1"
 smallstr = { version = "0.3.0", features = ["serde"] }
 smallvec = "1.13.2"
@@ -80,16 +82,16 @@ hf-hub = { git = "https://github.com/dureuill/hf-hub.git", branch = "rust_tls",
 tiktoken-rs = "0.5.9"
 liquid = "0.26.6"
 rhai = { version = "1.19.0", features = ["serde", "no_module", "no_custom_syntax", "no_time", "sync"] }
-arroy = "0.4.0"
+arroy = { git = "https://github.com/meilisearch/arroy/", rev = "2386594dfb009ce08821a925ccc89fb8e30bf73d" }
 rand = "0.8.5"
 tracing = "0.1.40"
 ureq = { version = "2.10.0", features = ["json"] }
 url = "2.5.2"
 rayon-par-bridge = "0.1.0"
+hashbrown = "0.14.5"
 
 [dev-dependencies]
 mimalloc = { version = "0.1.43", default-features = false }
-big_s = "1.0.2"
 insta = "1.39.0"
 maplit = "1.0.2"
 md5 = "0.7.0"
@@ -106,6 +108,8 @@ all-tokenizations = [
     "charabia/greek",
     "charabia/khmer",
     "charabia/vietnamese",
+    "charabia/swedish-recomposition",
+    "charabia/german-segmentation",
 ]
 
 # Use POSIX semaphores instead of SysV semaphores in LMDB
@@ -138,6 +142,9 @@ khmer = ["charabia/khmer"]
 # allow vietnamese specialized tokenization
 vietnamese = ["charabia/vietnamese"]
 
+# allow german specialized tokenization
+german = ["charabia/german-segmentation"]
+
 # force swedish character recomposition
 swedish-recomposition = ["charabia/swedish-recomposition"]
 

milli/src/documents/builder.rs

@@ -292,7 +292,7 @@ mod test {
             .unwrap()
             .into_cursor_and_fields_index();
         let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
+        let val = obkv_to_object(doc, &index).map(Value::from).unwrap();
 
         assert_eq!(
             val,
@@ -321,7 +321,7 @@ mod test {
             .into_cursor_and_fields_index();
 
         let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
+        let val = obkv_to_object(doc, &index).map(Value::from).unwrap();
 
         assert_eq!(
             val,
@@ -348,7 +348,7 @@ mod test {
             .into_cursor_and_fields_index();
 
         let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
+        let val = obkv_to_object(doc, &index).map(Value::from).unwrap();
 
         assert_eq!(
             val,
@@ -375,7 +375,7 @@ mod test {
             .into_cursor_and_fields_index();
 
         let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
+        let val = obkv_to_object(doc, &index).map(Value::from).unwrap();
 
         assert_eq!(
             val,
@@ -402,7 +402,7 @@ mod test {
             .into_cursor_and_fields_index();
 
         let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
+        let val = obkv_to_object(doc, &index).map(Value::from).unwrap();
 
         assert_eq!(
             val,
@@ -429,7 +429,7 @@ mod test {
             .into_cursor_and_fields_index();
 
         let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
+        let val = obkv_to_object(doc, &index).map(Value::from).unwrap();
 
         assert_eq!(
             val,
@@ -456,7 +456,7 @@ mod test {
             .into_cursor_and_fields_index();
 
         let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
+        let val = obkv_to_object(doc, &index).map(Value::from).unwrap();
 
         assert_eq!(
             val,
@@ -483,7 +483,7 @@ mod test {
             .into_cursor_and_fields_index();
 
         let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
+        let val = obkv_to_object(doc, &index).map(Value::from).unwrap();
 
         assert_eq!(
             val,
@@ -510,7 +510,7 @@ mod test {
             .into_cursor_and_fields_index();
 
         let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
+        let val = obkv_to_object(doc, &index).map(Value::from).unwrap();
 
         assert_eq!(
             val,
@@ -555,7 +555,7 @@ mod test {
             .into_cursor_and_fields_index();
 
         let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
+        let val = obkv_to_object(doc, &index).map(Value::from).unwrap();
 
         assert_eq!(
             val,

milli/src/documents/enriched.rs

@@ -69,7 +69,7 @@ impl<R: io::Read + io::Seek> EnrichedDocumentsBatchReader<R> {
 
 #[derive(Debug, Clone)]
 pub struct EnrichedDocument<'a> {
-    pub document: KvReader<'a, FieldId>,
+    pub document: &'a KvReader<FieldId>,
     pub document_id: DocumentId,
 }
 

milli/src/documents/mod.rs

@@ -27,7 +27,7 @@ use crate::{FieldId, Object, Result};
 const DOCUMENTS_BATCH_INDEX_KEY: [u8; 8] = u64::MAX.to_be_bytes();
 
 /// Helper function to convert an obkv reader into a JSON object.
-pub fn obkv_to_object(obkv: &KvReader<'_, FieldId>, index: &DocumentsBatchIndex) -> Result<Object> {
+pub fn obkv_to_object(obkv: &KvReader<FieldId>, index: &DocumentsBatchIndex) -> Result<Object> {
     obkv.iter()
         .map(|(field_id, value)| {
             let field_name = index
@@ -76,7 +76,7 @@ impl DocumentsBatchIndex {
         self.0.get_by_right(name).cloned()
     }
 
-    pub fn recreate_json(&self, document: &obkv::KvReaderU16<'_>) -> Result<Object> {
+    pub fn recreate_json(&self, document: &obkv::KvReaderU16) -> Result<Object> {
         let mut map = Object::new();
 
         for (k, v) in document.iter() {

milli/src/documents/primary_key.rs

@@ -1,8 +1,10 @@
+use std::borrow::Cow;
 use std::iter;
 use std::result::Result as StdResult;
 
-use serde_json::Value;
+use serde_json::{from_str, Value};
 
+use crate::update::new::{CowStr, TopLevelMap};
 use crate::{FieldId, InternalError, Object, Result, UserError};
 
 /// The symbol used to define levels in a nested primary key.
@@ -52,7 +54,7 @@ impl<'a> PrimaryKey<'a> {
 
     pub fn document_id(
         &self,
-        document: &obkv::KvReader<'_, FieldId>,
+        document: &obkv::KvReader<FieldId>,
         fields: &impl FieldIdMapper,
     ) -> Result<StdResult<String, DocumentIdExtractionError>> {
         match self {
@@ -100,6 +102,45 @@ impl<'a> PrimaryKey<'a> {
         }
     }
 
+    /// Returns the document ID based on the primary and
+    /// search for it recursively in zero-copy-deserialized documents.
+    pub fn document_id_from_top_level_map<'p>(
+        &self,
+        document: &TopLevelMap<'p>,
+    ) -> Result<StdResult<CowStr<'p>, DocumentIdExtractionError>> {
+        fn get_docid<'p>(
+            document: &TopLevelMap<'p>,
+            primary_key: &[&str],
+        ) -> Result<StdResult<CowStr<'p>, DocumentIdExtractionError>> {
+            match primary_key {
+                [] => unreachable!("arrrgh"), // would None be ok?
+                [primary_key] => match document.0.get(*primary_key) {
+                    Some(value) => match from_str::<u64>(value.get()) {
+                        Ok(value) => Ok(Ok(CowStr(Cow::Owned(value.to_string())))),
+                        Err(_) => match from_str(value.get()) {
+                            Ok(document_id) => Ok(Ok(document_id)),
+                            Err(e) => Ok(Err(DocumentIdExtractionError::InvalidDocumentId(
+                                UserError::SerdeJson(e),
+                            ))),
+                        },
+                    },
+                    None => Ok(Err(DocumentIdExtractionError::MissingDocumentId)),
+                },
+                [head, tail @ ..] => match document.0.get(*head) {
+                    Some(value) => {
+                        let document = from_str(value.get()).map_err(InternalError::SerdeJson)?;
+                        get_docid(&document, tail)
+                    }
+                    None => Ok(Err(DocumentIdExtractionError::MissingDocumentId)),
+                },
+            }
+        }
+
+        /// TODO do not allocate a vec everytime here
+        let primary_key: Vec<_> = self.name().split(PRIMARY_KEY_SPLIT_SYMBOL).collect();
+        get_docid(document, &primary_key)
+    }
+
     /// Returns an `Iterator` that gives all the possible fields names the primary key
     /// can have depending of the first level name and depth of the objects.
     pub fn possible_level_names(&self) -> impl Iterator<Item = (&str, &str)> + '_ {

milli/src/documents/reader.rs

@@ -72,15 +72,24 @@ impl<R> DocumentsBatchCursor<R> {
 }
 
 impl<R: io::Read + io::Seek> DocumentsBatchCursor<R> {
+    /// Returns a single document from the database.
+    pub fn get(
+        &mut self,
+        offset: u32,
+    ) -> Result<Option<&KvReader<FieldId>>, DocumentsBatchCursorError> {
+        match self.cursor.move_on_key_equal_to(offset.to_be_bytes())? {
+            Some((key, value)) if key != DOCUMENTS_BATCH_INDEX_KEY => Ok(Some(value.into())),
+            _otherwise => Ok(None),
+        }
+    }
+
     /// Returns the next document, starting from the first one. Subsequent calls to
     /// `next_document` advance the document reader until all the documents have been read.
     pub fn next_document(
         &mut self,
-    ) -> Result<Option<KvReader<'_, FieldId>>, DocumentsBatchCursorError> {
+    ) -> Result<Option<&KvReader<FieldId>>, DocumentsBatchCursorError> {
         match self.cursor.move_on_next()? {
-            Some((key, value)) if key != DOCUMENTS_BATCH_INDEX_KEY => {
-                Ok(Some(KvReader::new(value)))
-            }
+            Some((key, value)) if key != DOCUMENTS_BATCH_INDEX_KEY => Ok(Some(value.into())),
             _otherwise => Ok(None),
         }
     }

milli/src/error.rs

@@ -258,6 +258,12 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
     },
     #[error("`.embedders.{embedder_name}.dimensions`: `dimensions` cannot be zero")]
     InvalidSettingsDimensions { embedder_name: String },
+    #[error(
+        "`.embedders.{embedder_name}.binaryQuantized`: Cannot disable the binary quantization.\n - Note: Binary quantization is a lossy operation that cannot be reverted.\n - Hint: Add a new embedder that is non-quantized and regenerate the vectors."
+    )]
+    InvalidDisableBinaryQuantization { embedder_name: String },
+    #[error("`.embedders.{embedder_name}.documentTemplateMaxBytes`: `documentTemplateMaxBytes` cannot be zero")]
+    InvalidSettingsDocumentTemplateMaxBytes { embedder_name: String },
     #[error("`.embedders.{embedder_name}.url`: could not parse `{url}`: {inner_error}")]
     InvalidUrl { embedder_name: String, inner_error: url::ParseError, url: String },
     #[error("Document editions cannot modify a document's primary key")]

milli/src/fields_ids_map.rs

@@ -4,6 +4,9 @@ use serde::{Deserialize, Serialize};
 
 use crate::FieldId;
 
+mod global;
+pub use global::GlobalFieldsIdsMap;
+
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct FieldsIdsMap {
     names_ids: BTreeMap<String, FieldId>,

milli/src/fields_ids_map/global.rs

@@ -0,0 +1,86 @@
+use std::collections::BTreeMap;
+use std::sync::RwLock;
+
+use crate::{FieldId, FieldsIdsMap};
+
+/// A fields ids map that can be globally updated to add fields
+#[derive(Debug, Clone)]
+pub struct GlobalFieldsIdsMap<'indexing> {
+    global: &'indexing RwLock<FieldsIdsMap>,
+    local: LocalFieldsIdsMap,
+}
+
+#[derive(Debug, Clone)]
+struct LocalFieldsIdsMap {
+    names_ids: BTreeMap<String, FieldId>,
+    ids_names: BTreeMap<FieldId, String>,
+}
+
+impl LocalFieldsIdsMap {
+    fn new(global: &RwLock<FieldsIdsMap>) -> Self {
+        let global = global.read().unwrap();
+        Self { names_ids: global.names_ids.clone(), ids_names: global.ids_names.clone() }
+    }
+
+    fn insert(&mut self, name: &str, field_id: FieldId) {
+        self.names_ids.insert(name.to_owned(), field_id);
+        self.ids_names.insert(field_id, name.to_owned());
+    }
+
+    fn name(&self, id: FieldId) -> Option<&str> {
+        self.ids_names.get(&id).map(String::as_str)
+    }
+
+    fn id(&self, name: &str) -> Option<FieldId> {
+        self.names_ids.get(name).copied()
+    }
+}
+
+impl<'indexing> GlobalFieldsIdsMap<'indexing> {
+    pub fn new(global: &'indexing RwLock<FieldsIdsMap>) -> Self {
+        Self { local: LocalFieldsIdsMap::new(global), global }
+    }
+
+    /// Returns the field id related to a field name, it will create a new field id if the
+    /// name is not already known. Returns `None` if the maximum field id as been reached.
+    pub fn id_or_insert(&mut self, name: &str) -> Option<FieldId> {
+        if let Some(field_id) = self.local.id(name) {
+            return Some(field_id);
+        }
+
+        {
+            // optimistically lookup the global map
+            let global = self.global.read().unwrap();
+
+            if let Some(field_id) = global.id(name) {
+                self.local.insert(name, field_id);
+                return Some(field_id);
+            }
+        }
+
+        {
+            let mut global = self.global.write().unwrap();
+
+            if let Some(field_id) = global.id(name) {
+                self.local.insert(name, field_id);
+                return Some(field_id);
+            }
+
+            let field_id = global.insert(name)?;
+            self.local.insert(name, field_id);
+            Some(field_id)
+        }
+    }
+
+    /// Get the name of a field based on its id.
+    pub fn name(&mut self, id: FieldId) -> Option<&str> {
+        if self.local.name(id).is_none() {
+            let global = self.global.read().unwrap();
+
+            let name = global.name(id)?;
+            self.local.insert(name, id);
+        }
+
+        self.local.name(id)
+    }
+}

milli/src/heed_codec/obkv_codec.rs

@@ -6,10 +6,10 @@ use obkv::{KvReaderU16, KvWriterU16};
 pub struct ObkvCodec;
 
 impl<'a> heed::BytesDecode<'a> for ObkvCodec {
-    type DItem = KvReaderU16<'a>;
+    type DItem = &'a KvReaderU16;
 
     fn bytes_decode(bytes: &'a [u8]) -> Result<Self::DItem, BoxedError> {
-        Ok(KvReaderU16::new(bytes))
+        Ok(KvReaderU16::from_slice(bytes))
     }
 }
 

milli/src/heed_codec/roaring_bitmap/cbo_roaring_bitmap_codec.rs

@@ -122,7 +122,7 @@ impl CboRoaringBitmapCodec {
 
     /// Merges a DelAdd delta into a CboRoaringBitmap.
     pub fn merge_deladd_into<'a>(
-        deladd: KvReaderDelAdd<'_>,
+        deladd: &KvReaderDelAdd,
         previous: &[u8],
         buffer: &'a mut Vec<u8>,
     ) -> io::Result<Option<&'a [u8]>> {

milli/src/index.rs

@@ -21,7 +21,7 @@ use crate::heed_codec::{BEU16StrCodec, FstSetCodec, StrBEU16Codec, StrRefCodec};
 use crate::order_by_map::OrderByMap;
 use crate::proximity::ProximityPrecision;
 use crate::vector::parsed_vectors::RESERVED_VECTORS_FIELD_NAME;
-use crate::vector::{Embedding, EmbeddingConfig};
+use crate::vector::{ArroyWrapper, Embedding, EmbeddingConfig};
 use crate::{
     default_criteria, CboRoaringBitmapCodec, Criterion, DocumentId, ExternalDocumentsIds,
     FacetDistribution, FieldDistribution, FieldId, FieldIdMapMissingEntry, FieldIdWordCountCodec,
@@ -162,7 +162,7 @@ pub struct Index {
     /// Maps an embedder name to its id in the arroy store.
     pub embedder_category_id: Database<Str, U8>,
     /// Vector store based on arroy™.
-    pub vector_arroy: arroy::Database<arroy::distances::Angular>,
+    pub vector_arroy: arroy::Database<Unspecified>,
 
     /// Maps the document id to the document as an obkv store.
     pub(crate) documents: Database<BEU32, ObkvCodec>,
@@ -1251,12 +1251,20 @@ impl Index {
 
     /* documents */
 
+    /// Returns a document by using the document id.
+    pub fn document<'t>(&self, rtxn: &'t RoTxn, id: DocumentId) -> Result<&'t obkv::KvReaderU16> {
+        self.documents
+            .get(rtxn, &id)?
+            .ok_or(UserError::UnknownInternalDocumentId { document_id: id })
+            .map_err(Into::into)
+    }
+
     /// Returns an iterator over the requested documents. The next item will be an error if a document is missing.
     pub fn iter_documents<'a, 't: 'a>(
         &'a self,
         rtxn: &'t RoTxn<'t>,
         ids: impl IntoIterator<Item = DocumentId> + 'a,
-    ) -> Result<impl Iterator<Item = Result<(DocumentId, obkv::KvReaderU16<'t>)>> + 'a> {
+    ) -> Result<impl Iterator<Item = Result<(DocumentId, &'t obkv::KvReaderU16)>> + 'a> {
         Ok(ids.into_iter().map(move |id| {
             let kv = self
                 .documents
@@ -1271,7 +1279,7 @@ impl Index {
         &self,
         rtxn: &'t RoTxn<'t>,
         ids: impl IntoIterator<Item = DocumentId>,
-    ) -> Result<Vec<(DocumentId, obkv::KvReaderU16<'t>)>> {
+    ) -> Result<Vec<(DocumentId, &'t obkv::KvReaderU16)>> {
         self.iter_documents(rtxn, ids)?.collect()
     }
 
@@ -1279,7 +1287,7 @@ impl Index {
     pub fn all_documents<'a, 't: 'a>(
         &'a self,
         rtxn: &'t RoTxn<'t>,
-    ) -> Result<impl Iterator<Item = Result<(DocumentId, obkv::KvReaderU16<'t>)>> + 'a> {
+    ) -> Result<impl Iterator<Item = Result<(DocumentId, &'t obkv::KvReaderU16)>> + 'a> {
         self.iter_documents(rtxn, self.documents_ids(rtxn)?)
     }
 
@@ -1303,7 +1311,7 @@ impl Index {
         })?;
         Ok(self.iter_documents(rtxn, ids)?.map(move |entry| -> Result<_> {
             let (_docid, obkv) = entry?;
-            match primary_key.document_id(&obkv, &fields)? {
+            match primary_key.document_id(obkv, &fields)? {
                 Ok(document_id) => Ok(document_id),
                 Err(_) => Err(InternalError::DocumentsError(
                     crate::documents::Error::InvalidDocumentFormat,
@@ -1614,15 +1622,17 @@ impl Index {
         &'a self,
         rtxn: &'a RoTxn<'a>,
         embedder_id: u8,
-    ) -> impl Iterator<Item = Result<arroy::Reader<'a, arroy::distances::Angular>>> + 'a {
+        quantized: bool,
+    ) -> impl Iterator<Item = Result<ArroyWrapper>> + 'a {
         crate::vector::arroy_db_range_for_embedder(embedder_id).map_while(move |k| {
-            arroy::Reader::open(rtxn, k, self.vector_arroy)
-                .map(Some)
-                .or_else(|e| match e {
-                    arroy::Error::MissingMetadata(_) => Ok(None),
-                    e => Err(e.into()),
-                })
-                .transpose()
+            let reader = ArroyWrapper::new(self.vector_arroy, k, quantized);
+            // Here we don't care about the dimensions, but we want to know if we can read
+            // in the database or if its metadata are missing because there is no document with that many vectors.
+            match reader.dimensions(rtxn) {
+                Ok(_) => Some(Ok(reader)),
+                Err(arroy::Error::MissingMetadata(_)) => None,
+                Err(e) => Some(Err(e.into())),
+            }
         })
     }
 
@@ -1644,32 +1654,18 @@ impl Index {
         docid: DocumentId,
     ) -> Result<BTreeMap<String, Vec<Embedding>>> {
         let mut res = BTreeMap::new();
-        for row in self.embedder_category_id.iter(rtxn)? {
-            let (embedder_name, embedder_id) = row?;
-            let embedder_id = (embedder_id as u16) << 8;
-            let mut embeddings = Vec::new();
-            'vectors: for i in 0..=u8::MAX {
-                let reader = arroy::Reader::open(rtxn, embedder_id | (i as u16), self.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?.item_vector(rtxn, docid)?;
-                if let Some(embedding) = embedding {
-                    embeddings.push(embedding)
-                } else {
-                    break 'vectors;
-                }
-            }
-
-            res.insert(embedder_name.to_owned(), embeddings);
+        let embedding_configs = self.embedding_configs(rtxn)?;
+        for config in embedding_configs {
+            let embedder_id = self.embedder_category_id.get(rtxn, &config.name)?.unwrap();
+            let embeddings = self
+                .arroy_readers(rtxn, embedder_id, config.config.quantized())
+                .map_while(|reader| {
+                    reader
+                        .and_then(|r| r.item_vector(rtxn, docid).map_err(|e| e.into()))
+                        .transpose()
+                })
+                .collect::<Result<Vec<_>>>()?;
+            res.insert(config.name.to_owned(), embeddings);
         }
         Ok(res)
     }