Merge #5159

5159: Fix the New Indexer Spilling r=irevoire a=Kerollmops

Fix two bugs in the merging of the spilled caches. Thanks to `@ManyTheFish` and `@irevoire` 👏

Co-authored-by: Kerollmops <clement@meilisearch.com>
Co-authored-by: ManyTheFish <many@meilisearch.com>

Cargo.lock

@@ -80,7 +80,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e01ed3140b2f8d422c68afa1ed2e85d996ea619c988ac834d255db32138655cb"
 dependencies = [
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -216,7 +216,7 @@ dependencies = [
  "actix-router",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -296,9 +296,9 @@ dependencies = [
 
 [[package]]
 name = "allocator-api2"
-version = "0.2.16"
+version = "0.2.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0942ffc6dcaadf03badf6e6a2d0228460359d5e34b57ccdc720b7382dfbd5ec5"
+checksum = "5c6cb57a04249c6480766f7f7cef5467412af1490f8d1e243141daddada3264f"
 
 [[package]]
 name = "anes"
@@ -441,7 +441,7 @@ checksum = "6e0c28dcc82d7c8ead5cb13beb15405b57b8546e93215673ff8ca0349a028107"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -489,16 +489,23 @@ version = "0.22.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
+[[package]]
+name = "bbqueue"
+version = "0.5.1"
+source = "git+https://github.com/meilisearch/bbqueue#cbb87cc707b5af415ef203bdaf2443e06ba0d6d4"
+
 [[package]]
 name = "benchmarks"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "anyhow",
+ "bumpalo",
  "bytes",
  "convert_case 0.6.0",
  "criterion",
  "csv",
  "flate2",
+ "memmap2",
  "milli",
  "mimalloc",
  "rand",
@@ -506,6 +513,7 @@ dependencies = [
  "reqwest",
  "roaring",
  "serde_json",
+ "tempfile",
 ]
 
 [[package]]
@@ -549,7 +557,7 @@ dependencies = [
  "regex",
  "rustc-hash 1.1.0",
  "shlex",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -593,6 +601,15 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "bitpacking"
+version = "0.9.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4c1d3e2bfd8d06048a179f7b17afc3188effa10385e7b00dc65af6aae732ea92"
+dependencies = [
+ "crunchy",
+]
+
 [[package]]
 name = "bitvec"
 version = "1.0.1"
@@ -634,7 +651,7 @@ dependencies = [
  "proc-macro-crate",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
  "syn_derive",
 ]
 
@@ -672,7 +689,7 @@ dependencies = [
 
 [[package]]
 name = "build-info"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "anyhow",
  "time",
@@ -684,6 +701,24 @@ name = "bumpalo"
 version = "3.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c"
+dependencies = [
+ "allocator-api2",
+ "serde",
+]
+
+[[package]]
+name = "bumparaw-collections"
+version = "0.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4ce682bdc86c2e25ef5cd95881d9d6a1902214eddf74cf9ffea88fe1464377e8"
+dependencies = [
+ "allocator-api2",
+ "bitpacking",
+ "bumpalo",
+ "hashbrown 0.15.1",
+ "serde",
+ "serde_json",
+]
 
 [[package]]
 name = "byte-unit"
@@ -741,7 +776,7 @@ checksum = "4da9a32f3fed317401fa3c862968128267c3106685286e15d5aaa3d7389c2f60"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -953,9 +988,9 @@ dependencies = [
 
 [[package]]
 name = "charabia"
-version = "0.9.1"
+version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "55ff52497324e7d168505a16949ae836c14595606fab94687238d2f6c8d4c798"
+checksum = "cf8921fe4d53ab8f9e8f9b72ce6f91726cfc40fffab1243d27db406b5e2e9cc2"
 dependencies = [
  "aho-corasick",
  "csv",
@@ -1052,7 +1087,7 @@ dependencies = [
  "heck 0.5.0",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1230,19 +1265,6 @@ dependencies = [
  "itertools 0.10.5",
 ]
 
-[[package]]
-name = "crossbeam"
-version = "0.8.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1137cd7e7fc0fb5d3c5a8678be38ec56e819125d8d7907411fe24ccb943faca8"
-dependencies = [
- "crossbeam-channel",
- "crossbeam-deque",
- "crossbeam-epoch",
- "crossbeam-queue",
- "crossbeam-utils",
-]
-
 [[package]]
 name = "crossbeam-channel"
 version = "0.5.13"
@@ -1378,7 +1400,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "strsim 0.11.1",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1400,7 +1422,7 @@ checksum = "733cabb43482b1a1b53eee8583c2b9e8684d592215ea83efd305dd31bc2f0178"
 dependencies = [
  "darling_core 0.20.9",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1454,7 +1476,7 @@ checksum = "67e77553c4162a157adbf834ebae5b415acbecbeafc7a74b0e886657506a7611"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1496,7 +1518,7 @@ dependencies = [
  "darling 0.20.9",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1516,7 +1538,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "206868b8242f27cecce124c19fd88157fbd0dd334df2587f36417bafbc85097b"
 dependencies = [
  "derive_builder_core 0.20.0",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1558,7 +1580,7 @@ dependencies = [
  "convert_case 0.6.0",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1622,7 +1644,7 @@ checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1642,7 +1664,7 @@ dependencies = [
 
 [[package]]
 name = "dump"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "anyhow",
  "big_s",
@@ -1780,7 +1802,7 @@ dependencies = [
  "heck 0.4.1",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1800,7 +1822,7 @@ checksum = "a1ab991c1362ac86c61ab6f556cff143daa22e5a15e4e189df818b2fd19fe65b"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1848,13 +1870,13 @@ dependencies = [
 
 [[package]]
 name = "fastrand"
-version = "2.1.0"
+version = "2.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9fc0510504f03c51ada170672ac806f1f105a88aa97a5281117e1ddc3368e51a"
+checksum = "486f806e73c5707928240ddc295403b1b93c96a02038563881c4a2fd84b81ac4"
 
 [[package]]
 name = "file-store"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "tempfile",
  "thiserror",
@@ -1876,7 +1898,7 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "insta",
  "nom",
@@ -1896,18 +1918,33 @@ dependencies = [
 
 [[package]]
 name = "flatten-serde-json"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "criterion",
  "serde_json",
 ]
 
+[[package]]
+name = "flume"
+version = "0.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da0e4dd2a88388a1f4ccc7c9ce104604dab68d9f408dc34cd45823d5a9069095"
+dependencies = [
+ "spin",
+]
+
 [[package]]
 name = "fnv"
 version = "1.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
 
+[[package]]
+name = "foldhash"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f81ec6369c545a7d40e4589b5597581fa1c441fe1cce96dd1de43159910a36a2"
+
 [[package]]
 name = "form_urlencoded"
 version = "1.2.1"
@@ -1985,7 +2022,7 @@ checksum = "87750cf4b7a4c0625b1529e4c543c2182106e4dedc60a2a6455e00d212c489ac"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -2020,10 +2057,12 @@ dependencies = [
 
 [[package]]
 name = "fuzzers"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "arbitrary",
+ "bumpalo",
  "clap",
+ "either",
  "fastrand",
  "milli",
  "serde",
@@ -2240,12 +2279,13 @@ checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
 
 [[package]]
 name = "grenad"
-version = "0.4.7"
+version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "350d89047298d3b1b40050acd11ab76e487b854a104b760ebc5a7f375093de77"
+checksum = "0e2ac9baf835ee2a7f0622a5617792ced6f65af25994078c343d429431ef2bbc"
 dependencies = [
  "bytemuck",
  "byteorder",
+ "either",
  "rayon",
  "tempfile",
 ]
@@ -2336,6 +2376,18 @@ dependencies = [
  "allocator-api2",
 ]
 
+[[package]]
+name = "hashbrown"
+version = "0.15.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a9bfc1af68b1726ea47d3d5109de126281def866b33970e10fbab11b5dafab3"
+dependencies = [
+ "allocator-api2",
+ "equivalent",
+ "foldhash",
+ "serde",
+]
+
 [[package]]
 name = "heapless"
 version = "0.8.0"
@@ -2572,13 +2624,16 @@ checksum = "206ca75c9c03ba3d4ace2460e57b189f39f43de612c2f85836e65c929701bb2d"
 
 [[package]]
 name = "index-scheduler"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "anyhow",
  "arroy 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
  "big_s",
  "bincode",
- "crossbeam",
+ "bumpalo",
+ "bumparaw-collections",
+ "convert_case 0.6.0",
+ "crossbeam-channel",
  "csv",
  "derive_builder 0.20.0",
  "dump",
@@ -2590,6 +2645,7 @@ dependencies = [
  "meili-snap",
  "meilisearch-auth",
  "meilisearch-types",
+ "memmap2",
  "page_size",
  "rayon",
  "roaring",
@@ -2606,12 +2662,12 @@ dependencies = [
 
 [[package]]
 name = "indexmap"
-version = "2.2.6"
+version = "2.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "168fb715dda47215e360912c096649d23d58bf392ac62f73919e831745e40f26"
+checksum = "62f822373a4fe84d4bb149bf54e584a7f4abec90e072ed49cda0edea5b95471f"
 dependencies = [
  "equivalent",
- "hashbrown 0.14.3",
+ "hashbrown 0.15.1",
  "serde",
 ]
 
@@ -2766,7 +2822,7 @@ dependencies = [
 
 [[package]]
 name = "json-depth-checker"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "criterion",
  "serde_json",
@@ -2835,9 +2891,9 @@ dependencies = [
 
 [[package]]
 name = "libc"
-version = "0.2.155"
+version = "0.2.164"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "97b3888a4aecf77e811145cadf6eef5901f4782c53886191b2f693f24761847c"
+checksum = "433bfe06b8c75da9b2e3fbea6e5329ff87748f0b144ef75306e674c3f6f7c13f"
 
 [[package]]
 name = "libgit2-sys"
@@ -3221,9 +3277,9 @@ checksum = "0717cef1bc8b636c6e1c1bbdefc09e6322da8a9321966e8928ef80d20f7f770f"
 
 [[package]]
 name = "linux-raw-sys"
-version = "0.4.12"
+version = "0.4.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4cd1a83af159aa67994778be9070f0ae1bd732942279cabb14f86f986a21456"
+checksum = "78b3ae25bc7c8c38cec158d1f2757ee79e9b3740fbc7ccf0e59e4b08d793fa89"
 
 [[package]]
 name = "liquid"
@@ -3264,7 +3320,7 @@ checksum = "915f6d0a2963a27cd5205c1902f32ddfe3bc035816afd268cf88c0fc0f8d287e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -3368,7 +3424,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -3385,7 +3441,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
 
 [[package]]
 name = "meili-snap"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "insta",
  "md5",
@@ -3394,7 +3450,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "actix-cors",
  "actix-http",
@@ -3484,7 +3540,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-auth"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "base64 0.22.1",
  "enum-iterator",
@@ -3503,10 +3559,12 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-types"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "actix-web",
  "anyhow",
+ "bumpalo",
+ "bumparaw-collections",
  "convert_case 0.6.0",
  "csv",
  "deserr",
@@ -3520,6 +3578,7 @@ dependencies = [
  "memmap2",
  "milli",
  "roaring",
+ "rustc-hash 2.1.0",
  "serde",
  "serde-cs",
  "serde_json",
@@ -3533,16 +3592,19 @@ dependencies = [
 
 [[package]]
 name = "meilitool"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "anyhow",
  "arroy 0.5.0 (git+https://github.com/meilisearch/arroy/?tag=DO-NOT-DELETE-upgrade-v04-to-v05)",
  "clap",
  "dump",
  "file-store",
+ "indexmap",
  "meilisearch-auth",
  "meilisearch-types",
  "serde",
+ "serde_json",
+ "tempfile",
  "time",
  "uuid",
 ]
@@ -3555,9 +3617,9 @@ checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
 
 [[package]]
 name = "memmap2"
-version = "0.9.4"
+version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fe751422e4a8caa417e13c3ea66452215d7d63e19e604f4980461212f3ae1322"
+checksum = "fd3f7eed9d3848f8b98834af67102b720745c4ec028fcd0aa0239277e7de374f"
 dependencies = [
  "libc",
  "stable_deref_trait",
@@ -3565,13 +3627,17 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
+ "allocator-api2",
  "arroy 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
+ "bbqueue",
  "big_s",
  "bimap",
  "bincode",
  "bstr",
+ "bumpalo",
+ "bumparaw-collections",
  "bytemuck",
  "byteorder",
  "candle-core",
@@ -3583,12 +3649,15 @@ dependencies = [
  "csv",
  "deserr",
  "either",
+ "enum-iterator",
  "filter-parser",
  "flatten-serde-json",
+ "flume",
  "fst",
  "fxhash",
  "geoutils",
  "grenad",
+ "hashbrown 0.15.1",
  "heed",
  "hf-hub",
  "indexmap",
@@ -3612,6 +3681,7 @@ dependencies = [
  "rhai",
  "roaring",
  "rstar",
+ "rustc-hash 2.1.0",
  "serde",
  "serde_json",
  "slice-group-by",
@@ -3620,10 +3690,12 @@ dependencies = [
  "smartstring",
  "tempfile",
  "thiserror",
+ "thread_local",
  "tiktoken-rs",
  "time",
  "tokenizers",
  "tracing",
+ "uell",
  "ureq",
  "url",
  "uuid",
@@ -3699,7 +3771,7 @@ checksum = "371717c0a5543d6a800cac822eac735aa7d2d2fbb41002e9856a4089532dbdce"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -3835,7 +3907,7 @@ dependencies = [
  "proc-macro-crate",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -3864,9 +3936,9 @@ dependencies = [
 
 [[package]]
 name = "obkv"
-version = "0.2.2"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a2e27bcfe835a379d32352112f6b8dbae2d99d16a5fff42abe6e5ba5386c1e5a"
+checksum = "ae4512a8f418ac322335255a72361b9ac927e106f4d7fe6ab4d8ac59cb01f7a9"
 
 [[package]]
 name = "once_cell"
@@ -4011,7 +4083,7 @@ checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
 
 [[package]]
 name = "permissive-json-pointer"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "big_s",
  "serde_json",
@@ -4047,7 +4119,7 @@ dependencies = [
  "pest_meta",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -4101,7 +4173,7 @@ dependencies = [
  "phf_shared",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -4130,7 +4202,7 @@ checksum = "266c042b60c9c76b8d53061e52b2e0d1116abc57cefc8c5cd671619a56ac3690"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -4247,9 +4319,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.81"
+version = "1.0.89"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d1597b0c024618f09a9c3b8655b7e430397a36d23fdafec26d6965e9eec3eba"
+checksum = "f139b0662de085916d1fb67d2b4169d1addddda1919e696f3252b740b629986e"
 dependencies = [
  "unicode-ident",
 ]
@@ -4358,7 +4430,7 @@ dependencies = [
  "bytes",
  "rand",
  "ring",
- "rustc-hash 2.0.0",
+ "rustc-hash 2.1.0",
  "rustls",
  "slab",
  "thiserror",
@@ -4631,7 +4703,7 @@ source = "git+https://github.com/rhaiscript/rhai?rev=ef3df63121d27aacd838f366f2b
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -4680,9 +4752,9 @@ dependencies = [
 
 [[package]]
 name = "roaring"
-version = "0.10.6"
+version = "0.10.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f4b84ba6e838ceb47b41de5194a60244fac43d9fe03b71dbe8c5a201081d6d1"
+checksum = "f81dc953b2244ddd5e7860cb0bb2a790494b898ef321d4aff8e260efab60cc88"
 dependencies = [
  "bytemuck",
  "byteorder",
@@ -4731,9 +4803,9 @@ checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
 
 [[package]]
 name = "rustc-hash"
-version = "2.0.0"
+version = "2.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "583034fd73374156e66797ed8e5b0d5690409c9226b22d87cb7f19821c05d152"
+checksum = "c7fb8039b3032c191086b10f11f319a6e99e1e82889c5cc6046f515c9db1d497"
 
 [[package]]
 name = "rustc_version"
@@ -4746,9 +4818,9 @@ dependencies = [
 
 [[package]]
 name = "rustix"
-version = "0.38.31"
+version = "0.38.41"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6ea3e1a662af26cd7a3ba09c0297a31af215563ecf42817c98df621387f4e949"
+checksum = "d7f649912bc1495e167a6edee79151c84b1bad49748cb4f1f1167f459f6224f6"
 dependencies = [
  "bitflags 2.6.0",
  "errno",
@@ -4873,9 +4945,9 @@ checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
 
 [[package]]
 name = "serde"
-version = "1.0.209"
+version = "1.0.214"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "99fce0ffe7310761ca6bf9faf5115afbc19688edd00171d81b1bb1b116c63e09"
+checksum = "f55c3193aca71c12ad7890f1785d2b73e1b9f63a0bbc353c08ef26fe03fc56b5"
 dependencies = [
  "serde_derive",
 ]
@@ -4891,23 +4963,24 @@ dependencies = [
 
 [[package]]
 name = "serde_derive"
-version = "1.0.209"
+version = "1.0.214"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a5831b979fd7b5439637af1752d535ff49f4860c0f341d1baeb6faf0f4242170"
+checksum = "de523f781f095e28fa605cdce0f8307e451cc0fd14e2eb4cd2e98a355b147766"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.120"
+version = "1.0.133"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4e0d21c9a8cae1235ad58a00c11cb40d4b1e5c784f1ef2c537876ed6ffd8b7c5"
+checksum = "c7fceb2473b9166b2294ef05efcb65a3db80803f0b03ef86a5fc88a2b85ee377"
 dependencies = [
  "indexmap",
  "itoa",
+ "memchr",
  "ryu",
  "serde",
 ]
@@ -5123,6 +5196,9 @@ name = "spin"
 version = "0.9.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6980e8d7511241f8acf4aebddbb1ff938df5eebe98691418c4468d0b72a96a67"
+dependencies = [
+ "lock_api",
+]
 
 [[package]]
 name = "spm_precompiled"
@@ -5190,7 +5266,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "rustversion",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -5212,9 +5288,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.60"
+version = "2.0.87"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "909518bc7b1c9b779f1bbf07f2929d35af9f0f37e47c6e9ef7f9dddc1e1821f3"
+checksum = "25aa4ce346d03a6dcd68dd8b4010bcb74e54e62c90c573f394c46eae99aba32d"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -5230,7 +5306,7 @@ dependencies = [
  "proc-macro-error",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -5256,7 +5332,7 @@ checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -5316,12 +5392,13 @@ dependencies = [
 
 [[package]]
 name = "tempfile"
-version = "3.10.1"
+version = "3.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "85b77fafb263dd9d05cbeac119526425676db3784113aa9295c88498cbf8bff1"
+checksum = "28cce251fcbc87fac86a866eeb0d6c2d536fc16d06f184bb61aeae11aa4cee0c"
 dependencies = [
  "cfg-if",
  "fastrand",
+ "once_cell",
  "rustix",
  "windows-sys 0.52.0",
 ]
@@ -5361,14 +5438,14 @@ checksum = "46c3384250002a6d5af4d114f2845d37b57521033f30d5c3f46c4d70e1197533"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
 name = "thread_local"
-version = "1.1.7"
+version = "1.1.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3fdd6f064ccff2d6567adcb3873ca630700f00b5ad3f060c25b5dcfd9a4ce152"
+checksum = "8b9ef9bad013ada3808854ceac7b46812a6465ba368859a37e2100283d2d719c"
 dependencies = [
  "cfg-if",
  "once_cell",
@@ -5513,7 +5590,7 @@ checksum = "5f5ae998a069d4b5aba8ee9dad856af7d520c3699e6159b185c2acd48155d39a"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -5645,7 +5722,7 @@ checksum = "34704c8d6ebcbc939824180af020566b01a7c01f80641264eba0999f6c2b6be7"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -5740,6 +5817,15 @@ version = "0.1.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ed646292ffc8188ef8ea4d1e0e0150fb15a5c2e12ad9b8fc191ae7a8a7f3c4b9"
 
+[[package]]
+name = "uell"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "40de5982e28612e20330e77d81f1559b74f66caf3c7fc10b19ada4843f4b4fd7"
+dependencies = [
+ "bumpalo",
+]
+
 [[package]]
 name = "unescaper"
 version = "0.1.5"
@@ -5946,9 +6032,9 @@ dependencies = [
 
 [[package]]
 name = "wana_kana"
-version = "3.0.0"
+version = "4.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "477976a5c56fb7b014795df5a2ce08d2de8bcd4d5980844c5bd3978a7fd1c30b"
+checksum = "a74666202acfcb4f9b995be2e3e9f7f530deb65e05a1407b8d0b30c9c451238a"
 dependencies = [
  "fnv",
  "itertools 0.10.5",
@@ -5991,7 +6077,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
  "wasm-bindgen-shared",
 ]
 
@@ -6025,7 +6111,7 @@ checksum = "e94f17b526d0a461a191c78ea52bbce64071ed5c04c9ffe424dcb38f74171bb7"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
@@ -6400,7 +6486,7 @@ dependencies = [
 
 [[package]]
 name = "xtask"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "anyhow",
  "build-info",
@@ -6458,7 +6544,7 @@ checksum = "9e6936f0cce458098a201c245a11bef556c6a0181129c7034d10d76d1ec3a2b8"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
  "synstructure",
 ]
 
@@ -6479,7 +6565,7 @@ checksum = "9ce1b18ccd8e73a9321186f97e46f9f04b778851177567b1975109d26a08d2a6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -6499,7 +6585,7 @@ checksum = "e6a647510471d372f2e6c2e6b7219e44d8c574d24fdc11c610a61455782f18c3"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
  "synstructure",
 ]
 
@@ -6520,7 +6606,7 @@ checksum = "ce36e65b0d2999d2aafac989fb249189a141aee1f53c612c1f37d72631959f69"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]

Cargo.toml

@@ -22,7 +22,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.11.0"
+version = "1.12.0"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",
@@ -43,24 +43,3 @@ opt-level = 3
 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

crates/benchmarks/Cargo.toml

@@ -12,16 +12,19 @@ license.workspace = true
 
 [dependencies]
 anyhow = "1.0.86"
+bumpalo = "3.16.0"
 csv = "1.3.0"
+memmap2 = "0.9.5"
 milli = { path = "../milli" }
 mimalloc = { version = "0.1.43", default-features = false }
 serde_json = { version = "1.0.120", features = ["preserve_order"] }
+tempfile = "3.14.0"
 
 [dev-dependencies]
 criterion = { version = "0.5.1", features = ["html_reports"] }
 rand = "0.8.5"
 rand_chacha = "0.3.1"
-roaring = "0.10.6"
+roaring = "0.10.7"
 
 [build-dependencies]
 anyhow = "1.0.86"

crates/benchmarks/benches/search_geo.rs

@@ -5,6 +5,7 @@ use criterion::{criterion_group, criterion_main};
 use milli::update::Settings;
 use utils::Conf;
 
+#[cfg(not(windows))]
 #[global_allocator]
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 

crates/benchmarks/benches/search_songs.rs

@@ -5,6 +5,7 @@ use criterion::{criterion_group, criterion_main};
 use milli::update::Settings;
 use utils::Conf;
 
+#[cfg(not(windows))]
 #[global_allocator]
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 

crates/benchmarks/benches/search_wiki.rs

@@ -5,6 +5,7 @@ use criterion::{criterion_group, criterion_main};
 use milli::update::Settings;
 use utils::Conf;
 
+#[cfg(not(windows))]
 #[global_allocator]
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 

crates/benchmarks/benches/utils.rs

@@ -1,17 +1,19 @@
 #![allow(dead_code)]
 
 use std::fs::{create_dir_all, remove_dir_all, File};
-use std::io::{self, BufRead, BufReader, Cursor, Read, Seek};
-use std::num::ParseFloatError;
+use std::io::{self, BufReader, BufWriter, Read};
 use std::path::Path;
-use std::str::FromStr;
+use std::str::FromStr as _;
 
+use anyhow::Context;
+use bumpalo::Bump;
 use criterion::BenchmarkId;
-use milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
+use memmap2::Mmap;
 use milli::heed::EnvOpenOptions;
-use milli::update::{
-    IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings,
-};
+use milli::progress::Progress;
+use milli::update::new::indexer;
+use milli::update::{IndexDocumentsMethod, IndexerConfig, Settings};
+use milli::vector::EmbeddingConfigs;
 use milli::{Criterion, Filter, Index, Object, TermsMatchingStrategy};
 use serde_json::Value;
 
@@ -65,7 +67,7 @@ pub fn base_setup(conf: &Conf) -> Index {
 
     let mut options = EnvOpenOptions::new();
     options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
-    options.max_readers(10);
+    options.max_readers(100);
     let index = Index::new(options, conf.database_name).unwrap();
 
     let config = IndexerConfig::default();
@@ -92,18 +94,44 @@ pub fn base_setup(conf: &Conf) -> Index {
 
     let config = IndexerConfig::default();
     let mut wtxn = index.write_txn().unwrap();
-    let indexing_config = IndexDocumentsConfig {
-        autogenerate_docids: conf.primary_key.is_none(),
-        update_method: IndexDocumentsMethod::ReplaceDocuments,
-        ..Default::default()
-    };
-    let builder =
-        IndexDocuments::new(&mut wtxn, &index, &config, indexing_config, |_| (), || false).unwrap();
+    let rtxn = index.read_txn().unwrap();
+    let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
+    let mut new_fields_ids_map = db_fields_ids_map.clone();
+
     let documents = documents_from(conf.dataset, conf.dataset_format);
-    let (builder, user_error) = builder.add_documents(documents).unwrap();
-    user_error.unwrap();
-    builder.execute().unwrap();
+    let mut indexer = indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
+    indexer.add_documents(&documents).unwrap();
+
+    let indexer_alloc = Bump::new();
+    let (document_changes, _operation_stats, primary_key) = indexer
+        .into_changes(
+            &indexer_alloc,
+            &index,
+            &rtxn,
+            None,
+            &mut new_fields_ids_map,
+            &|| false,
+            Progress::default(),
+        )
+        .unwrap();
+
+    indexer::index(
+        &mut wtxn,
+        &index,
+        &milli::ThreadPoolNoAbortBuilder::new().build().unwrap(),
+        config.grenad_parameters(),
+        &db_fields_ids_map,
+        new_fields_ids_map,
+        primary_key,
+        &document_changes,
+        EmbeddingConfigs::default(),
+        &|| false,
+        &Progress::default(),
+    )
+    .unwrap();
+
     wtxn.commit().unwrap();
+    drop(rtxn);
 
     index
 }
@@ -140,49 +168,96 @@ pub fn run_benches(c: &mut criterion::Criterion, confs: &[Conf]) {
     }
 }
 
-pub fn documents_from(filename: &str, filetype: &str) -> DocumentsBatchReader<impl BufRead + Seek> {
-    let reader = File::open(filename)
-        .unwrap_or_else(|_| panic!("could not find the dataset in: {}", filename));
-    let reader = BufReader::new(reader);
-    let documents = match filetype {
-        "csv" => documents_from_csv(reader).unwrap(),
-        "json" => documents_from_json(reader).unwrap(),
-        "jsonl" => documents_from_jsonl(reader).unwrap(),
-        otherwise => panic!("invalid update format {:?}", otherwise),
-    };
-    DocumentsBatchReader::from_reader(Cursor::new(documents)).unwrap()
+pub fn documents_from(filename: &str, filetype: &str) -> Mmap {
+    let file = File::open(filename)
+        .unwrap_or_else(|_| panic!("could not find the dataset in: {filename}"));
+    match filetype {
+        "csv" => documents_from_csv(file).unwrap(),
+        "json" => documents_from_json(file).unwrap(),
+        "jsonl" => documents_from_jsonl(file).unwrap(),
+        otherwise => panic!("invalid update format {otherwise:?}"),
+    }
 }
 
-fn documents_from_jsonl(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
-    let mut documents = DocumentsBatchBuilder::new(Vec::new());
+fn documents_from_jsonl(file: File) -> anyhow::Result<Mmap> {
+    unsafe { Mmap::map(&file).map_err(Into::into) }
+}
 
-    for result in serde_json::Deserializer::from_reader(reader).into_iter::<Object>() {
-        let object = result?;
-        documents.append_json_object(&object)?;
+fn documents_from_json(file: File) -> anyhow::Result<Mmap> {
+    let reader = BufReader::new(file);
+    let documents: Vec<milli::Object> = serde_json::from_reader(reader)?;
+    let mut output = tempfile::tempfile().map(BufWriter::new)?;
+
+    for document in documents {
+        serde_json::to_writer(&mut output, &document)?;
     }
 
-    documents.into_inner().map_err(Into::into)
+    let file = output.into_inner()?;
+    unsafe { Mmap::map(&file).map_err(Into::into) }
 }
 
-fn documents_from_json(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
-    let mut documents = DocumentsBatchBuilder::new(Vec::new());
+fn documents_from_csv(file: File) -> anyhow::Result<Mmap> {
+    let output = tempfile::tempfile()?;
+    let mut output = BufWriter::new(output);
+    let mut reader = csv::ReaderBuilder::new().from_reader(file);
 
-    documents.append_json_array(reader)?;
+    let headers = reader.headers().context("while retrieving headers")?.clone();
+    let typed_fields: Vec<_> = headers.iter().map(parse_csv_header).collect();
+    let mut object: serde_json::Map<_, _> =
+        typed_fields.iter().map(|(k, _)| (k.to_string(), Value::Null)).collect();
 
-    documents.into_inner().map_err(Into::into)
-}
+    let mut line = 0;
+    let mut record = csv::StringRecord::new();
+    while reader.read_record(&mut record).context("while reading a record")? {
+        // We increment here and not at the end of the loop
+        // to take the header offset into account.
+        line += 1;
 
-fn documents_from_csv(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
-    let csv = csv::Reader::from_reader(reader);
+        // Reset the document values
+        object.iter_mut().for_each(|(_, v)| *v = Value::Null);
 
-    let mut documents = DocumentsBatchBuilder::new(Vec::new());
-    documents.append_csv(csv)?;
+        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) => {
+                                anyhow::bail!("document format error on line {line}: {error}. For value: {value}")
+                            }
+                        },
+                    }
+                }
+                AllowedType::Boolean if trimmed_value.is_empty() => Value::Null,
+                AllowedType::Boolean => match trimmed_value.parse::<bool>() {
+                    Ok(bool) => Value::from(bool),
+                    Err(error) => {
+                        anyhow::bail!(
+                            "document format error on line {line}: {error}. For value: {value}"
+                        )
+                    }
+                },
+                AllowedType::String if value.is_empty() => Value::Null,
+                AllowedType::String => Value::from(value),
+            };
 
-    documents.into_inner().map_err(Into::into)
+            *object.get_mut(name).expect("encountered an unknown field") = value;
+        }
+
+        serde_json::to_writer(&mut output, &object).context("while writing to disk")?;
+    }
+
+    let output = output.into_inner()?;
+    unsafe { Mmap::map(&output).map_err(Into::into) }
 }
 
 enum AllowedType {
     String,
+    Boolean,
     Number,
 }
 
@@ -191,8 +266,9 @@ fn parse_csv_header(header: &str) -> (String, AllowedType) {
     match header.rsplit_once(':') {
         Some((field_name, field_type)) => match field_type {
             "string" => (field_name.to_string(), AllowedType::String),
+            "boolean" => (field_name.to_string(), AllowedType::Boolean),
             "number" => (field_name.to_string(), AllowedType::Number),
-            // we may return an error in this case.
+            // if the pattern isn't recognized, we keep the whole field.
             _otherwise => (header.to_string(), AllowedType::String),
         },
         None => (header.to_string(), AllowedType::String),
@@ -230,10 +306,13 @@ impl<R: Read> Iterator for CSVDocumentDeserializer<R> {
                 for ((field_name, field_type), value) in
                     self.headers.iter().zip(csv_document.into_iter())
                 {
-                    let parsed_value: Result<Value, ParseFloatError> = match field_type {
+                    let parsed_value: anyhow::Result<Value> = match field_type {
                         AllowedType::Number => {
                             value.parse::<f64>().map(Value::from).map_err(Into::into)
                         }
+                        AllowedType::Boolean => {
+                            value.parse::<bool>().map(Value::from).map_err(Into::into)
+                        }
                         AllowedType::String => Ok(Value::String(value.to_string())),
                     };
 

crates/dump/Cargo.toml

@@ -17,7 +17,7 @@ http = "1.1.0"
 meilisearch-types = { path = "../meilisearch-types" }
 once_cell = "1.19.0"
 regex = "1.10.5"
-roaring = { version = "0.10.6", features = ["serde"] }
+roaring = { version = "0.10.7", features = ["serde"] }
 serde = { version = "1.0.204", features = ["derive"] }
 serde_json = { version = "1.0.120", features = ["preserve_order"] }
 tar = "0.4.41"

crates/dump/src/lib.rs

@@ -292,6 +292,8 @@ pub(crate) mod test {
             embedders: Setting::NotSet,
             search_cutoff_ms: Setting::NotSet,
             localized_attributes: Setting::NotSet,
+            facet_search: Setting::NotSet,
+            prefix_search: Setting::NotSet,
             _kind: std::marker::PhantomData,
         };
         settings.check()

crates/dump/src/reader/compat/v5_to_v6.rs

@@ -382,6 +382,8 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
             embedders: v6::Setting::NotSet,
             localized_attributes: v6::Setting::NotSet,
             search_cutoff_ms: v6::Setting::NotSet,
+            facet_search: v6::Setting::NotSet,
+            prefix_search: v6::Setting::NotSet,
             _kind: std::marker::PhantomData,
         }
     }

crates/file-store/src/lib.rs

@@ -136,6 +136,14 @@ pub struct File {
 }
 
 impl File {
+    pub fn from_parts(path: PathBuf, file: Option<NamedTempFile>) -> Self {
+        Self { path, file }
+    }
+
+    pub fn into_parts(self) -> (PathBuf, Option<NamedTempFile>) {
+        (self.path, self.file)
+    }
+
     pub fn dry_file() -> Result<Self> {
         Ok(Self { path: PathBuf::new(), file: None })
     }

crates/fuzzers/Cargo.toml

@@ -12,7 +12,9 @@ license.workspace = true
 
 [dependencies]
 arbitrary = { version = "1.3.2", features = ["derive"] }
+bumpalo = "3.16.0"
 clap = { version = "4.5.9", features = ["derive"] }
+either = "1.13.0"
 fastrand = "2.1.0"
 milli = { path = "../milli" }
 serde = { version = "1.0.204", features = ["derive"] }

crates/fuzzers/src/bin/fuzz-indexing.rs

@@ -4,11 +4,18 @@ use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering};
 use std::time::Duration;
 
 use arbitrary::{Arbitrary, Unstructured};
+use bumpalo::Bump;
 use clap::Parser;
+use either::Either;
 use fuzzers::Operation;
+use milli::documents::mmap_from_objects;
 use milli::heed::EnvOpenOptions;
-use milli::update::{IndexDocuments, IndexDocumentsConfig, IndexerConfig};
+use milli::progress::Progress;
+use milli::update::new::indexer;
+use milli::update::{IndexDocumentsMethod, IndexerConfig};
+use milli::vector::EmbeddingConfigs;
 use milli::Index;
+use serde_json::Value;
 use tempfile::TempDir;
 
 #[derive(Debug, Arbitrary)]
@@ -58,7 +65,6 @@ fn main() {
             };
             let index = Index::new(options, tempdir.path()).unwrap();
             let indexer_config = IndexerConfig::default();
-            let index_documents_config = IndexDocumentsConfig::default();
 
             std::thread::scope(|s| {
                 loop {
@@ -75,38 +81,72 @@ fn main() {
 
                     let handle = s.spawn(|| {
                         let mut wtxn = index.write_txn().unwrap();
+                        let rtxn = index.read_txn().unwrap();
 
                         for batch in batches {
-                            let mut builder = IndexDocuments::new(
-                                &mut wtxn,
-                                &index,
-                                &indexer_config,
-                                index_documents_config.clone(),
-                                |_| (),
-                                || false,
-                            )
-                            .unwrap();
+                            let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
+                            let mut new_fields_ids_map = db_fields_ids_map.clone();
 
+                            let indexer_alloc = Bump::new();
+                            let embedders = EmbeddingConfigs::default();
+                            let mut indexer = indexer::DocumentOperation::new(
+                                IndexDocumentsMethod::ReplaceDocuments,
+                            );
+
+                            let mut operations = Vec::new();
                             for op in batch.0 {
                                 match op {
                                     Operation::AddDoc(doc) => {
-                                        let documents =
-                                            milli::documents::objects_from_json_value(doc.to_d());
-                                        let documents =
-                                            milli::documents::documents_batch_reader_from_objects(
-                                                documents,
-                                            );
-                                        let (b, _added) = builder.add_documents(documents).unwrap();
-                                        builder = b;
+                                        let object = match doc.to_d() {
+                                            Value::Object(object) => object,
+                                            _ => unreachable!(),
+                                        };
+                                        let documents = mmap_from_objects(vec![object]);
+                                        operations.push(Either::Left(documents));
                                     }
                                     Operation::DeleteDoc(id) => {
-                                        let (b, _removed) =
-                                            builder.remove_documents(vec![id.to_s()]).unwrap();
-                                        builder = b;
+                                        let id = indexer_alloc.alloc_str(&id.to_s());
+                                        let ids = indexer_alloc.alloc_slice_copy(&[&*id]);
+                                        operations.push(Either::Right(ids));
                                     }
                                 }
                             }
-                            builder.execute().unwrap();
+
+                            for op in &operations {
+                                match op {
+                                    Either::Left(documents) => {
+                                        indexer.add_documents(documents).unwrap()
+                                    }
+                                    Either::Right(ids) => indexer.delete_documents(ids),
+                                }
+                            }
+
+                            let (document_changes, _operation_stats, primary_key) = indexer
+                                .into_changes(
+                                    &indexer_alloc,
+                                    &index,
+                                    &rtxn,
+                                    None,
+                                    &mut new_fields_ids_map,
+                                    &|| false,
+                                    Progress::default(),
+                                )
+                                .unwrap();
+
+                            indexer::index(
+                                &mut wtxn,
+                                &index,
+                                &milli::ThreadPoolNoAbortBuilder::new().build().unwrap(),
+                                indexer_config.grenad_parameters(),
+                                &db_fields_ids_map,
+                                new_fields_ids_map,
+                                primary_key,
+                                &document_changes,
+                                embedders,
+                                &|| false,
+                                &Progress::default(),
+                            )
+                            .unwrap();
 
                             // after executing a batch we check if the database is corrupted
                             let res = index.search(&wtxn).execute().unwrap();

crates/index-scheduler/Cargo.toml

@@ -13,6 +13,9 @@ license.workspace = true
 [dependencies]
 anyhow = "1.0.86"
 bincode = "1.3.3"
+bumpalo = "3.16.0"
+bumparaw-collections = "0.1.2"
+convert_case = "0.6.0"
 csv = "1.3.0"
 derive_builder = "0.20.0"
 dump = { path = "../dump" }
@@ -21,9 +24,10 @@ file-store = { path = "../file-store" }
 flate2 = "1.0.30"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
+memmap2 = "0.9.4"
 page_size = "0.6.0"
 rayon = "1.10.0"
-roaring = { version = "0.10.6", features = ["serde"] }
+roaring = { version = "0.10.7", features = ["serde"] }
 serde = { version = "1.0.204", features = ["derive"] }
 serde_json = { version = "1.0.120", features = ["preserve_order"] }
 synchronoise = "1.0.1"
@@ -42,7 +46,7 @@ uuid = { version = "1.10.0", features = ["serde", "v4"] }
 [dev-dependencies]
 arroy = "0.5.0"
 big_s = "1.0.2"
-crossbeam = "0.8.4"
+crossbeam-channel = "0.5.13"
 insta = { version = "1.39.0", features = ["json", "redactions"] }
 maplit = "1.0.2"
 meili-snap = { path = "../meili-snap" }

crates/index-scheduler/src/autobatcher.rs

@@ -115,13 +115,6 @@ pub enum BatchKind {
         allow_index_creation: bool,
         settings_ids: Vec<TaskId>,
     },
-    SettingsAndDocumentOperation {
-        settings_ids: Vec<TaskId>,
-        method: IndexDocumentsMethod,
-        allow_index_creation: bool,
-        primary_key: Option<String>,
-        operation_ids: Vec<TaskId>,
-    },
     Settings {
         allow_index_creation: bool,
         settings_ids: Vec<TaskId>,
@@ -146,7 +139,6 @@ impl BatchKind {
         match self {
             BatchKind::DocumentOperation { allow_index_creation, .. }
             | BatchKind::ClearAndSettings { allow_index_creation, .. }
-            | BatchKind::SettingsAndDocumentOperation { allow_index_creation, .. }
             | BatchKind::Settings { allow_index_creation, .. } => Some(*allow_index_creation),
             _ => None,
         }
@@ -154,10 +146,7 @@ impl BatchKind {
 
     fn primary_key(&self) -> Option<Option<&str>> {
         match self {
-            BatchKind::DocumentOperation { primary_key, .. }
-            | BatchKind::SettingsAndDocumentOperation { primary_key, .. } => {
-                Some(primary_key.as_deref())
-            }
+            BatchKind::DocumentOperation { primary_key, .. } => Some(primary_key.as_deref()),
             _ => None,
         }
     }
@@ -275,8 +264,7 @@ impl BatchKind {
                 Break(BatchKind::IndexDeletion { ids })
             }
             (
-                BatchKind::ClearAndSettings { settings_ids: mut ids, allow_index_creation: _, mut other }
-                | BatchKind::SettingsAndDocumentOperation { operation_ids: mut ids, method: _, allow_index_creation: _, primary_key: _, settings_ids: mut other },
+                BatchKind::ClearAndSettings { settings_ids: mut ids, allow_index_creation: _, mut other },
                 K::IndexDeletion,
             ) => {
                 ids.push(id);
@@ -356,15 +344,9 @@ impl BatchKind {
             ) => Break(this),
 
             (
-                BatchKind::DocumentOperation { method, allow_index_creation, primary_key, operation_ids },
+                this @ BatchKind::DocumentOperation { .. },
                 K::Settings { .. },
-            ) => Continue(BatchKind::SettingsAndDocumentOperation {
-                settings_ids: vec![id],
-                method,
-                allow_index_creation,
-                primary_key,
-                operation_ids,
-            }),
+            ) => Break(this),
 
             (BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: _ }, K::DocumentClear) => {
                 deletion_ids.push(id);
@@ -477,63 +459,7 @@ impl BatchKind {
                     allow_index_creation,
                 })
             }
-            (
-                BatchKind::SettingsAndDocumentOperation { settings_ids, method: _, mut operation_ids, allow_index_creation, primary_key: _ },
-                K::DocumentClear,
-            ) => {
-                operation_ids.push(id);
-                Continue(BatchKind::ClearAndSettings {
-                    settings_ids,
-                    other: operation_ids,
-                    allow_index_creation,
-                })
-            }
 
-            (
-                BatchKind::SettingsAndDocumentOperation { settings_ids, method: ReplaceDocuments, mut operation_ids, allow_index_creation, primary_key: _},
-                K::DocumentImport { method: ReplaceDocuments, primary_key: pk2, .. },
-            ) => {
-                operation_ids.push(id);
-                Continue(BatchKind::SettingsAndDocumentOperation {
-                    settings_ids,
-                    method: ReplaceDocuments,
-                    allow_index_creation,
-                        primary_key: pk2,
-                    operation_ids,
-                })
-            }
-            (
-                BatchKind::SettingsAndDocumentOperation { settings_ids, method: UpdateDocuments, allow_index_creation, primary_key: _, mut operation_ids },
-                K::DocumentImport { method: UpdateDocuments, primary_key: pk2, .. },
-            ) => {
-                operation_ids.push(id);
-                Continue(BatchKind::SettingsAndDocumentOperation {
-                    settings_ids,
-                    method: UpdateDocuments,
-                    allow_index_creation,
-                    primary_key: pk2,
-                    operation_ids,
-                })
-            }
-            // But we can't batch a settings and a doc op with another doc op
-            // this MUST be AFTER the two previous branch
-            (
-                this @ BatchKind::SettingsAndDocumentOperation { .. },
-                K::DocumentDeletion { .. } | K::DocumentImport { .. },
-            ) => Break(this),
-            (
-                BatchKind::SettingsAndDocumentOperation { mut settings_ids, method, allow_index_creation,primary_key, operation_ids },
-                K::Settings { .. },
-            ) => {
-                settings_ids.push(id);
-                Continue(BatchKind::SettingsAndDocumentOperation {
-                    settings_ids,
-                    method,
-                    allow_index_creation,
-                    primary_key,
-                    operation_ids,
-                })
-            }
             (
                 BatchKind::IndexCreation { .. }
                 | BatchKind::IndexDeletion { .. }
@@ -808,30 +734,30 @@ mod tests {
     }
 
     #[test]
-    fn document_addition_batch_with_settings() {
+    fn document_addition_doesnt_batch_with_settings() {
         // simple case
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"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), settings(true)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
 
         // multiple settings and doc addition
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), settings(true), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [2, 3], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), settings(true), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [2, 3], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), settings(true), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), settings(true), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
 
         // addition and setting unordered
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1, 3], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_imp(UpdateDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1, 3], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 2] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_imp(ReplaceDocuments, true, None), settings(true)]), @"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), settings(true), doc_imp(UpdateDocuments, true, None), settings(true)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
 
-        // We ensure this kind of batch doesn't batch with forbidden operations
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_imp(UpdateDocuments, true, None)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_imp(ReplaceDocuments, true, None)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_del()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_del()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_create()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_create()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_update()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_update()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_swap()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_swap()]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        // Doesn't batch with other forbidden operations
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), 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), settings(true), 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(ReplaceDocuments, true, None), settings(true), doc_del()]), @"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), settings(true), doc_del()]), @"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), settings(true), 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), settings(true), idx_create()]), @"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), settings(true), 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), settings(true), idx_update()]), @"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), settings(true), 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), settings(true), idx_swap()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
     }
 
     #[test]
@@ -859,8 +785,8 @@ mod tests {
         debug_snapshot!(autobatch_from(true, None, [doc_clr(), settings(true)]), @"Some((DocumentClear { ids: [0] }, false))");
 
         debug_snapshot!(autobatch_from(true, None, [settings(true), doc_clr(), settings(true)]), @"Some((ClearAndSettings { other: [1], allow_index_creation: true, settings_ids: [0, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_clr()]), @"Some((ClearAndSettings { other: [0, 2], allow_index_creation: true, settings_ids: [1] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_clr()]), @"Some((ClearAndSettings { other: [0, 2], allow_index_creation: true, settings_ids: [1] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_clr()]), @"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), settings(true), doc_clr()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
     }
 
     #[test]
@@ -907,50 +833,6 @@ mod tests {
         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))");
-
-        // Then the mixed cases.
-        // The index already exists, whatever is the right of the tasks it shouldn't change the result.
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,false, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,false, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,false, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,true, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments,true, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-
-        // When the index doesn't exists yet it's more complicated.
-        // Either the first task we encounter create it, in which case we can create a big batch with everything.
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), settings(true), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        // The right of the tasks following isn't really important.
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,true, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, true))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,true, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, true))");
-        // Or, the second case; the first task doesn't create the index and thus we wants to batch it with only tasks that can't create an index.
-        // that can be a second task that don't have the right to create an index. Or anything that can't create an index like an index deletion, document deletion, document clear, etc.
-        // All theses tasks are going to throw an error `Index doesn't exist` once the batch is processed.
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,false, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        // The third and final case is when the first task doesn't create an index but is directly followed by a task creating an index. In this case we can't batch whit what
-        // follows because we first need to process the erronous batch.
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,false, None), settings(true), idx_del()]), @"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), settings(true), idx_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,false, None), settings(true), doc_clr(), idx_del()]), @"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), settings(true), doc_clr(), idx_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
     }
 
     #[test]
@@ -959,13 +841,13 @@ mod tests {
         debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
         debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
         debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
 
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((SettingsAndDocumentOperation { settings_ids: [1], method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
         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

crates/index-scheduler/src/error.rs

@@ -104,7 +104,7 @@ pub enum Error {
     )]
     InvalidTaskCanceledBy { canceled_by: String },
     #[error(
-        "{index_uid} is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes."
+        "{index_uid} is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 400 bytes."
     )]
     InvalidIndexUid { index_uid: String },
     #[error("Task `{0}` not found.")]
@@ -122,8 +122,11 @@ pub enum Error {
     Dump(#[from] dump::Error),
     #[error(transparent)]
     Heed(#[from] heed::Error),
-    #[error(transparent)]
-    Milli(#[from] milli::Error),
+    #[error("{}", match .index_uid {
+        Some(uid) if !uid.is_empty() => format!("Index `{}`: {error}", uid),
+        _ => format!("{error}")
+    })]
+    Milli { error: milli::Error, index_uid: Option<String> },
     #[error("An unexpected crash occurred when processing the task.")]
     ProcessBatchPanicked,
     #[error(transparent)]
@@ -190,7 +193,7 @@ impl Error {
             | Error::AbortedTask
             | Error::Dump(_)
             | Error::Heed(_)
-            | Error::Milli(_)
+            | Error::Milli { .. }
             | Error::ProcessBatchPanicked
             | Error::FileStore(_)
             | Error::IoError(_)
@@ -209,6 +212,20 @@ impl Error {
     pub fn with_custom_error_code(self, code: Code) -> Self {
         Self::WithCustomErrorCode(code, Box::new(self))
     }
+
+    pub fn from_milli(err: milli::Error, index_uid: Option<String>) -> Self {
+        match err {
+            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
+                Self::Milli { error: err, index_uid }
+                    .with_custom_error_code(Code::InvalidDocumentFilter)
+            }
+            milli::Error::UserError(milli::UserError::InvalidFilterExpression { .. }) => {
+                Self::Milli { error: err, index_uid }
+                    .with_custom_error_code(Code::InvalidDocumentFilter)
+            }
+            _ => Self::Milli { error: err, index_uid },
+        }
+    }
 }
 
 impl ErrorCode for Error {
@@ -236,7 +253,7 @@ impl ErrorCode for Error {
             // TODO: not sure of the Code to use
             Error::NoSpaceLeftInTaskQueue => Code::NoSpaceLeftOnDevice,
             Error::Dump(e) => e.error_code(),
-            Error::Milli(e) => e.error_code(),
+            Error::Milli { error, .. } => error.error_code(),
             Error::ProcessBatchPanicked => Code::Internal,
             Error::Heed(e) => e.error_code(),
             Error::HeedTransaction(e) => e.error_code(),

crates/index-scheduler/src/index_mapper/index_map.rs

@@ -3,14 +3,13 @@ use std::path::Path;
 use std::time::Duration;
 
 use meilisearch_types::heed::{EnvClosingEvent, EnvFlags, EnvOpenOptions};
-use meilisearch_types::milli::Index;
+use meilisearch_types::milli::{Index, Result};
 use time::OffsetDateTime;
 use uuid::Uuid;
 
 use super::IndexStatus::{self, Available, BeingDeleted, Closing, Missing};
+use crate::clamp_to_page_size;
 use crate::lru::{InsertionOutcome, LruMap};
-use crate::{clamp_to_page_size, Result};
-
 /// Keep an internally consistent view of the open indexes in memory.
 ///
 /// This view is made of an LRU cache that will evict the least frequently used indexes when new indexes are opened.

crates/index-scheduler/src/index_mapper/mod.rs

@@ -5,6 +5,7 @@ use std::{fs, thread};
 
 use meilisearch_types::heed::types::{SerdeJson, Str};
 use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
+use meilisearch_types::milli;
 use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::{FieldDistribution, Index};
 use serde::{Deserialize, Serialize};
@@ -121,7 +122,7 @@ impl IndexStats {
     /// # Parameters
     ///
     /// - rtxn: a RO transaction for the index, obtained from `Index::read_txn()`.
-    pub fn new(index: &Index, rtxn: &RoTxn) -> Result<Self> {
+    pub fn new(index: &Index, rtxn: &RoTxn) -> milli::Result<Self> {
         Ok(IndexStats {
             number_of_documents: index.number_of_documents(rtxn)?,
             database_size: index.on_disk_size()?,
@@ -183,13 +184,18 @@ impl IndexMapper {
                 // Error if the UUIDv4 somehow already exists in the map, since it should be fresh.
                 // This is very unlikely to happen in practice.
                 // TODO: it would be better to lazily create the index. But we need an Index::open function for milli.
-                let index = self.index_map.write().unwrap().create(
-                    &uuid,
-                    &index_path,
-                    date,
-                    self.enable_mdb_writemap,
-                    self.index_base_map_size,
-                )?;
+                let index = self
+                    .index_map
+                    .write()
+                    .unwrap()
+                    .create(
+                        &uuid,
+                        &index_path,
+                        date,
+                        self.enable_mdb_writemap,
+                        self.index_base_map_size,
+                    )
+                    .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
 
                 wtxn.commit()?;
 
@@ -357,7 +363,9 @@ impl IndexMapper {
                     };
                     let index_path = self.base_path.join(uuid.to_string());
                     // take the lock to reopen the environment.
-                    reopen.reopen(&mut self.index_map.write().unwrap(), &index_path)?;
+                    reopen
+                        .reopen(&mut self.index_map.write().unwrap(), &index_path)
+                        .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
                     continue;
                 }
                 BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
@@ -372,13 +380,15 @@ impl IndexMapper {
                         Missing => {
                             let index_path = self.base_path.join(uuid.to_string());
 
-                            break index_map.create(
-                                &uuid,
-                                &index_path,
-                                None,
-                                self.enable_mdb_writemap,
-                                self.index_base_map_size,
-                            )?;
+                            break index_map
+                                .create(
+                                    &uuid,
+                                    &index_path,
+                                    None,
+                                    self.enable_mdb_writemap,
+                                    self.index_base_map_size,
+                                )
+                                .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
                         }
                         Available(index) => break index,
                         Closing(_) => {
@@ -460,6 +470,7 @@ impl IndexMapper {
                 let index = self.index(rtxn, index_uid)?;
                 let index_rtxn = index.read_txn()?;
                 IndexStats::new(&index, &index_rtxn)
+                    .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))
             }
         }
     }

crates/index-scheduler/src/insta_snapshot.rs

@@ -353,7 +353,7 @@ pub fn snapshot_canceled_by(rtxn: &RoTxn, db: Database<BEU32, RoaringBitmapCodec
 
 pub fn snapshot_batch(batch: &Batch) -> String {
     let mut snap = String::new();
-    let Batch { uid, details, stats, started_at, finished_at } = batch;
+    let Batch { uid, details, stats, started_at, finished_at, progress: _ } = batch;
     if let Some(finished_at) = finished_at {
         assert!(finished_at > started_at);
     }

crates/index-scheduler/src/lib.rs

@@ -26,6 +26,7 @@ mod index_mapper;
 #[cfg(test)]
 mod insta_snapshot;
 mod lru;
+mod processing;
 mod utils;
 pub mod uuid_codec;
 
@@ -61,6 +62,7 @@ use meilisearch_types::milli::vector::{Embedder, EmbedderOptions, EmbeddingConfi
 use meilisearch_types::milli::{self, CboRoaringBitmapCodec, Index, RoaringBitmapCodec, BEU32};
 use meilisearch_types::task_view::TaskView;
 use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
+use processing::ProcessingTasks;
 use rayon::current_num_threads;
 use rayon::prelude::{IntoParallelIterator, ParallelIterator};
 use roaring::RoaringBitmap;
@@ -71,7 +73,8 @@ use utils::{filter_out_references_to_newer_tasks, keep_ids_within_datetimes, map
 use uuid::Uuid;
 
 use crate::index_mapper::IndexMapper;
-use crate::utils::{check_index_swap_validity, clamp_to_page_size, ProcessingBatch};
+use crate::processing::{AtomicTaskStep, BatchProgress};
+use crate::utils::{check_index_swap_validity, clamp_to_page_size};
 
 pub(crate) type BEI128 = I128<BE>;
 
@@ -162,39 +165,6 @@ impl Query {
     }
 }
 
-#[derive(Debug, Clone)]
-pub struct ProcessingTasks {
-    batch: Option<ProcessingBatch>,
-    /// The list of tasks ids that are currently running.
-    processing: RoaringBitmap,
-}
-
-impl ProcessingTasks {
-    /// Creates an empty `ProcessingAt` struct.
-    fn new() -> ProcessingTasks {
-        ProcessingTasks { batch: None, processing: RoaringBitmap::new() }
-    }
-
-    /// Stores the currently processing tasks, and the date time at which it started.
-    fn start_processing(&mut self, processing_batch: ProcessingBatch, processing: RoaringBitmap) {
-        self.batch = Some(processing_batch);
-        self.processing = processing;
-    }
-
-    /// Set the processing tasks to an empty list
-    fn stop_processing(&mut self) -> Self {
-        Self {
-            batch: std::mem::take(&mut self.batch),
-            processing: std::mem::take(&mut self.processing),
-        }
-    }
-
-    /// Returns `true` if there, at least, is one task that is currently processing that we must stop.
-    fn must_cancel_processing_tasks(&self, canceled_tasks: &RoaringBitmap) -> bool {
-        !self.processing.is_disjoint(canceled_tasks)
-    }
-}
-
 #[derive(Default, Clone, Debug)]
 struct MustStopProcessing(Arc<AtomicBool>);
 
@@ -397,7 +367,7 @@ pub struct IndexScheduler {
     ///
     /// See [self.breakpoint()](`IndexScheduler::breakpoint`) for an explanation.
     #[cfg(test)]
-    test_breakpoint_sdr: crossbeam::channel::Sender<(Breakpoint, bool)>,
+    test_breakpoint_sdr: crossbeam_channel::Sender<(Breakpoint, bool)>,
 
     /// A list of planned failures within the [`tick`](IndexScheduler::tick) method of the index scheduler.
     ///
@@ -466,7 +436,7 @@ impl IndexScheduler {
     /// Create an index scheduler and start its run loop.
     pub fn new(
         options: IndexSchedulerOptions,
-        #[cfg(test)] test_breakpoint_sdr: crossbeam::channel::Sender<(Breakpoint, bool)>,
+        #[cfg(test)] test_breakpoint_sdr: crossbeam_channel::Sender<(Breakpoint, bool)>,
         #[cfg(test)] planned_failures: Vec<(usize, tests::FailureLocation)>,
     ) -> Result<Self> {
         std::fs::create_dir_all(&options.tasks_path)?;
@@ -768,7 +738,7 @@ impl IndexScheduler {
 
     /// Return the task ids matched by the given query from the index scheduler's point of view.
     pub(crate) fn get_task_ids(&self, rtxn: &RoTxn, query: &Query) -> Result<RoaringBitmap> {
-        let ProcessingTasks { batch: processing_batch, processing: processing_tasks } =
+        let ProcessingTasks { batch: processing_batch, processing: processing_tasks, progress: _ } =
             self.processing_tasks.read().unwrap().clone();
         let Query {
             limit,
@@ -803,7 +773,7 @@ impl IndexScheduler {
             let mut batch_tasks = RoaringBitmap::new();
             for batch_uid in batch_uids {
                 if processing_batch.as_ref().map_or(false, |batch| batch.uid == *batch_uid) {
-                    batch_tasks |= &processing_tasks;
+                    batch_tasks |= &*processing_tasks;
                 } else {
                     batch_tasks |= self.tasks_in_batch(rtxn, *batch_uid)?;
                 }
@@ -817,13 +787,13 @@ impl IndexScheduler {
                 match status {
                     // special case for Processing tasks
                     Status::Processing => {
-                        status_tasks |= &processing_tasks;
+                        status_tasks |= &*processing_tasks;
                     }
                     status => status_tasks |= &self.get_status(rtxn, *status)?,
                 };
             }
             if !status.contains(&Status::Processing) {
-                tasks -= &processing_tasks;
+                tasks -= &*processing_tasks;
             }
             tasks &= status_tasks;
         }
@@ -872,7 +842,7 @@ impl IndexScheduler {
         // Once we have filtered the two subsets, we put them back together and assign it back to `tasks`.
         tasks = {
             let (mut filtered_non_processing_tasks, mut filtered_processing_tasks) =
-                (&tasks - &processing_tasks, &tasks & &processing_tasks);
+                (&tasks - &*processing_tasks, &tasks & &*processing_tasks);
 
             // special case for Processing tasks
             // A closure that clears the filtered_processing_tasks if their started_at date falls outside the given bounds
@@ -1080,7 +1050,7 @@ impl IndexScheduler {
         // Once we have filtered the two subsets, we put them back together and assign it back to `batches`.
         batches = {
             let (mut filtered_non_processing_batches, mut filtered_processing_batches) =
-                (&batches - &processing.processing, &batches & &processing.processing);
+                (&batches - &*processing.processing, &batches & &*processing.processing);
 
             // special case for Processing batches
             // A closure that clears the filtered_processing_batches if their started_at date falls outside the given bounds
@@ -1352,9 +1322,12 @@ impl IndexScheduler {
         let tasks =
             self.get_existing_tasks(&rtxn, tasks.take(query.limit.unwrap_or(u32::MAX) as usize))?;
 
-        let ProcessingTasks { batch, processing } =
+        let ProcessingTasks { batch, processing, progress } =
             self.processing_tasks.read().map_err(|_| Error::CorruptedTaskQueue)?.clone();
 
+        // ignored for now, might be added to batch details later
+        let _ = progress;
+
         let ret = tasks.into_iter();
         if processing.is_empty() || batch.is_none() {
             Ok((ret.collect(), total))
@@ -1427,7 +1400,7 @@ impl IndexScheduler {
 
         // if the task doesn't delete anything and 50% of the task queue is full, we must refuse to enqueue the incomming task
         if !matches!(&kind, KindWithContent::TaskDeletion { tasks, .. } if !tasks.is_empty())
-            && (self.env.non_free_pages_size()? * 100) / self.env.info().map_size as u64 > 50
+            && (self.env.non_free_pages_size()? * 100) / self.env.info().map_size as u64 > 40
         {
             return Err(Error::NoSpaceLeftInTaskQueue);
         }
@@ -1593,7 +1566,8 @@ impl IndexScheduler {
 
         // We reset the must_stop flag to be sure that we don't stop processing tasks
         self.must_stop_processing.reset();
-        self.processing_tasks
+        let progress = self
+            .processing_tasks
             .write()
             .unwrap()
             // We can clone the processing batch here because we don't want its modification to affect the view of the processing batches
@@ -1606,11 +1580,12 @@ impl IndexScheduler {
         let res = {
             let cloned_index_scheduler = self.private_clone();
             let processing_batch = &mut processing_batch;
+            let progress = progress.clone();
             std::thread::scope(|s| {
                 let handle = std::thread::Builder::new()
                     .name(String::from("batch-operation"))
                     .spawn_scoped(s, move || {
-                        cloned_index_scheduler.process_batch(batch, processing_batch)
+                        cloned_index_scheduler.process_batch(batch, processing_batch, progress)
                     })
                     .unwrap();
                 handle.join().unwrap_or(Err(Error::ProcessBatchPanicked))
@@ -1623,6 +1598,7 @@ impl IndexScheduler {
         #[cfg(test)]
         self.maybe_fail(tests::FailureLocation::AcquiringWtxn)?;
 
+        progress.update_progress(BatchProgress::WritingTasksToDisk);
         processing_batch.finished();
         let mut wtxn = self.env.write_txn().map_err(Error::HeedTransaction)?;
         let mut canceled = RoaringBitmap::new();
@@ -1632,12 +1608,15 @@ impl IndexScheduler {
                 #[cfg(test)]
                 self.breakpoint(Breakpoint::ProcessBatchSucceeded);
 
+                let (task_progress, task_progress_obj) = AtomicTaskStep::new(tasks.len() as u32);
+                progress.update_progress(task_progress_obj);
                 let mut success = 0;
                 let mut failure = 0;
                 let mut canceled_by = None;
 
                 #[allow(unused_variables)]
                 for (i, mut task) in tasks.into_iter().enumerate() {
+                    task_progress.fetch_add(1, Ordering::Relaxed);
                     processing_batch.update(&mut task);
                     if task.status == Status::Canceled {
                         canceled.insert(task.uid);
@@ -1665,9 +1644,10 @@ impl IndexScheduler {
                 tracing::info!("A batch of tasks was successfully completed with {success} successful tasks and {failure} failed tasks.");
             }
             // If we have an abortion error we must stop the tick here and re-schedule tasks.
-            Err(Error::Milli(milli::Error::InternalError(
-                milli::InternalError::AbortedIndexation,
-            )))
+            Err(Error::Milli {
+                error: milli::Error::InternalError(milli::InternalError::AbortedIndexation),
+                ..
+            })
             | Err(Error::AbortedTask) => {
                 #[cfg(test)]
                 self.breakpoint(Breakpoint::AbortedIndexation);
@@ -1686,9 +1666,10 @@ impl IndexScheduler {
             // 2. close the associated environment
             // 3. resize it
             // 4. re-schedule tasks
-            Err(Error::Milli(milli::Error::UserError(
-                milli::UserError::MaxDatabaseSizeReached,
-            ))) if index_uid.is_some() => {
+            Err(Error::Milli {
+                error: milli::Error::UserError(milli::UserError::MaxDatabaseSizeReached),
+                ..
+            }) if index_uid.is_some() => {
                 // fixme: add index_uid to match to avoid the unwrap
                 let index_uid = index_uid.unwrap();
                 // fixme: handle error more gracefully? not sure when this could happen
@@ -1703,8 +1684,12 @@ impl IndexScheduler {
             Err(err) => {
                 #[cfg(test)]
                 self.breakpoint(Breakpoint::ProcessBatchFailed);
+                let (task_progress, task_progress_obj) = AtomicTaskStep::new(ids.len() as u32);
+                progress.update_progress(task_progress_obj);
+
                 let error: ResponseError = err.into();
                 for id in ids.iter() {
+                    task_progress.fetch_add(1, Ordering::Relaxed);
                     let mut task = self
                         .get_task(&wtxn, id)
                         .map_err(|e| Error::TaskDatabaseUpdate(Box::new(e)))?
@@ -1725,11 +1710,8 @@ impl IndexScheduler {
             }
         }
 
-        self.processing_tasks.write().unwrap().stop_processing();
         // We must re-add the canceled task so they're part of the same batch.
-        // processed.processing |= canceled;
         ids |= canceled;
-
         self.write_batch(&mut wtxn, processing_batch, &ids)?;
 
         #[cfg(test)]
@@ -1737,6 +1719,10 @@ impl IndexScheduler {
 
         wtxn.commit().map_err(Error::HeedTransaction)?;
 
+        // We should stop processing AFTER everything is processed and written to disk otherwise, a batch (which only lives in RAM) may appear in the processing task
+        // and then become « not found » for some time until the commit everything is written and the final commit is made.
+        self.processing_tasks.write().unwrap().stop_processing();
+
         // Once the tasks are committed, we should delete all the update files associated ASAP to avoid leaking files in case of a restart
         tracing::debug!("Deleting the update files");
 
@@ -1929,6 +1915,7 @@ impl IndexScheduler {
     // TODO: consider using a type alias or a struct embedder/template
     pub fn embedders(
         &self,
+        index_uid: String,
         embedding_configs: Vec<IndexEmbeddingConfig>,
     ) -> Result<EmbeddingConfigs> {
         let res: Result<_> = embedding_configs
@@ -1939,8 +1926,12 @@ impl IndexScheduler {
                      config: milli::vector::EmbeddingConfig { embedder_options, prompt, quantized },
                      ..
                  }| {
-                    let prompt =
-                        Arc::new(prompt.try_into().map_err(meilisearch_types::milli::Error::from)?);
+                    let prompt = Arc::new(
+                        prompt
+                            .try_into()
+                            .map_err(meilisearch_types::milli::Error::from)
+                            .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
+                    );
                     // optimistically return existing embedder
                     {
                         let embedders = self.embedders.read().unwrap();
@@ -1956,7 +1947,9 @@ impl IndexScheduler {
                     let embedder = Arc::new(
                         Embedder::new(embedder_options.clone())
                             .map_err(meilisearch_types::milli::vector::Error::from)
-                            .map_err(meilisearch_types::milli::Error::from)?,
+                            .map_err(|err| {
+                                Error::from_milli(err.into(), Some(index_uid.clone()))
+                            })?,
                     );
                     {
                         let mut embedders = self.embedders.write().unwrap();
@@ -2224,7 +2217,7 @@ mod tests {
     use std::time::Instant;
 
     use big_s::S;
-    use crossbeam::channel::RecvTimeoutError;
+    use crossbeam_channel::RecvTimeoutError;
     use file_store::File;
     use insta::assert_json_snapshot;
     use maplit::btreeset;
@@ -2276,7 +2269,7 @@ mod tests {
             configuration: impl Fn(&mut IndexSchedulerOptions),
         ) -> (Self, IndexSchedulerHandle) {
             let tempdir = TempDir::new().unwrap();
-            let (sender, receiver) = crossbeam::channel::bounded(0);
+            let (sender, receiver) = crossbeam_channel::bounded(0);
 
             let indexer_config = IndexerConfig { skip_index_budget: true, ..Default::default() };
 
@@ -2290,7 +2283,7 @@ mod tests {
                 dumps_path: tempdir.path().join("dumps"),
                 webhook_url: None,
                 webhook_authorization_header: None,
-                task_db_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
+                task_db_size: 1000 * 1000 * 10, // 10 MB, we don't use MiB on purpose.
                 index_base_map_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
                 enable_mdb_writemap: false,
                 index_growth_amount: 1000 * 1000 * 1000 * 1000, // 1 TB
@@ -2408,7 +2401,7 @@ mod tests {
     pub struct IndexSchedulerHandle {
         _tempdir: TempDir,
         index_scheduler: IndexScheduler,
-        test_breakpoint_rcv: crossbeam::channel::Receiver<(Breakpoint, bool)>,
+        test_breakpoint_rcv: crossbeam_channel::Receiver<(Breakpoint, bool)>,
         last_breakpoint: Breakpoint,
     }
 
@@ -4305,10 +4298,35 @@ mod tests {
         let proc = index_scheduler.processing_tasks.read().unwrap().clone();
 
         let query = Query { statuses: Some(vec![Status::Processing]), ..Default::default() };
-        let (batches, _) = index_scheduler
-            .get_batch_ids_from_authorized_indexes(&rtxn, &proc, &query, &AuthFilter::default())
+        let (mut batches, _) = index_scheduler
+            .get_batches_from_authorized_indexes(query.clone(), &AuthFilter::default())
             .unwrap();
-        snapshot!(snapshot_bitmap(&batches), @"[0,]"); // only the processing batch in the first tick
+        assert_eq!(batches.len(), 1);
+        batches[0].started_at = OffsetDateTime::UNIX_EPOCH;
+        // Insta cannot snapshot our batches because the batch stats contains an enum as key: https://github.com/mitsuhiko/insta/issues/689
+        let batch = serde_json::to_string_pretty(&batches[0]).unwrap();
+        snapshot!(batch, @r#"
+        {
+          "uid": 0,
+          "details": {
+            "primaryKey": "mouse"
+          },
+          "stats": {
+            "totalNbTasks": 1,
+            "status": {
+              "processing": 1
+            },
+            "types": {
+              "indexCreation": 1
+            },
+            "indexUids": {
+              "catto": 1
+            }
+          },
+          "startedAt": "1970-01-01T00:00:00Z",
+          "finishedAt": null
+        }
+        "#);
 
         let query = Query { statuses: Some(vec![Status::Enqueued]), ..Default::default() };
         let (batches, _) = index_scheduler
@@ -5186,12 +5204,10 @@ mod tests {
         handle.advance_one_successful_batch();
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "only_first_task_succeed");
 
-        // The second batch should fail.
-        handle.advance_one_failed_batch();
+        handle.advance_one_successful_batch();
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "second_task_fails");
 
-        // The second batch should fail.
-        handle.advance_one_failed_batch();
+        handle.advance_one_successful_batch();
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "third_task_fails");
 
         // Is the primary key still what we expect?
@@ -5251,8 +5267,7 @@ mod tests {
         handle.advance_one_successful_batch();
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "only_first_task_succeed");
 
-        // The second batch should fail and contains two tasks.
-        handle.advance_one_failed_batch();
+        handle.advance_one_successful_batch();
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "second_and_third_tasks_fails");
 
         // Is the primary key still what we expect?
@@ -5331,7 +5346,8 @@ mod tests {
         snapshot!(primary_key, @"id");
 
         // We're trying to `bork` again, but now there is already a primary key set for this index.
-        handle.advance_one_failed_batch();
+        // NOTE: it's marked as successful because the batch didn't fails, it's the individual tasks that failed.
+        handle.advance_one_successful_batch();
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "fourth_task_fails");
 
         // Finally the last task should succeed since its primary key is the same as the valid one.
@@ -5491,7 +5507,7 @@ mod tests {
         snapshot!(primary_key.is_none(), @"false");
 
         // The second batch should contains only one task that fails because it tries to update the primary key to `bork`.
-        handle.advance_one_failed_batch();
+        handle.advance_one_successful_batch();
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "second_task_fails");
 
         // The third batch should succeed and only contains one task.
@@ -6134,11 +6150,12 @@ mod tests {
             insta::assert_json_snapshot!(simple_hf_config.embedder_options);
             let simple_hf_name = name.clone();
 
-            let configs = index_scheduler.embedders(configs).unwrap();
+            let configs = index_scheduler.embedders("doggos".to_string(), configs).unwrap();
             let (hf_embedder, _, _) = configs.get(&simple_hf_name).unwrap();
-            let beagle_embed = hf_embedder.embed_one(S("Intel the beagle best doggo")).unwrap();
-            let lab_embed = hf_embedder.embed_one(S("Max the lab best doggo")).unwrap();
-            let patou_embed = hf_embedder.embed_one(S("kefir the patou best doggo")).unwrap();
+            let beagle_embed =
+                hf_embedder.embed_one(S("Intel the beagle best doggo"), None).unwrap();
+            let lab_embed = hf_embedder.embed_one(S("Max the lab best doggo"), None).unwrap();
+            let patou_embed = hf_embedder.embed_one(S("kefir the patou best doggo"), None).unwrap();
             (fakerest_name, simple_hf_name, beagle_embed, lab_embed, patou_embed)
         };
 

crates/index-scheduler/src/processing.rs

@@ -0,0 +1,316 @@
+use std::borrow::Cow;
+use std::sync::Arc;
+
+use enum_iterator::Sequence;
+use meilisearch_types::milli::progress::{AtomicSubStep, NamedStep, Progress, ProgressView, Step};
+use meilisearch_types::milli::{make_atomic_progress, make_enum_progress};
+use roaring::RoaringBitmap;
+
+use crate::utils::ProcessingBatch;
+
+#[derive(Clone)]
+pub struct ProcessingTasks {
+    pub batch: Option<Arc<ProcessingBatch>>,
+    /// The list of tasks ids that are currently running.
+    pub processing: Arc<RoaringBitmap>,
+    /// The progress on processing tasks
+    pub progress: Option<Progress>,
+}
+
+impl ProcessingTasks {
+    /// Creates an empty `ProcessingAt` struct.
+    pub fn new() -> ProcessingTasks {
+        ProcessingTasks { batch: None, processing: Arc::new(RoaringBitmap::new()), progress: None }
+    }
+
+    pub fn get_progress_view(&self) -> Option<ProgressView> {
+        Some(self.progress.as_ref()?.as_progress_view())
+    }
+
+    /// Stores the currently processing tasks, and the date time at which it started.
+    pub fn start_processing(
+        &mut self,
+        processing_batch: ProcessingBatch,
+        processing: RoaringBitmap,
+    ) -> Progress {
+        self.batch = Some(Arc::new(processing_batch));
+        self.processing = Arc::new(processing);
+        let progress = Progress::default();
+        progress.update_progress(BatchProgress::ProcessingTasks);
+        self.progress = Some(progress.clone());
+
+        progress
+    }
+
+    /// Set the processing tasks to an empty list
+    pub fn stop_processing(&mut self) -> Self {
+        self.progress = None;
+
+        Self {
+            batch: std::mem::take(&mut self.batch),
+            processing: std::mem::take(&mut self.processing),
+            progress: None,
+        }
+    }
+
+    /// Returns `true` if there, at least, is one task that is currently processing that we must stop.
+    pub fn must_cancel_processing_tasks(&self, canceled_tasks: &RoaringBitmap) -> bool {
+        !self.processing.is_disjoint(canceled_tasks)
+    }
+}
+
+make_enum_progress! {
+    pub enum BatchProgress {
+        ProcessingTasks,
+        WritingTasksToDisk,
+    }
+}
+
+make_enum_progress! {
+    pub enum TaskCancelationProgress {
+        RetrievingTasks,
+        UpdatingTasks,
+    }
+}
+
+make_enum_progress! {
+    pub enum TaskDeletionProgress {
+        DeletingTasksDateTime,
+        DeletingTasksMetadata,
+        DeletingTasks,
+        DeletingBatches,
+    }
+}
+
+make_enum_progress! {
+    pub enum SnapshotCreationProgress {
+        StartTheSnapshotCreation,
+        SnapshotTheIndexScheduler,
+        SnapshotTheUpdateFiles,
+        SnapshotTheIndexes,
+        SnapshotTheApiKeys,
+        CreateTheTarball,
+    }
+}
+
+make_enum_progress! {
+    pub enum DumpCreationProgress {
+        StartTheDumpCreation,
+        DumpTheApiKeys,
+        DumpTheTasks,
+        DumpTheIndexes,
+        DumpTheExperimentalFeatures,
+        CompressTheDump,
+    }
+}
+
+make_enum_progress! {
+    pub enum CreateIndexProgress {
+        CreatingTheIndex,
+    }
+}
+
+make_enum_progress! {
+    pub enum UpdateIndexProgress {
+        UpdatingTheIndex,
+    }
+}
+
+make_enum_progress! {
+    pub enum DeleteIndexProgress {
+        DeletingTheIndex,
+    }
+}
+
+make_enum_progress! {
+    pub enum SwappingTheIndexes {
+        EnsuringCorrectnessOfTheSwap,
+        SwappingTheIndexes,
+    }
+}
+
+make_enum_progress! {
+    pub enum InnerSwappingTwoIndexes {
+        RetrieveTheTasks,
+        UpdateTheTasks,
+        UpdateTheIndexesMetadata,
+    }
+}
+
+make_enum_progress! {
+    pub enum DocumentOperationProgress {
+        RetrievingConfig,
+        ComputingDocumentChanges,
+        Indexing,
+    }
+}
+
+make_enum_progress! {
+    pub enum DocumentEditionProgress {
+        RetrievingConfig,
+        ComputingDocumentChanges,
+        Indexing,
+    }
+}
+
+make_enum_progress! {
+    pub enum DocumentDeletionProgress {
+        RetrievingConfig,
+        DeleteDocuments,
+        Indexing,
+    }
+}
+
+make_enum_progress! {
+    pub enum SettingsProgress {
+        RetrievingAndMergingTheSettings,
+        ApplyTheSettings,
+    }
+}
+
+make_atomic_progress!(Task alias AtomicTaskStep => "task" );
+make_atomic_progress!(Document alias AtomicDocumentStep => "document" );
+make_atomic_progress!(Batch alias AtomicBatchStep => "batch" );
+make_atomic_progress!(UpdateFile alias AtomicUpdateFileStep => "update file" );
+
+pub struct VariableNameStep {
+    name: String,
+    current: u32,
+    total: u32,
+}
+
+impl VariableNameStep {
+    pub fn new(name: impl Into<String>, current: u32, total: u32) -> Self {
+        Self { name: name.into(), current, total }
+    }
+}
+
+impl Step for VariableNameStep {
+    fn name(&self) -> Cow<'static, str> {
+        self.name.clone().into()
+    }
+
+    fn current(&self) -> u32 {
+        self.current
+    }
+
+    fn total(&self) -> u32 {
+        self.total
+    }
+}
+
+#[cfg(test)]
+mod test {
+    use std::sync::atomic::Ordering;
+
+    use meili_snap::{json_string, snapshot};
+
+    use super::*;
+
+    #[test]
+    fn one_level() {
+        let mut processing = ProcessingTasks::new();
+        processing.start_processing(ProcessingBatch::new(0), RoaringBitmap::new());
+        snapshot!(json_string!(processing.get_progress_view()), @r#"
+        {
+          "steps": [
+            {
+              "currentStep": "processing tasks",
+              "finished": 0,
+              "total": 2
+            }
+          ],
+          "percentage": 0.0
+        }
+        "#);
+        processing.progress.as_ref().unwrap().update_progress(BatchProgress::WritingTasksToDisk);
+        snapshot!(json_string!(processing.get_progress_view()), @r#"
+        {
+          "steps": [
+            {
+              "currentStep": "writing tasks to disk",
+              "finished": 1,
+              "total": 2
+            }
+          ],
+          "percentage": 50.0
+        }
+        "#);
+    }
+
+    #[test]
+    fn task_progress() {
+        let mut processing = ProcessingTasks::new();
+        processing.start_processing(ProcessingBatch::new(0), RoaringBitmap::new());
+        let (atomic, tasks) = AtomicTaskStep::new(10);
+        processing.progress.as_ref().unwrap().update_progress(tasks);
+        snapshot!(json_string!(processing.get_progress_view()), @r#"
+        {
+          "steps": [
+            {
+              "currentStep": "processing tasks",
+              "finished": 0,
+              "total": 2
+            },
+            {
+              "currentStep": "task",
+              "finished": 0,
+              "total": 10
+            }
+          ],
+          "percentage": 0.0
+        }
+        "#);
+        atomic.fetch_add(6, Ordering::Relaxed);
+        snapshot!(json_string!(processing.get_progress_view()), @r#"
+        {
+          "steps": [
+            {
+              "currentStep": "processing tasks",
+              "finished": 0,
+              "total": 2
+            },
+            {
+              "currentStep": "task",
+              "finished": 6,
+              "total": 10
+            }
+          ],
+          "percentage": 30.000002
+        }
+        "#);
+        processing.progress.as_ref().unwrap().update_progress(BatchProgress::WritingTasksToDisk);
+        snapshot!(json_string!(processing.get_progress_view()), @r#"
+        {
+          "steps": [
+            {
+              "currentStep": "writing tasks to disk",
+              "finished": 1,
+              "total": 2
+            }
+          ],
+          "percentage": 50.0
+        }
+        "#);
+        let (atomic, tasks) = AtomicTaskStep::new(5);
+        processing.progress.as_ref().unwrap().update_progress(tasks);
+        atomic.fetch_add(4, Ordering::Relaxed);
+        snapshot!(json_string!(processing.get_progress_view()), @r#"
+        {
+          "steps": [
+            {
+              "currentStep": "writing tasks to disk",
+              "finished": 1,
+              "total": 2
+            },
+            {
+              "currentStep": "task",
+              "finished": 4,
+              "total": 5
+            }
+          ],
+          "percentage": 90.0
+        }
+        "#);
+    }
+}

crates/index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/aborted_indexation.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(1):
 [1,]
-{uid: 1, details: {"receivedDocuments":2,"indexedDocuments":null}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"documentAdditionOrUpdate":2},"indexUids":{"beavero":2}}, }
+{uid: 1, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"beavero":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, batch_uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}

crates/index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/processing_second_task_cancel_enqueued.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(1):
 [1,]
-{uid: 1, details: {"receivedDocuments":2,"indexedDocuments":null}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"documentAdditionOrUpdate":2},"indexUids":{"beavero":2}}, }
+{uid: 1, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"beavero":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, batch_uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}

crates/index-scheduler/src/snapshots/lib.rs/cancel_processing_dump/cancel_registered.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"dumpUid":null}, stats: {"totalNbTasks":1,"status":{"enqueued":1},"types":{"dumpCreation":1},"indexUids":{}}, }
+{uid: 0, details: {"dumpUid":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"dumpCreation":1},"indexUids":{}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { dump_uid: None }, kind: DumpCreation { keys: [], instance_uid: None }}

crates/index-scheduler/src/snapshots/lib.rs/cancel_processing_task/aborted_indexation.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"receivedDocuments":2,"indexedDocuments":null}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"documentAdditionOrUpdate":2},"indexUids":{"catto":2}}, }
+{uid: 0, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"catto":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}

crates/index-scheduler/src/snapshots/lib.rs/cancel_processing_task/cancel_task_registered.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"receivedDocuments":2,"indexedDocuments":null}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"documentAdditionOrUpdate":2},"indexUids":{"catto":2}}, }
+{uid: 0, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"catto":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}

crates/index-scheduler/src/snapshots/lib.rs/cancel_processing_task/initial_task_processing.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"receivedDocuments":2,"indexedDocuments":null}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"documentAdditionOrUpdate":2},"indexUids":{"catto":2}}, }
+{uid: 0, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"catto":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}

crates/index-scheduler/src/snapshots/lib.rs/document_addition/after_the_batch_creation.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"receivedDocuments":2,"indexedDocuments":null}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"documentAdditionOrUpdate":2},"indexUids":{"doggos":2}}, }
+{uid: 0, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"doggos":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}

crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_addition/document_addition_batch_created.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"receivedDocuments":2,"indexedDocuments":null}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"documentAdditionOrUpdate":2},"indexUids":{"doggos":2}}, }
+{uid: 0, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"doggos":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_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 }}
+0 {uid: 0, batch_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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_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:

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_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 }}
+0 {uid: 0, batch_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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: 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:

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

@@ -1,17 +1,16 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_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 }}
+0 {uid: 0, batch_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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_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, batch_uid: 2, status: succeeded, details: { received_document_ids: 1, deleted_documents: Some(1) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
-3 {uid: 3, batch_uid: 2, 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, batch_uid: 2, 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") }}
+3 {uid: 3, batch_uid: 2, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: 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, batch_uid: 2, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: 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, batch_uid: 2, status: succeeded, details: { original_filter: "catto EXISTS", deleted_documents: Some(1) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
 ----------------------------------------------------------------------
 ### Status:

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_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 }}
+0 {uid: 0, batch_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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_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) }}

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### 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 }}
+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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: 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:

crates/index-scheduler/src/snapshots/lib.rs/fail_in_update_task_after_process_batch_success_for_document_addition/after_batch_succeeded.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"receivedDocuments":2,"indexedDocuments":null}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"documentAdditionOrUpdate":2},"indexUids":{"doggos":2}}, }
+{uid: 0, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"doggos":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}

crates/index-scheduler/src/snapshots/lib.rs/fail_in_update_task_after_process_batch_success_for_document_addition/after_failing_to_commit.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"receivedDocuments":2,"indexedDocuments":null}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"documentAdditionOrUpdate":2},"indexUids":{"doggos":2}}, }
+{uid: 0, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"doggos":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_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 }}
+0 {uid: 0, batch_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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_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, batch_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 }}
 ----------------------------------------------------------------------
@@ -23,7 +22,7 @@ succeeded [0,1,2,]
 doggos [0,1,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
+doggos: { number_of_documents: 1, field_distribution: {"breed": 1, "doggo": 1, "id": 1} }
 
 ----------------------------------------------------------------------
 ### Canceled By:

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_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 }}
+0 {uid: 0, batch_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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_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 }}
 ----------------------------------------------------------------------
@@ -23,7 +22,7 @@ succeeded [0,1,]
 doggos [0,1,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
+doggos: { number_of_documents: 1, field_distribution: {"breed": 1, "doggo": 1, "id": 1} }
 
 ----------------------------------------------------------------------
 ### Canceled By:

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_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 }}
+0 {uid: 0, batch_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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_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:
@@ -22,7 +21,7 @@ succeeded [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
+doggos: { number_of_documents: 1, field_distribution: {"breed": 1, "doggo": 1, "id": 1} }
 
 ----------------------------------------------------------------------
 ### Canceled By:

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_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 }}
+0 {uid: 0, batch_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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: 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:

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### 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), 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 }}
+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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_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 }}
+0 {uid: 0, batch_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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

crates/index-scheduler/src/snapshots/lib.rs/insert_task_while_another_task_is_processing/after_batch_creation.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"primaryKey":"id"}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"indexCreation":2},"indexUids":{"index_a":2}}, }
+{uid: 0, details: {"primaryKey":"id"}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"indexCreation":1},"indexUids":{"index_a":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { primary_key: Some("id") }, kind: IndexCreation { index_uid: "index_a", primary_key: Some("id") }}

crates/index-scheduler/src/snapshots/lib.rs/insert_task_while_another_task_is_processing/registered_the_second_task.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"primaryKey":"id"}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"indexCreation":2},"indexUids":{"index_a":2}}, }
+{uid: 0, details: {"primaryKey":"id"}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"indexCreation":1},"indexUids":{"index_a":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { primary_key: Some("id") }, kind: IndexCreation { index_uid: "index_a", primary_key: Some("id") }}

crates/index-scheduler/src/snapshots/lib.rs/insert_task_while_another_task_is_processing/registered_the_third_task.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"primaryKey":"id"}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"indexCreation":2},"indexUids":{"index_a":2}}, }
+{uid: 0, details: {"primaryKey":"id"}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"indexCreation":1},"indexUids":{"index_a":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { primary_key: Some("id") }, kind: IndexCreation { index_uid: "index_a", primary_key: Some("id") }}

crates/index-scheduler/src/snapshots/lib.rs/query_batches_simple/after-advancing-a-bit.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(1):
 [1,]
-{uid: 1, details: {"primaryKey":"sheep"}, stats: {"totalNbTasks":2,"status":{"enqueued":2},"types":{"indexCreation":2},"indexUids":{"doggo":2}}, }
+{uid: 1, details: {"primaryKey":"sheep"}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, batch_uid: 0, status: succeeded, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}

crates/index-scheduler/src/snapshots/lib.rs/task_deletion_undeleteable/task_deletion_processing.snap

@@ -5,7 +5,7 @@ snapshot_kind: text
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [3,]
-{uid: 0, details: {"matchedTasks":2,"deletedTasks":null,"originalFilter":"test_query"}, stats: {"totalNbTasks":1,"status":{"enqueued":1},"types":{"taskDeletion":1},"indexUids":{}}, }
+{uid: 0, details: {"matchedTasks":2,"deletedTasks":null,"originalFilter":"test_query"}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"taskDeletion":1},"indexUids":{}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### 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), 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 }}
+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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/lib.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_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 }}
+0 {uid: 0, batch_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, facet_search: NotSet, prefix_search: 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, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

crates/index-scheduler/src/utils.rs

@@ -67,7 +67,7 @@ impl ProcessingBatch {
             task.batch_uid = Some(self.uid);
             // We don't store the statuses in the map since they're all enqueued but we must
             // still store them in the stats since that can be displayed.
-            *self.stats.status.entry(task.status).or_default() += 1;
+            *self.stats.status.entry(Status::Processing).or_default() += 1;
 
             self.kinds.insert(task.kind.as_kind());
             *self.stats.types.entry(task.kind.as_kind()).or_default() += 1;
@@ -106,7 +106,7 @@ impl ProcessingBatch {
         self.stats.total_nb_tasks = 0;
     }
 
-    /// Update the timestamp of the tasks and the inner structure of this sturcture.
+    /// Update the timestamp of the tasks and the inner structure of this structure.
     pub fn update(&mut self, task: &mut Task) {
         // We must re-set this value in case we're dealing with a task that has been added between
         // the `processing` and `finished` state
@@ -134,6 +134,7 @@ impl ProcessingBatch {
     pub fn to_batch(&self) -> Batch {
         Batch {
             uid: self.uid,
+            progress: None,
             details: self.details.clone(),
             stats: self.stats.clone(),
             started_at: self.started_at,
@@ -187,6 +188,7 @@ impl IndexScheduler {
             &batch.uid,
             &Batch {
                 uid: batch.uid,
+                progress: None,
                 details: batch.details,
                 stats: batch.stats,
                 started_at: batch.started_at,
@@ -273,7 +275,9 @@ impl IndexScheduler {
             .into_iter()
             .map(|batch_id| {
                 if Some(batch_id) == processing.batch.as_ref().map(|batch| batch.uid) {
-                    Ok(processing.batch.as_ref().unwrap().to_batch())
+                    let mut batch = processing.batch.as_ref().unwrap().to_batch();
+                    batch.progress = processing.get_progress_view();
+                    Ok(batch)
                 } else {
                     self.get_batch(rtxn, batch_id)
                         .and_then(|task| task.ok_or(Error::CorruptedTaskQueue))

crates/meili-snap/Cargo.toml

@@ -11,6 +11,7 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-insta = { version = "^1.39.0", features = ["json", "redactions"] }
+# fixed version due to format breakages in v1.40
+insta = { version = "=1.39.0", features = ["json", "redactions"] }
 md5 = "0.7.0"
 once_cell = "1.19"

crates/meilisearch-auth/Cargo.toml

@@ -17,7 +17,7 @@ hmac = "0.12.1"
 maplit = "1.0.2"
 meilisearch-types = { path = "../meilisearch-types" }
 rand = "0.8.5"
-roaring = { version = "0.10.6", features = ["serde"] }
+roaring = { version = "0.10.7", features = ["serde"] }
 serde = { version = "1.0.204", features = ["derive"] }
 serde_json = { version = "1.0.120", features = ["preserve_order"] }
 sha2 = "0.10.8"

crates/meilisearch-types/Cargo.toml

@@ -13,6 +13,7 @@ license.workspace = true
 [dependencies]
 actix-web = { version = "4.8.0", default-features = false }
 anyhow = "1.0.86"
+bumpalo = "3.16.0"
 convert_case = "0.6.0"
 csv = "1.3.0"
 deserr = { version = "0.6.2", features = ["actix-web"] }
@@ -23,7 +24,9 @@ flate2 = "1.0.30"
 fst = "0.4.7"
 memmap2 = "0.9.4"
 milli = { path = "../milli" }
-roaring = { version = "0.10.6", features = ["serde"] }
+bumparaw-collections = "0.1.2"
+roaring = { version = "0.10.7", features = ["serde"] }
+rustc-hash = "2.1.0"
 serde = { version = "1.0.204", features = ["derive"] }
 serde-cs = "0.2.4"
 serde_json = "1.0.120"
@@ -70,4 +73,3 @@ swedish-recomposition = ["milli/swedish-recomposition"]
 german = ["milli/german"]
 # allow turkish normalization
 turkish = ["milli/turkish"]
-

crates/meilisearch-types/src/batch_view.rs

@@ -1,16 +1,16 @@
+use milli::progress::ProgressView;
 use serde::Serialize;
 use time::{Duration, OffsetDateTime};
 
-use crate::{
-    batches::{Batch, BatchId, BatchStats},
-    task_view::DetailsView,
-    tasks::serialize_duration,
-};
+use crate::batches::{Batch, BatchId, BatchStats};
+use crate::task_view::DetailsView;
+use crate::tasks::serialize_duration;
 
 #[derive(Debug, Clone, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct BatchView {
     pub uid: BatchId,
+    pub progress: Option<ProgressView>,
     pub details: DetailsView,
     pub stats: BatchStats,
     #[serde(serialize_with = "serialize_duration", default)]
@@ -25,6 +25,7 @@ impl BatchView {
     pub fn from_batch(batch: &Batch) -> Self {
         Self {
             uid: batch.uid,
+            progress: batch.progress.clone(),
             details: batch.details.clone(),
             stats: batch.stats.clone(),
             duration: batch.finished_at.map(|finished_at| finished_at - batch.started_at),

crates/meilisearch-types/src/batches.rs

@@ -1,12 +1,11 @@
 use std::collections::BTreeMap;
 
+use milli::progress::ProgressView;
 use serde::{Deserialize, Serialize};
 use time::OffsetDateTime;
 
-use crate::{
-    task_view::DetailsView,
-    tasks::{Kind, Status},
-};
+use crate::task_view::DetailsView;
+use crate::tasks::{Kind, Status};
 
 pub type BatchId = u32;
 
@@ -15,6 +14,8 @@ pub type BatchId = u32;
 pub struct Batch {
     pub uid: BatchId,
 
+    #[serde(skip)]
+    pub progress: Option<ProgressView>,
     pub details: DetailsView,
     pub stats: BatchStats,
 

crates/meilisearch-types/src/document_formats.rs

@@ -1,20 +1,25 @@
 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 bumpalo::Bump;
+use bumparaw_collections::RawMap;
+use memmap2::Mmap;
+use milli::documents::Error;
 use milli::Object;
+use rustc_hash::FxBuildHasher;
 use serde::de::{SeqAccess, Visitor};
 use serde::{Deserialize, Deserializer};
 use serde_json::error::Category;
+use serde_json::value::RawValue;
+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 +93,26 @@ 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 +128,151 @@ 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)
+#[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 deserialize into a RawMap 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 doc_alloc = Bump::with_capacity(1024 * 1024); // 1MiB
+
+    let mut out = BufWriter::new(output);
+    let mut deserializer = serde_json::Deserializer::from_slice(&input);
+    let res = array_each(&mut deserializer, |obj: &RawValue| {
+        doc_alloc.reset();
+        let map = RawMap::from_raw_value_and_hasher(obj, FxBuildHasher, &doc_alloc)?;
+        to_writer(&mut out, &map)
+    });
+    let count = match res {
         // 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())),
+    }
+}
+
+/// Reads NDJSON from file and checks it.
+pub fn read_ndjson(input: &File) -> Result<u64> {
+    // We memory map to be able to deserialize into a RawMap 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 bump = Bump::with_capacity(1024 * 1024);
+
+    let mut count = 0;
+    for result in serde_json::Deserializer::from_slice(&input).into_iter() {
+        bump.reset();
+        match result {
+            Ok(raw) => {
+                // try to deserialize as a map
+                RawMap::from_raw_value_and_hasher(raw, FxBuildHasher, &bump)
+                    .map_err(|e| DocumentFormatError::from((PayloadType::Ndjson, e)))?;
+                count += 1;
+            }
+            Err(e) => return Err(DocumentFormatError::from((PayloadType::Ndjson, e))),
         }
     }
 
-    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)? };
-
-    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 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 +281,23 @@ 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 +306,7 @@ 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 +315,7 @@ where
                 match self.0(value) {
                     Ok(()) => max += 1,
                     Err(e) => return Ok(Err(e)),
-                };
+                }
             }
             Ok(Ok(max))
         }

crates/meilisearch-types/src/error.rs

@@ -279,6 +279,7 @@ InvalidSearchPage                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchQ                        , InvalidRequest       , BAD_REQUEST ;
 InvalidFacetSearchQuery               , InvalidRequest       , BAD_REQUEST ;
 InvalidFacetSearchName                , InvalidRequest       , BAD_REQUEST ;
+FacetSearchDisabled                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchVector                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowMatchesPosition      , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowRankingScore         , InvalidRequest       , BAD_REQUEST ;
@@ -290,6 +291,8 @@ InvalidSearchDistinct                 , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDisplayedAttributes    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDistinctAttribute      , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsProximityPrecision     , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsFacetSearch            , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsPrefixSearch           , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFaceting               , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFilterableAttributes   , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsPagination             , InvalidRequest       , BAD_REQUEST ;
@@ -547,7 +550,7 @@ impl fmt::Display for deserr_codes::InvalidSimilarId {
             "the value of `id` is invalid. \
             A document identifier can be of type integer or string, \
             only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), \
-            and can not be more than 512 bytes."
+            and can not be more than 511 bytes."
         )
     }
 }

crates/meilisearch-types/src/settings.rs

@@ -8,7 +8,7 @@ use std::str::FromStr;
 
 use deserr::{DeserializeError, Deserr, ErrorKind, MergeWithError, ValuePointerRef};
 use fst::IntoStreamer;
-use milli::index::IndexEmbeddingConfig;
+use milli::index::{IndexEmbeddingConfig, PrefixSearch};
 use milli::proximity::ProximityPrecision;
 use milli::update::Setting;
 use milli::{Criterion, CriterionError, Index, DEFAULT_VALUES_PER_FACET};
@@ -202,6 +202,12 @@ pub struct Settings<T> {
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsLocalizedAttributes>)]
     pub localized_attributes: Setting<Vec<LocalizedAttributesRuleView>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    #[deserr(default, error = DeserrJsonError<InvalidSettingsFacetSearch>)]
+    pub facet_search: Setting<bool>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    #[deserr(default, error = DeserrJsonError<InvalidSettingsPrefixSearch>)]
+    pub prefix_search: Setting<PrefixSearchSettings>,
 
     #[serde(skip)]
     #[deserr(skip)]
@@ -266,6 +272,8 @@ impl Settings<Checked> {
             embedders: Setting::Reset,
             search_cutoff_ms: Setting::Reset,
             localized_attributes: Setting::Reset,
+            facet_search: Setting::Reset,
+            prefix_search: Setting::Reset,
             _kind: PhantomData,
         }
     }
@@ -290,6 +298,8 @@ impl Settings<Checked> {
             embedders,
             search_cutoff_ms,
             localized_attributes: localized_attributes_rules,
+            facet_search,
+            prefix_search,
             _kind,
         } = self;
 
@@ -312,6 +322,8 @@ impl Settings<Checked> {
             embedders,
             search_cutoff_ms,
             localized_attributes: localized_attributes_rules,
+            facet_search,
+            prefix_search,
             _kind: PhantomData,
         }
     }
@@ -360,6 +372,8 @@ impl Settings<Unchecked> {
             embedders: self.embedders,
             search_cutoff_ms: self.search_cutoff_ms,
             localized_attributes: self.localized_attributes,
+            facet_search: self.facet_search,
+            prefix_search: self.prefix_search,
             _kind: PhantomData,
         }
     }
@@ -433,6 +447,8 @@ impl Settings<Unchecked> {
                     Setting::Set(this)
                 }
             },
+            prefix_search: other.prefix_search.or(self.prefix_search),
+            facet_search: other.facet_search.or(self.facet_search),
             _kind: PhantomData,
         }
     }
@@ -469,6 +485,8 @@ pub fn apply_settings_to_builder(
         embedders,
         search_cutoff_ms,
         localized_attributes: localized_attributes_rules,
+        facet_search,
+        prefix_search,
         _kind,
     } = settings;
 
@@ -657,6 +675,20 @@ pub fn apply_settings_to_builder(
         Setting::Reset => builder.reset_search_cutoff(),
         Setting::NotSet => (),
     }
+
+    match prefix_search {
+        Setting::Set(prefix_search) => {
+            builder.set_prefix_search(PrefixSearch::from(*prefix_search))
+        }
+        Setting::Reset => builder.reset_prefix_search(),
+        Setting::NotSet => (),
+    }
+
+    match facet_search {
+        Setting::Set(facet_search) => builder.set_facet_search(*facet_search),
+        Setting::Reset => builder.reset_facet_search(),
+        Setting::NotSet => (),
+    }
 }
 
 pub enum SecretPolicy {
@@ -755,6 +787,10 @@ pub fn settings(
 
     let localized_attributes_rules = index.localized_attributes_rules(rtxn)?;
 
+    let prefix_search = index.prefix_search(rtxn)?.map(PrefixSearchSettings::from);
+
+    let facet_search = index.facet_search(rtxn)?;
+
     let mut settings = Settings {
         displayed_attributes: match displayed_attributes {
             Some(attrs) => Setting::Set(attrs),
@@ -791,13 +827,14 @@ pub fn settings(
             Some(rules) => Setting::Set(rules.into_iter().map(|r| r.into()).collect()),
             None => Setting::Reset,
         },
+        prefix_search: Setting::Set(prefix_search.unwrap_or_default()),
+        facet_search: Setting::Set(facet_search),
         _kind: PhantomData,
     };
 
     if let SecretPolicy::HideSecrets = secret_policy {
         settings.hide_secrets()
     }
-
     Ok(settings)
 }
 
@@ -964,6 +1001,32 @@ impl std::ops::Deref for WildcardSetting {
     }
 }
 
+#[derive(Default, Debug, Clone, Copy, PartialEq, Eq, Deserr, Serialize, Deserialize)]
+#[serde(deny_unknown_fields, rename_all = "camelCase")]
+#[deserr(error = DeserrJsonError<InvalidSettingsPrefixSearch>, rename_all = camelCase, deny_unknown_fields)]
+pub enum PrefixSearchSettings {
+    #[default]
+    IndexingTime,
+    Disabled,
+}
+
+impl From<PrefixSearch> for PrefixSearchSettings {
+    fn from(value: PrefixSearch) -> Self {
+        match value {
+            PrefixSearch::IndexingTime => PrefixSearchSettings::IndexingTime,
+            PrefixSearch::Disabled => PrefixSearchSettings::Disabled,
+        }
+    }
+}
+impl From<PrefixSearchSettings> for PrefixSearch {
+    fn from(value: PrefixSearchSettings) -> Self {
+        match value {
+            PrefixSearchSettings::IndexingTime => PrefixSearch::IndexingTime,
+            PrefixSearchSettings::Disabled => PrefixSearch::Disabled,
+        }
+    }
+}
+
 #[cfg(test)]
 pub(crate) mod test {
     use super::*;
@@ -990,6 +1053,8 @@ pub(crate) mod test {
             embedders: Setting::NotSet,
             localized_attributes: Setting::NotSet,
             search_cutoff_ms: Setting::NotSet,
+            facet_search: Setting::NotSet,
+            prefix_search: Setting::NotSet,
             _kind: PhantomData::<Unchecked>,
         };
 
@@ -1019,6 +1084,8 @@ pub(crate) mod test {
             embedders: Setting::NotSet,
             localized_attributes: Setting::NotSet,
             search_cutoff_ms: Setting::NotSet,
+            facet_search: Setting::NotSet,
+            prefix_search: Setting::NotSet,
             _kind: PhantomData::<Unchecked>,
         };
 

crates/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 = "0.3.0"
 once_cell = "1.19.0"
 ordered-float = "4.2.1"
 parking_lot = "0.12.3"
@@ -103,7 +103,7 @@ tracing-subscriber = { version = "0.3.18", features = ["json"] }
 tracing-trace = { version = "0.1.0", path = "../tracing-trace" }
 tracing-actix-web = "0.7.11"
 build-info = { version = "1.7.0", path = "../build-info" }
-roaring = "0.10.2"
+roaring = "0.10.7"
 mopa-maintained = "0.2.3"
 
 [dev-dependencies]
@@ -157,5 +157,5 @@ german = ["meilisearch-types/german"]
 turkish = ["meilisearch-types/turkish"]
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.15/build.zip"
-sha1 = "d057600b4a839a2e0c0be7a372cd1b2683f3ca7e"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.16/build.zip"
+sha1 = "68f83438a114aabbe76bc9fe480071e741996662"

crates/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;
 use meilisearch_types::milli::OrderBy;
 use serde_json::Value;
 use tokio::task::JoinError;
@@ -62,8 +63,11 @@ pub enum MeilisearchHttpError {
     HeedError(#[from] meilisearch_types::heed::Error),
     #[error(transparent)]
     IndexScheduler(#[from] index_scheduler::Error),
-    #[error(transparent)]
-    Milli(#[from] meilisearch_types::milli::Error),
+    #[error("{}", match .index_name {
+        Some(name) if !name.is_empty() => format!("Index `{}`: {error}", name),
+        _ => format!("{error}")
+    })]
+    Milli { error: milli::Error, index_name: Option<String> },
     #[error(transparent)]
     Payload(#[from] PayloadError),
     #[error(transparent)]
@@ -76,6 +80,12 @@ pub enum MeilisearchHttpError {
     MissingSearchHybrid,
 }
 
+impl MeilisearchHttpError {
+    pub(crate) fn from_milli(error: milli::Error, index_name: Option<String>) -> Self {
+        Self::Milli { error, index_name }
+    }
+}
+
 impl ErrorCode for MeilisearchHttpError {
     fn error_code(&self) -> Code {
         match self {
@@ -95,7 +105,7 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::SerdeJson(_) => Code::Internal,
             MeilisearchHttpError::HeedError(_) => Code::Internal,
             MeilisearchHttpError::IndexScheduler(e) => e.error_code(),
-            MeilisearchHttpError::Milli(e) => e.error_code(),
+            MeilisearchHttpError::Milli { error, .. } => error.error_code(),
             MeilisearchHttpError::Payload(e) => e.error_code(),
             MeilisearchHttpError::FileStore(_) => Code::Internal,
             MeilisearchHttpError::DocumentFormat(e) => e.error_code(),

crates/meilisearch/src/lib.rs

@@ -395,6 +395,7 @@ fn import_dump(
     for index_reader in dump_reader.indexes()? {
         let mut index_reader = index_reader?;
         let metadata = index_reader.metadata();
+        let uid = metadata.uid.clone();
         tracing::info!("Importing index `{}`.", metadata.uid);
 
         let date = Some((metadata.created_at, metadata.updated_at));
@@ -432,7 +433,7 @@ fn import_dump(
         let reader = DocumentsBatchReader::from_reader(reader)?;
 
         let embedder_configs = index.embedding_configs(&wtxn)?;
-        let embedders = index_scheduler.embedders(embedder_configs)?;
+        let embedders = index_scheduler.embedders(uid, embedder_configs)?;
 
         let builder = milli::update::IndexDocuments::new(
             &mut wtxn,

crates/meilisearch/src/main.rs

@@ -20,14 +20,14 @@ use meilisearch::{
     LogStderrType, Opt, SubscriberForSecondLayer,
 };
 use meilisearch_auth::{generate_master_key, AuthController, MASTER_KEY_MIN_SIZE};
-use mimalloc::MiMalloc;
 use termcolor::{Color, ColorChoice, ColorSpec, StandardStream, WriteColor};
 use tracing::level_filters::LevelFilter;
 use tracing_subscriber::layer::SubscriberExt as _;
 use tracing_subscriber::Layer;
 
+#[cfg(not(windows))]
 #[global_allocator]
-static ALLOC: MiMalloc = MiMalloc;
+static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 
 fn default_log_route_layer() -> LogRouteType {
     None.with_filter(tracing_subscriber::filter::Targets::new().with_target("", LevelFilter::OFF))
@@ -129,6 +129,11 @@ async fn try_main() -> anyhow::Result<()> {
 
     print_launch_resume(&opt, analytics.clone(), config_read_from);
 
+    tokio::spawn(async move {
+        tokio::signal::ctrl_c().await.unwrap();
+        std::process::exit(130);
+    });
+
     run_http(index_scheduler, auth_controller, opt, log_handle, Arc::new(analytics)).await?;
 
     Ok(())

crates/meilisearch/src/routes/batches.rs

@@ -1,18 +1,18 @@
-use actix_web::{
-    web::{self, Data},
-    HttpResponse,
-};
+use actix_web::web::{self, Data};
+use actix_web::HttpResponse;
 use deserr::actix_web::AwebQueryParameter;
 use index_scheduler::{IndexScheduler, Query};
-use meilisearch_types::{
-    batch_view::BatchView, batches::BatchId, deserr::DeserrQueryParamError, error::ResponseError,
-    keys::actions,
-};
+use meilisearch_types::batch_view::BatchView;
+use meilisearch_types::batches::BatchId;
+use meilisearch_types::deserr::DeserrQueryParamError;
+use meilisearch_types::error::ResponseError;
+use meilisearch_types::keys::actions;
 use serde::Serialize;
 
-use crate::extractors::{authentication::GuardedData, sequential_extractor::SeqHandler};
-
-use super::{tasks::TasksFilterQuery, ActionPolicy};
+use super::tasks::TasksFilterQuery;
+use super::ActionPolicy;
+use crate::extractors::authentication::GuardedData;
+use crate::extractors::sequential_extractor::SeqHandler;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::get().to(SeqHandler(get_batches))))

crates/meilisearch/src/routes/indexes/documents.rs

@@ -1,5 +1,5 @@
 use std::collections::HashSet;
-use std::io::ErrorKind;
+use std::io::{ErrorKind, Seek as _};
 use std::marker::PhantomData;
 
 use actix_web::http::header::CONTENT_TYPE;
@@ -572,7 +572,7 @@ async fn document_addition(
     index_uid: IndexUid,
     primary_key: Option<String>,
     csv_delimiter: Option<u8>,
-    mut body: Payload,
+    body: Payload,
     method: IndexDocumentsMethod,
     task_id: Option<TaskId>,
     dry_run: bool,
@@ -609,54 +609,60 @@ async fn document_addition(
     };
 
     let (uuid, mut update_file) = index_scheduler.create_update_file(dry_run)?;
+    let documents_count = match format {
+        PayloadType::Ndjson => {
+            let (path, file) = update_file.into_parts();
+            let file = match file {
+                Some(file) => {
+                    let (file, path) = file.into_parts();
+                    let mut file = copy_body_to_file(file, body, format).await?;
+                    file.rewind().map_err(|e| {
+                        index_scheduler::Error::FileStore(file_store::Error::IoError(e))
+                    })?;
+                    Some(tempfile::NamedTempFile::from_parts(file, path))
+                }
+                None => None,
+            };
 
-    let temp_file = match tempfile() {
-        Ok(file) => file,
-        Err(e) => return Err(MeilisearchHttpError::Payload(ReceivePayload(Box::new(e)))),
+            let documents_count = tokio::task::spawn_blocking(move || {
+                let documents_count = file.as_ref().map_or(Ok(0), |ntf| {
+                    read_ndjson(ntf.as_file()).map_err(MeilisearchHttpError::DocumentFormat)
+                })?;
+
+                let update_file = file_store::File::from_parts(path, file);
+                update_file.persist()?;
+
+                Ok(documents_count)
+            })
+            .await?;
+
+            Ok(documents_count)
+        }
+        PayloadType::Json | PayloadType::Csv { delimiter: _ } => {
+            let temp_file = match tempfile() {
+                Ok(file) => file,
+                Err(e) => return Err(MeilisearchHttpError::Payload(ReceivePayload(Box::new(e)))),
+            };
+
+            let read_file = copy_body_to_file(temp_file, body, format).await?;
+            tokio::task::spawn_blocking(move || {
+                let documents_count = match format {
+                    PayloadType::Json => read_json(&read_file, &mut update_file)?,
+                    PayloadType::Csv { delimiter } => {
+                        read_csv(&read_file, &mut update_file, delimiter)?
+                    }
+                    PayloadType::Ndjson => {
+                        unreachable!("We already wrote the user content into the update file")
+                    }
+                };
+                // we NEED to persist the file here because we moved the `udpate_file` in another task.
+                update_file.persist()?;
+                Ok(documents_count)
+            })
+            .await
+        }
     };
 
-    let async_file = File::from_std(temp_file);
-    let mut buffer = BufWriter::new(async_file);
-
-    let mut buffer_write_size: usize = 0;
-    while let Some(result) = body.next().await {
-        let byte = result?;
-
-        if byte.is_empty() && buffer_write_size == 0 {
-            return Err(MeilisearchHttpError::MissingPayload(format));
-        }
-
-        match buffer.write_all(&byte).await {
-            Ok(()) => buffer_write_size += 1,
-            Err(e) => return Err(MeilisearchHttpError::Payload(ReceivePayload(Box::new(e)))),
-        }
-    }
-
-    if let Err(e) = buffer.flush().await {
-        return Err(MeilisearchHttpError::Payload(ReceivePayload(Box::new(e))));
-    }
-
-    if buffer_write_size == 0 {
-        return Err(MeilisearchHttpError::MissingPayload(format));
-    }
-
-    if let Err(e) = buffer.seek(std::io::SeekFrom::Start(0)).await {
-        return Err(MeilisearchHttpError::Payload(ReceivePayload(Box::new(e))));
-    }
-
-    let read_file = buffer.into_inner().into_std().await;
-    let documents_count = tokio::task::spawn_blocking(move || {
-        let documents_count = match format {
-            PayloadType::Json => read_json(&read_file, &mut update_file)?,
-            PayloadType::Csv { delimiter } => read_csv(&read_file, &mut update_file, delimiter)?,
-            PayloadType::Ndjson => read_ndjson(&read_file, &mut update_file)?,
-        };
-        // we NEED to persist the file here because we moved the `udpate_file` in another task.
-        update_file.persist()?;
-        Ok(documents_count)
-    })
-    .await;
-
     let documents_count = match documents_count {
         Ok(Ok(documents_count)) => documents_count,
         // in this case the file has not possibly be persisted.
@@ -703,6 +709,39 @@ async fn document_addition(
     Ok(task.into())
 }
 
+async fn copy_body_to_file(
+    output: std::fs::File,
+    mut body: Payload,
+    format: PayloadType,
+) -> Result<std::fs::File, MeilisearchHttpError> {
+    let async_file = File::from_std(output);
+    let mut buffer = BufWriter::new(async_file);
+    let mut buffer_write_size: usize = 0;
+    while let Some(result) = body.next().await {
+        let byte = result?;
+
+        if byte.is_empty() && buffer_write_size == 0 {
+            return Err(MeilisearchHttpError::MissingPayload(format));
+        }
+
+        match buffer.write_all(&byte).await {
+            Ok(()) => buffer_write_size += 1,
+            Err(e) => return Err(MeilisearchHttpError::Payload(ReceivePayload(Box::new(e)))),
+        }
+    }
+    if let Err(e) = buffer.flush().await {
+        return Err(MeilisearchHttpError::Payload(ReceivePayload(Box::new(e))));
+    }
+    if buffer_write_size == 0 {
+        return Err(MeilisearchHttpError::MissingPayload(format));
+    }
+    if let Err(e) = buffer.seek(std::io::SeekFrom::Start(0)).await {
+        return Err(MeilisearchHttpError::Payload(ReceivePayload(Box::new(e))));
+    }
+    let read_file = buffer.into_inner().into_std().await;
+    Ok(read_file)
+}
+
 pub async fn delete_documents_batch(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,

crates/meilisearch/src/routes/indexes/facet_search.rs

@@ -185,7 +185,8 @@ 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 search_kind =
+        search_kind(&search_query, &index_scheduler, index_uid.to_string(), &index, features)?;
     let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
         perform_facet_search(

crates/meilisearch/src/routes/indexes/mod.rs

@@ -5,7 +5,7 @@ use actix_web::web::Data;
 use actix_web::{web, HttpRequest, HttpResponse};
 use deserr::actix_web::{AwebJson, AwebQueryParameter};
 use deserr::{DeserializeError, Deserr, ValuePointerRef};
-use index_scheduler::IndexScheduler;
+use index_scheduler::{Error, IndexScheduler};
 use meilisearch_types::deserr::query_params::Param;
 use meilisearch_types::deserr::{immutable_field_error, DeserrJsonError, DeserrQueryParamError};
 use meilisearch_types::error::deserr_codes::*;
@@ -107,7 +107,10 @@ pub async fn list_indexes(
             if !filters.is_index_authorized(uid) {
                 return Ok(None);
             }
-            Ok(Some(IndexView::new(uid.to_string(), index)?))
+            Ok(Some(
+                IndexView::new(uid.to_string(), index)
+                    .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?,
+            ))
         })?;
     // Won't cause to open all indexes because IndexView doesn't keep the `Index` opened.
     let indexes: Vec<IndexView> = indexes.into_iter().flatten().collect();

crates/meilisearch/src/routes/indexes/search.rs

@@ -243,11 +243,19 @@ pub async fn search_with_url_query(
     let index = index_scheduler.index(&index_uid)?;
     let features = index_scheduler.features();
 
-    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
+    let search_kind =
+        search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index, features)?;
     let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)?;
     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())
+        perform_search(
+            index_uid.to_string(),
+            &index,
+            query,
+            search_kind,
+            retrieve_vector,
+            index_scheduler.features(),
+        )
     })
     .await;
     permit.drop().await;
@@ -287,12 +295,20 @@ pub async fn search_with_post(
 
     let features = index_scheduler.features();
 
-    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
+    let search_kind =
+        search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index, features)?;
     let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
 
     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())
+        perform_search(
+            index_uid.to_string(),
+            &index,
+            query,
+            search_kind,
+            retrieve_vectors,
+            index_scheduler.features(),
+        )
     })
     .await;
     permit.drop().await;
@@ -314,6 +330,7 @@ pub async fn search_with_post(
 pub fn search_kind(
     query: &SearchQuery,
     index_scheduler: &IndexScheduler,
+    index_uid: String,
     index: &milli::Index,
     features: RoFeatures,
 ) -> Result<SearchKind, ResponseError> {
@@ -332,7 +349,7 @@ pub fn search_kind(
         (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()))
+            SearchKind::semantic(index_scheduler, index_uid, index, embedder, v.map(|v| v.len()))
         }
         // hybrid.semantic_ratio == 0.0 => keyword
         (_, Some(HybridQuery { semantic_ratio, embedder: _ }), _) if **semantic_ratio == 0.0 => {
@@ -340,13 +357,14 @@ pub fn search_kind(
         }
         // no query, hybrid, vector => semantic
         (None, Some(HybridQuery { semantic_ratio: _, embedder }), Some(v)) => {
-            SearchKind::semantic(index_scheduler, index, embedder, Some(v.len()))
+            SearchKind::semantic(index_scheduler, index_uid, 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_uid,
             index,
             embedder,
             **semantic_ratio,

crates/meilisearch/src/routes/indexes/settings.rs

@@ -17,6 +17,32 @@ use crate::extractors::authentication::GuardedData;
 use crate::routes::{get_task_id, is_dry_run, SummarizedTaskView};
 use crate::Opt;
 
+/// This macro generates the routes for the settings.
+///
+/// It takes a list of settings and generates a module for each setting.
+/// Each module contains the `get`, `update` and `delete` routes for the setting.
+///
+/// It also generates a `configure` function that configures the routes for the settings.
+macro_rules! make_setting_routes {
+    ($({route: $route:literal, update_verb: $update_verb:ident, value_type: $type:ty, err_type: $err_ty:ty, attr: $attr:ident, camelcase_attr: $camelcase_attr:literal, analytics: $analytics:ident},)*) => {
+        $(
+            make_setting_route!($route, $update_verb, $type, $err_ty, $attr, $camelcase_attr, $analytics);
+        )*
+
+        pub fn configure(cfg: &mut web::ServiceConfig) {
+            use crate::extractors::sequential_extractor::SeqHandler;
+            cfg.service(
+                web::resource("")
+                .route(web::patch().to(SeqHandler(update_all)))
+                .route(web::get().to(SeqHandler(get_all)))
+                .route(web::delete().to(SeqHandler(delete_all))))
+                $(.service($attr::resources()))*;
+        }
+
+        pub const ALL_SETTINGS_NAMES: &[&str] = &[$(stringify!($attr)),*];
+    };
+}
+
 #[macro_export]
 macro_rules! make_setting_route {
     ($route:literal, $update_verb:ident, $type:ty, $err_ty:ty, $attr:ident, $camelcase_attr:literal, $analytics:ident) => {
@@ -153,255 +179,227 @@ macro_rules! make_setting_route {
     };
 }
 
-make_setting_route!(
-    "/filterable-attributes",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsFilterableAttributes,
-    >,
-    filterable_attributes,
-    "filterableAttributes",
-    FilterableAttributesAnalytics
-);
-
-make_setting_route!(
-    "/sortable-attributes",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSortableAttributes,
-    >,
-    sortable_attributes,
-    "sortableAttributes",
-    SortableAttributesAnalytics
-);
-
-make_setting_route!(
-    "/displayed-attributes",
-    put,
-    Vec<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsDisplayedAttributes,
-    >,
-    displayed_attributes,
-    "displayedAttributes",
-    DisplayedAttributesAnalytics
-);
-
-make_setting_route!(
-    "/typo-tolerance",
-    patch,
-    meilisearch_types::settings::TypoSettings,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsTypoTolerance,
-    >,
-    typo_tolerance,
-    "typoTolerance",
-    TypoToleranceAnalytics
-);
-
-make_setting_route!(
-    "/searchable-attributes",
-    put,
-    Vec<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSearchableAttributes,
-    >,
-    searchable_attributes,
-    "searchableAttributes",
-    SearchableAttributesAnalytics
-);
-
-make_setting_route!(
-    "/stop-words",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsStopWords,
-    >,
-    stop_words,
-    "stopWords",
-    StopWordsAnalytics
-);
-
-make_setting_route!(
-    "/non-separator-tokens",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsNonSeparatorTokens,
-    >,
-    non_separator_tokens,
-    "nonSeparatorTokens",
-    NonSeparatorTokensAnalytics
-);
-
-make_setting_route!(
-    "/separator-tokens",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSeparatorTokens,
-    >,
-    separator_tokens,
-    "separatorTokens",
-    SeparatorTokensAnalytics
-);
-
-make_setting_route!(
-    "/dictionary",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsDictionary,
-    >,
-    dictionary,
-    "dictionary",
-    DictionaryAnalytics
-);
-
-make_setting_route!(
-    "/synonyms",
-    put,
-    std::collections::BTreeMap<String, Vec<String>>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSynonyms,
-    >,
-    synonyms,
-    "synonyms",
-    SynonymsAnalytics
-);
-
-make_setting_route!(
-    "/distinct-attribute",
-    put,
-    String,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsDistinctAttribute,
-    >,
-    distinct_attribute,
-    "distinctAttribute",
-    DistinctAttributeAnalytics
-);
-
-make_setting_route!(
-    "/proximity-precision",
-    put,
-    meilisearch_types::settings::ProximityPrecisionView,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsProximityPrecision,
-    >,
-    proximity_precision,
-    "proximityPrecision",
-    ProximityPrecisionAnalytics
-);
-
-make_setting_route!(
-    "/localized-attributes",
-    put,
-    Vec<meilisearch_types::locales::LocalizedAttributesRuleView>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsLocalizedAttributes,
-    >,
-    localized_attributes,
-    "localizedAttributes",
-    LocalesAnalytics
-);
-
-make_setting_route!(
-    "/ranking-rules",
-    put,
-    Vec<meilisearch_types::settings::RankingRuleView>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsRankingRules,
-    >,
-    ranking_rules,
-    "rankingRules",
-    RankingRulesAnalytics
-);
-
-make_setting_route!(
-    "/faceting",
-    patch,
-    meilisearch_types::settings::FacetingSettings,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsFaceting,
-    >,
-    faceting,
-    "faceting",
-    FacetingAnalytics
-);
-
-make_setting_route!(
-    "/pagination",
-    patch,
-    meilisearch_types::settings::PaginationSettings,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsPagination,
-    >,
-    pagination,
-    "pagination",
-    PaginationAnalytics
-);
-
-make_setting_route!(
-    "/embedders",
-    patch,
-    std::collections::BTreeMap<String, Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsEmbedders,
-    >,
-    embedders,
-    "embedders",
-    EmbeddersAnalytics
-);
-
-make_setting_route!(
-    "/search-cutoff-ms",
-    put,
-    u64,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSearchCutoffMs,
-    >,
-    search_cutoff_ms,
-    "searchCutoffMs",
-    SearchCutoffMsAnalytics
-);
-
-macro_rules! generate_configure {
-    ($($mod:ident),*) => {
-        pub fn configure(cfg: &mut web::ServiceConfig) {
-            use crate::extractors::sequential_extractor::SeqHandler;
-            cfg.service(
-                web::resource("")
-                .route(web::patch().to(SeqHandler(update_all)))
-                .route(web::get().to(SeqHandler(get_all)))
-                .route(web::delete().to(SeqHandler(delete_all))))
-                $(.service($mod::resources()))*;
-        }
-    };
-}
-
-generate_configure!(
-    filterable_attributes,
-    sortable_attributes,
-    displayed_attributes,
-    localized_attributes,
-    searchable_attributes,
-    distinct_attribute,
-    proximity_precision,
-    stop_words,
-    separator_tokens,
-    non_separator_tokens,
-    dictionary,
-    synonyms,
-    ranking_rules,
-    typo_tolerance,
-    pagination,
-    faceting,
-    embedders,
-    search_cutoff_ms
+make_setting_routes!(
+    {
+        route: "/filterable-attributes",
+        update_verb: put,
+        value_type: std::collections::BTreeSet<String>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsFilterableAttributes,
+        >,
+        attr: filterable_attributes,
+        camelcase_attr: "filterableAttributes",
+        analytics: FilterableAttributesAnalytics
+    },
+    {
+        route: "/sortable-attributes",
+        update_verb: put,
+        value_type: std::collections::BTreeSet<String>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsSortableAttributes,
+        >,
+        attr: sortable_attributes,
+        camelcase_attr: "sortableAttributes",
+        analytics: SortableAttributesAnalytics
+    },
+    {
+        route: "/displayed-attributes",
+        update_verb: put,
+        value_type: Vec<String>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsDisplayedAttributes,
+        >,
+        attr: displayed_attributes,
+        camelcase_attr: "displayedAttributes",
+        analytics: DisplayedAttributesAnalytics
+    },
+    {
+        route: "/typo-tolerance",
+        update_verb: patch,
+        value_type: meilisearch_types::settings::TypoSettings,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsTypoTolerance,
+        >,
+        attr: typo_tolerance,
+        camelcase_attr: "typoTolerance",
+        analytics: TypoToleranceAnalytics
+    },
+    {
+        route: "/searchable-attributes",
+        update_verb: put,
+        value_type: Vec<String>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsSearchableAttributes,
+        >,
+        attr: searchable_attributes,
+        camelcase_attr: "searchableAttributes",
+        analytics: SearchableAttributesAnalytics
+    },
+    {
+        route: "/stop-words",
+        update_verb: put,
+        value_type: std::collections::BTreeSet<String>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsStopWords,
+        >,
+        attr: stop_words,
+        camelcase_attr: "stopWords",
+        analytics: StopWordsAnalytics
+    },
+    {
+        route: "/non-separator-tokens",
+        update_verb: put,
+        value_type: std::collections::BTreeSet<String>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsNonSeparatorTokens,
+        >,
+        attr: non_separator_tokens,
+        camelcase_attr: "nonSeparatorTokens",
+        analytics: NonSeparatorTokensAnalytics
+    },
+    {
+        route: "/separator-tokens",
+        update_verb: put,
+        value_type: std::collections::BTreeSet<String>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsSeparatorTokens,
+        >,
+        attr: separator_tokens,
+        camelcase_attr: "separatorTokens",
+        analytics: SeparatorTokensAnalytics
+    },
+    {
+        route: "/dictionary",
+        update_verb: put,
+        value_type: std::collections::BTreeSet<String>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsDictionary,
+        >,
+        attr: dictionary,
+        camelcase_attr: "dictionary",
+        analytics: DictionaryAnalytics
+    },
+    {
+        route: "/synonyms",
+        update_verb: put,
+        value_type: std::collections::BTreeMap<String, Vec<String>>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsSynonyms,
+        >,
+        attr: synonyms,
+        camelcase_attr: "synonyms",
+        analytics: SynonymsAnalytics
+    },
+    {
+        route: "/distinct-attribute",
+        update_verb: put,
+        value_type: String,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsDistinctAttribute,
+        >,
+        attr: distinct_attribute,
+        camelcase_attr: "distinctAttribute",
+        analytics: DistinctAttributeAnalytics
+    },
+    {
+        route: "/proximity-precision",
+        update_verb: put,
+        value_type: meilisearch_types::settings::ProximityPrecisionView,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsProximityPrecision,
+        >,
+        attr: proximity_precision,
+        camelcase_attr: "proximityPrecision",
+        analytics: ProximityPrecisionAnalytics
+    },
+    {
+        route: "/localized-attributes",
+        update_verb: put,
+        value_type: Vec<meilisearch_types::locales::LocalizedAttributesRuleView>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsLocalizedAttributes,
+        >,
+        attr: localized_attributes,
+        camelcase_attr: "localizedAttributes",
+        analytics: LocalesAnalytics
+    },
+    {
+        route: "/ranking-rules",
+        update_verb: put,
+        value_type: Vec<meilisearch_types::settings::RankingRuleView>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsRankingRules,
+        >,
+        attr: ranking_rules,
+        camelcase_attr: "rankingRules",
+        analytics: RankingRulesAnalytics
+    },
+    {
+        route: "/faceting",
+        update_verb: patch,
+        value_type: meilisearch_types::settings::FacetingSettings,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsFaceting,
+        >,
+        attr: faceting,
+        camelcase_attr: "faceting",
+        analytics: FacetingAnalytics
+    },
+    {
+        route: "/pagination",
+        update_verb: patch,
+        value_type: meilisearch_types::settings::PaginationSettings,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsPagination,
+        >,
+        attr: pagination,
+        camelcase_attr: "pagination",
+        analytics: PaginationAnalytics
+    },
+    {
+        route: "/embedders",
+        update_verb: patch,
+        value_type: std::collections::BTreeMap<String, Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>>,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsEmbedders,
+        >,
+        attr: embedders,
+        camelcase_attr: "embedders",
+        analytics: EmbeddersAnalytics
+    },
+    {
+        route: "/search-cutoff-ms",
+        update_verb: put,
+        value_type: u64,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsSearchCutoffMs,
+        >,
+        attr: search_cutoff_ms,
+        camelcase_attr: "searchCutoffMs",
+        analytics: SearchCutoffMsAnalytics
+    },
+    {
+        route: "/facet-search",
+        update_verb: put,
+        value_type: bool,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsFacetSearch,
+        >,
+        attr: facet_search,
+        camelcase_attr: "facetSearch",
+        analytics: FacetSearchAnalytics
+    },
+    {
+        route: "/prefix-search",
+        update_verb: put,
+        value_type: meilisearch_types::settings::PrefixSearchSettings,
+        err_type: meilisearch_types::deserr::DeserrJsonError<
+            meilisearch_types::error::deserr_codes::InvalidSettingsPrefixSearch,
+        >,
+        attr: prefix_search,
+        camelcase_attr: "prefixSearch",
+        analytics: PrefixSearchAnalytics
+    },
 );
 
 pub async fn update_all(
@@ -456,6 +454,8 @@ pub async fn update_all(
             non_separator_tokens: NonSeparatorTokensAnalytics::new(
                 new_settings.non_separator_tokens.as_ref().set(),
             ),
+            facet_search: FacetSearchAnalytics::new(new_settings.facet_search.as_ref().set()),
+            prefix_search: PrefixSearchAnalytics::new(new_settings.prefix_search.as_ref().set()),
         },
         &req,
     );

crates/meilisearch/src/routes/indexes/settings_analytics.rs

@@ -10,7 +10,8 @@ use meilisearch_types::locales::{Locale, LocalizedAttributesRuleView};
 use meilisearch_types::milli::update::Setting;
 use meilisearch_types::milli::vector::settings::EmbeddingSettings;
 use meilisearch_types::settings::{
-    FacetingSettings, PaginationSettings, ProximityPrecisionView, RankingRuleView, TypoSettings,
+    FacetingSettings, PaginationSettings, PrefixSearchSettings, ProximityPrecisionView,
+    RankingRuleView, TypoSettings,
 };
 use serde::Serialize;
 
@@ -36,6 +37,8 @@ pub struct SettingsAnalytics {
     pub dictionary: DictionaryAnalytics,
     pub separator_tokens: SeparatorTokensAnalytics,
     pub non_separator_tokens: NonSeparatorTokensAnalytics,
+    pub facet_search: FacetSearchAnalytics,
+    pub prefix_search: PrefixSearchAnalytics,
 }
 
 impl Aggregate for SettingsAnalytics {
@@ -183,6 +186,14 @@ impl Aggregate for SettingsAnalytics {
             non_separator_tokens: NonSeparatorTokensAnalytics {
                 total: new.non_separator_tokens.total.or(self.non_separator_tokens.total),
             },
+            facet_search: FacetSearchAnalytics {
+                set: new.facet_search.set | self.facet_search.set,
+                value: new.facet_search.value.or(self.facet_search.value),
+            },
+            prefix_search: PrefixSearchAnalytics {
+                set: new.prefix_search.set | self.prefix_search.set,
+                value: new.prefix_search.value.or(self.prefix_search.value),
+            },
         })
     }
 
@@ -620,3 +631,35 @@ impl NonSeparatorTokensAnalytics {
         SettingsAnalytics { non_separator_tokens: self, ..Default::default() }
     }
 }
+
+#[derive(Serialize, Default)]
+pub struct FacetSearchAnalytics {
+    pub set: bool,
+    pub value: Option<bool>,
+}
+
+impl FacetSearchAnalytics {
+    pub fn new(settings: Option<&bool>) -> Self {
+        Self { set: settings.is_some(), value: settings.copied() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { facet_search: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct PrefixSearchAnalytics {
+    pub set: bool,
+    pub value: Option<PrefixSearchSettings>,
+}
+
+impl PrefixSearchAnalytics {
+    pub fn new(settings: Option<&PrefixSearchSettings>) -> Self {
+        Self { set: settings.is_some(), value: settings.cloned() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { prefix_search: self, ..Default::default() }
+    }
+}

crates/meilisearch/src/routes/indexes/similar.rs

@@ -103,8 +103,13 @@ async fn similar(
 
     let index = index_scheduler.index(&index_uid)?;
 
-    let (embedder_name, embedder, quantized) =
-        SearchKind::embedder(&index_scheduler, &index, &query.embedder, None)?;
+    let (embedder_name, embedder, quantized) = SearchKind::embedder(
+        &index_scheduler,
+        index_uid.to_string(),
+        &index,
+        &query.embedder,
+        None,
+    )?;
 
     tokio::task::spawn_blocking(move || {
         perform_similar(

crates/meilisearch/src/routes/multi_search.rs

@@ -125,14 +125,28 @@ pub async fn multi_search_with_post(
                         })
                         .with_index(query_index)?;
 
-                    let search_kind =
-                        search_kind(&query, index_scheduler.get_ref(), &index, features)
-                            .with_index(query_index)?;
+                    let index_uid_str = index_uid.to_string();
+
+                    let search_kind = search_kind(
+                        &query,
+                        index_scheduler.get_ref(),
+                        index_uid_str.clone(),
+                        &index,
+                        features,
+                    )
+                    .with_index(query_index)?;
                     let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)
                         .with_index(query_index)?;
 
                     let search_result = tokio::task::spawn_blocking(move || {
-                        perform_search(&index, query, search_kind, retrieve_vector, features)
+                        perform_search(
+                            index_uid_str.clone(),
+                            &index,
+                            query,
+                            search_kind,
+                            retrieve_vector,
+                            features,
+                        )
                     })
                     .await
                     .with_index(query_index)?;

crates/meilisearch/src/search/federated.rs

@@ -560,7 +560,8 @@ pub fn perform_federated_search(
             // use an immediately invoked lambda to capture the result without returning from the function
 
             let res: Result<(), ResponseError> = (|| {
-                let search_kind = search_kind(&query, index_scheduler, &index, features)?;
+                let search_kind =
+                    search_kind(&query, index_scheduler, index_uid.to_string(), &index, features)?;
 
                 let canonicalization_kind = match (&search_kind, &query.q) {
                     (SearchKind::SemanticOnly { .. }, _) => {
@@ -636,7 +637,8 @@ pub fn perform_federated_search(
                 search.offset(0);
                 search.limit(required_hit_count);
 
-                let (result, _semantic_hit_count) = super::search_from_kind(search_kind, search)?;
+                let (result, _semantic_hit_count) =
+                    super::search_from_kind(index_uid.to_string(), search_kind, search)?;
                 let format = AttributesFormat {
                     attributes_to_retrieve: query.attributes_to_retrieve,
                     retrieve_vectors,
@@ -670,7 +672,10 @@ pub fn perform_federated_search(
 
                 let formatter_builder = HitMaker::formatter_builder(matching_words, tokenizer);
 
-                let hit_maker = HitMaker::new(&index, &rtxn, format, formatter_builder)?;
+                let hit_maker =
+                    HitMaker::new(&index, &rtxn, format, formatter_builder).map_err(|e| {
+                        MeilisearchHttpError::from_milli(e, Some(index_uid.to_string()))
+                    })?;
 
                 results_by_query.push(SearchResultByQuery {
                     federation_options,

crates/meilisearch/src/search/mod.rs

@@ -19,7 +19,9 @@ use meilisearch_types::locales::Locale;
 use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
 use meilisearch_types::milli::vector::parsed_vectors::ExplicitVectors;
 use meilisearch_types::milli::vector::Embedder;
-use meilisearch_types::milli::{FacetValueHit, OrderBy, SearchForFacetValues, TimeBudget};
+use meilisearch_types::milli::{
+    FacetValueHit, InternalError, OrderBy, SearchForFacetValues, TimeBudget,
+};
 use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
 use meilisearch_types::{milli, Document};
 use milli::tokenizer::{Language, TokenizerBuilder};
@@ -281,35 +283,38 @@ pub enum SearchKind {
 impl SearchKind {
     pub(crate) fn semantic(
         index_scheduler: &index_scheduler::IndexScheduler,
+        index_uid: String,
         index: &Index,
         embedder_name: &str,
         vector_len: Option<usize>,
     ) -> Result<Self, ResponseError> {
         let (embedder_name, embedder, quantized) =
-            Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
+            Self::embedder(index_scheduler, index_uid, index, embedder_name, vector_len)?;
         Ok(Self::SemanticOnly { embedder_name, embedder, quantized })
     }
 
     pub(crate) fn hybrid(
         index_scheduler: &index_scheduler::IndexScheduler,
+        index_uid: String,
         index: &Index,
         embedder_name: &str,
         semantic_ratio: f32,
         vector_len: Option<usize>,
     ) -> Result<Self, ResponseError> {
         let (embedder_name, embedder, quantized) =
-            Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
+            Self::embedder(index_scheduler, index_uid, index, embedder_name, vector_len)?;
         Ok(Self::Hybrid { embedder_name, embedder, quantized, semantic_ratio })
     }
 
     pub(crate) fn embedder(
         index_scheduler: &index_scheduler::IndexScheduler,
+        index_uid: String,
         index: &Index,
         embedder_name: &str,
         vector_len: Option<usize>,
     ) -> Result<(String, Arc<Embedder>, bool), ResponseError> {
         let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
-        let embedders = index_scheduler.embedders(embedder_configs)?;
+        let embedders = index_scheduler.embedders(index_uid, embedder_configs)?;
 
         let (embedder, _, quantized) = embedders
             .get(embedder_name)
@@ -796,8 +801,10 @@ fn prepare_search<'t>(
                     let span = tracing::trace_span!(target: "search::vector", "embed_one");
                     let _entered = span.enter();
 
+                    let deadline = std::time::Instant::now() + std::time::Duration::from_secs(10);
+
                     embedder
-                        .embed_one(query.q.clone().unwrap())
+                        .embed_one(query.q.clone().unwrap(), Some(deadline))
                         .map_err(milli::vector::Error::from)
                         .map_err(milli::Error::from)?
                 }
@@ -888,6 +895,7 @@ fn prepare_search<'t>(
 }
 
 pub fn perform_search(
+    index_uid: String,
     index: &Index,
     query: SearchQuery,
     search_kind: SearchKind,
@@ -914,7 +922,7 @@ pub fn perform_search(
             used_negative_operator,
         },
         semantic_hit_count,
-    ) = search_from_kind(search_kind, search)?;
+    ) = search_from_kind(index_uid, search_kind, search)?;
 
     let SearchQuery {
         q,
@@ -1067,17 +1075,27 @@ fn compute_facet_distribution_stats<S: AsRef<str>>(
 }
 
 pub fn search_from_kind(
+    index_uid: String,
     search_kind: SearchKind,
     search: milli::Search<'_>,
 ) -> Result<(milli::SearchResult, Option<u32>), MeilisearchHttpError> {
     let (milli_result, semantic_hit_count) = match &search_kind {
-        SearchKind::KeywordOnly => (search.execute()?, None),
+        SearchKind::KeywordOnly => {
+            let results = search
+                .execute()
+                .map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid.to_string())))?;
+            (results, None)
+        }
         SearchKind::SemanticOnly { .. } => {
-            let results = search.execute()?;
+            let results = search
+                .execute()
+                .map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid.to_string())))?;
             let semantic_hit_count = results.document_scores.len() as u32;
             (results, Some(semantic_hit_count))
         }
-        SearchKind::Hybrid { semantic_ratio, .. } => search.execute_hybrid(*semantic_ratio)?,
+        SearchKind::Hybrid { semantic_ratio, .. } => search
+            .execute_hybrid(*semantic_ratio)
+            .map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid)))?,
     };
     Ok((milli_result, semantic_hit_count))
 }
@@ -1179,7 +1197,7 @@ impl<'a> HitMaker<'a> {
         rtxn: &'a RoTxn<'a>,
         format: AttributesFormat,
         mut formatter_builder: MatcherBuilder<'a>,
-    ) -> Result<Self, MeilisearchHttpError> {
+    ) -> milli::Result<Self> {
         formatter_builder.crop_marker(format.crop_marker);
         formatter_builder.highlight_prefix(format.highlight_pre_tag);
         formatter_builder.highlight_suffix(format.highlight_post_tag);
@@ -1274,11 +1292,7 @@ impl<'a> HitMaker<'a> {
         })
     }
 
-    pub fn make_hit(
-        &self,
-        id: u32,
-        score: &[ScoreDetails],
-    ) -> Result<SearchHit, MeilisearchHttpError> {
+    pub fn make_hit(&self, id: u32, score: &[ScoreDetails]) -> milli::Result<SearchHit> {
         let (_, obkv) =
             self.index.iter_documents(self.rtxn, std::iter::once(id))?.next().unwrap()?;
 
@@ -1321,7 +1335,10 @@ impl<'a> HitMaker<'a> {
                     .is_some_and(|conf| conf.user_provided.contains(id));
                 let embeddings =
                     ExplicitVectors { embeddings: Some(vector.into()), regenerate: !user_provided };
-                vectors.insert(name, serde_json::to_value(embeddings)?);
+                vectors.insert(
+                    name,
+                    serde_json::to_value(embeddings).map_err(InternalError::SerdeJson)?,
+                );
             }
             document.insert("_vectors".into(), vectors.into());
         }
@@ -1367,7 +1384,7 @@ fn make_hits<'a>(
     format: AttributesFormat,
     matching_words: milli::MatchingWords,
     documents_ids_scores: impl Iterator<Item = (u32, &'a Vec<ScoreDetails>)> + 'a,
-) -> Result<Vec<SearchHit>, MeilisearchHttpError> {
+) -> milli::Result<Vec<SearchHit>> {
     let mut documents = Vec::new();
 
     let dictionary = index.dictionary(rtxn)?;
@@ -1405,6 +1422,13 @@ pub fn perform_facet_search(
         None => TimeBudget::default(),
     };
 
+    if !index.facet_search(&rtxn)? {
+        return Err(ResponseError::from_msg(
+            "The facet search is disabled for this index".to_string(),
+            Code::FacetSearchDisabled,
+        ));
+    }
+
     // In the faceted search context, we want to use the intersection between the locales provided by the user
     // and the locales of the facet string.
     // If the facet string is not localized, we **ignore** the locales provided by the user because the facet data has no locale.
@@ -1687,13 +1711,13 @@ fn add_non_formatted_ids_to_formatted_options(
 fn make_document(
     displayed_attributes: &BTreeSet<FieldId>,
     field_ids_map: &FieldsIdsMap,
-    obkv: obkv::KvReaderU16,
-) -> Result<Document, MeilisearchHttpError> {
+    obkv: &obkv::KvReaderU16,
+) -> milli::Result<Document> {
     let mut document = serde_json::Map::new();
 
     // recreate the original json
     for (key, value) in obkv.iter() {
-        let value = serde_json::from_slice(value)?;
+        let value = serde_json::from_slice(value).map_err(InternalError::SerdeJson)?;
         let key = field_ids_map.name(key).expect("Missing field name").to_string();
 
         document.insert(key, value);
@@ -1718,7 +1742,7 @@ fn format_fields(
     displayable_ids: &BTreeSet<FieldId>,
     locales: Option<&[Language]>,
     localized_attributes: &[LocalizedAttributesRule],
-) -> Result<(Option<MatchesPosition>, Document), MeilisearchHttpError> {
+) -> milli::Result<(Option<MatchesPosition>, Document)> {
     let mut matches_position = compute_matches.then(BTreeMap::new);
     let mut document = document.clone();
 
@@ -1896,7 +1920,7 @@ fn parse_filter_array(arr: &[Value]) -> Result<Option<Filter>, MeilisearchHttpEr
         }
     }
 
-    Ok(Filter::from_array(ands)?)
+    Filter::from_array(ands).map_err(|e| MeilisearchHttpError::from_milli(e, None))
 }
 
 #[cfg(test)]

crates/meilisearch/tests/batches/mod.rs

@@ -224,7 +224,7 @@ async fn list_batches_status_and_type_filtered() {
 }
 
 #[actix_rt::test]
-async fn get_batch_filter_error() {
+async fn list_batch_filter_error() {
     let server = Server::new().await;
 
     let (response, code) = server.batches_filter("lol=pied").await;
@@ -284,6 +284,7 @@ async fn test_summarized_document_addition_or_update() {
         @r#"
     {
       "uid": 0,
+      "progress": null,
       "details": {
         "receivedDocuments": 1,
         "indexedDocuments": 1
@@ -314,6 +315,7 @@ async fn test_summarized_document_addition_or_update() {
         @r#"
     {
       "uid": 1,
+      "progress": null,
       "details": {
         "receivedDocuments": 1,
         "indexedDocuments": 1
@@ -349,6 +351,7 @@ async fn test_summarized_delete_documents_by_batch() {
         @r#"
     {
       "uid": 0,
+      "progress": null,
       "details": {
         "providedIds": 3,
         "deletedDocuments": 0
@@ -380,6 +383,7 @@ async fn test_summarized_delete_documents_by_batch() {
         @r#"
     {
       "uid": 2,
+      "progress": null,
       "details": {
         "providedIds": 1,
         "deletedDocuments": 0
@@ -416,6 +420,7 @@ async fn test_summarized_delete_documents_by_filter() {
         @r#"
     {
       "uid": 0,
+      "progress": null,
       "details": {
         "providedIds": 0,
         "deletedDocuments": 0,
@@ -448,6 +453,7 @@ async fn test_summarized_delete_documents_by_filter() {
         @r#"
     {
       "uid": 2,
+      "progress": null,
       "details": {
         "providedIds": 0,
         "deletedDocuments": 0,
@@ -480,6 +486,7 @@ async fn test_summarized_delete_documents_by_filter() {
         @r#"
     {
       "uid": 4,
+      "progress": null,
       "details": {
         "providedIds": 0,
         "deletedDocuments": 0,
@@ -516,6 +523,7 @@ async fn test_summarized_delete_document_by_id() {
         @r#"
     {
       "uid": 0,
+      "progress": null,
       "details": {
         "providedIds": 1,
         "deletedDocuments": 0
@@ -547,6 +555,7 @@ async fn test_summarized_delete_document_by_id() {
         @r#"
     {
       "uid": 2,
+      "progress": null,
       "details": {
         "providedIds": 1,
         "deletedDocuments": 0
@@ -594,6 +603,7 @@ async fn test_summarized_settings_update() {
         @r#"
     {
       "uid": 0,
+      "progress": null,
       "details": {
         "displayedAttributes": [
           "doggos",
@@ -638,6 +648,7 @@ async fn test_summarized_index_creation() {
         @r#"
     {
       "uid": 0,
+      "progress": null,
       "details": {},
       "stats": {
         "totalNbTasks": 1,
@@ -665,6 +676,7 @@ async fn test_summarized_index_creation() {
         @r#"
     {
       "uid": 1,
+      "progress": null,
       "details": {
         "primaryKey": "doggos"
       },
@@ -809,6 +821,7 @@ async fn test_summarized_index_update() {
         @r#"
     {
       "uid": 0,
+      "progress": null,
       "details": {},
       "stats": {
         "totalNbTasks": 1,
@@ -836,6 +849,7 @@ async fn test_summarized_index_update() {
         @r#"
     {
       "uid": 1,
+      "progress": null,
       "details": {
         "primaryKey": "bones"
       },
@@ -868,6 +882,7 @@ async fn test_summarized_index_update() {
         @r#"
     {
       "uid": 3,
+      "progress": null,
       "details": {},
       "stats": {
         "totalNbTasks": 1,
@@ -895,6 +910,7 @@ async fn test_summarized_index_update() {
         @r#"
     {
       "uid": 4,
+      "progress": null,
       "details": {
         "primaryKey": "bones"
       },
@@ -932,6 +948,7 @@ async fn test_summarized_index_swap() {
         @r#"
     {
       "uid": 0,
+      "progress": null,
       "details": {
         "swaps": [
           {
@@ -972,6 +989,7 @@ async fn test_summarized_index_swap() {
         @r#"
     {
       "uid": 3,
+      "progress": null,
       "details": {
         "swaps": [
           {
@@ -1014,6 +1032,7 @@ async fn test_summarized_batch_cancelation() {
         @r#"
     {
       "uid": 1,
+      "progress": null,
       "details": {
         "matchedTasks": 1,
         "canceledTasks": 0,
@@ -1051,6 +1070,7 @@ async fn test_summarized_batch_deletion() {
         @r#"
     {
       "uid": 1,
+      "progress": null,
       "details": {
         "matchedTasks": 1,
         "deletedTasks": 1,
@@ -1084,6 +1104,7 @@ async fn test_summarized_dump_creation() {
         @r#"
     {
       "uid": 0,
+      "progress": null,
       "details": {
         "dumpUid": "[dumpUid]"
       },

crates/meilisearch/tests/common/mod.rs

@@ -52,6 +52,25 @@ impl Value {
         }
         self
     }
+
+    /// Return `true` if the `status` field is set to `failed`.
+    /// Panic if the `status` field doesn't exists.
+    #[track_caller]
+    pub fn is_fail(&self) -> bool {
+        if !self["status"].is_string() {
+            panic!("Called `is_fail` on {}", serde_json::to_string_pretty(&self.0).unwrap());
+        }
+        self["status"] == serde_json::Value::String(String::from("failed"))
+    }
+
+    // Panic if the json doesn't contain the `status` field set to "succeeded"
+    #[track_caller]
+    pub fn failed(&self) -> &Self {
+        if !self.is_fail() {
+            panic!("Called failed on {}", serde_json::to_string_pretty(&self.0).unwrap());
+        }
+        self
+    }
 }
 
 impl From<serde_json::Value> for Value {

crates/meilisearch/tests/documents/add_documents.rs

@@ -1264,15 +1264,18 @@ async fn error_add_documents_bad_document_id() {
     let server = Server::new().await;
     let index = server.index("test");
     index.create(Some("docid")).await;
+
+    // unsupported characters
+
     let documents = json!([
         {
             "docid": "foo & bar",
             "content": "foobar"
         }
     ]);
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-    let (response, code) = index.get_task(1).await;
+    let (value, _code) = index.add_documents(documents, None).await;
+    index.wait_task(value.uid()).await;
+    let (response, code) = index.get_task(value.uid()).await;
     snapshot!(code, @"200 OK");
     snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" }),
         @r###"
@@ -1288,7 +1291,81 @@ async fn error_add_documents_bad_document_id() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Document identifier `\"foo & bar\"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 512 bytes.",
+        "message": "Document identifier `\"foo & bar\"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 511 bytes.",
+        "code": "invalid_document_id",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_document_id"
+      },
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    // More than 512 bytes
+    let documents = json!([
+        {
+            "docid": "a".repeat(600),
+            "content": "foobar"
+        }
+    ]);
+    let (value, _code) = index.add_documents(documents, None).await;
+    index.wait_task(value.uid()).await;
+    let (response, code) = index.get_task(value.uid()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" }),
+      @r###"
+    {
+      "uid": 2,
+      "batchUid": 2,
+      "indexUid": "test",
+      "status": "failed",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "error": {
+        "message": "Document identifier `\"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 511 bytes.",
+        "code": "invalid_document_id",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_document_id"
+      },
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    // Exactly 512 bytes
+    let documents = json!([
+        {
+            "docid": "a".repeat(512),
+            "content": "foobar"
+        }
+    ]);
+    let (value, _code) = index.add_documents(documents, None).await;
+    index.wait_task(value.uid()).await;
+    let (response, code) = index.get_task(value.uid()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" }),
+    @r###"
+    {
+      "uid": 3,
+      "batchUid": 3,
+      "indexUid": "test",
+      "status": "failed",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "error": {
+        "message": "Document identifier `\"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 511 bytes.",
         "code": "invalid_document_id",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_id"
@@ -1344,7 +1421,6 @@ async fn error_add_documents_missing_document_id() {
 }
 
 #[actix_rt::test]
-#[should_panic]
 async fn error_document_field_limit_reached_in_one_document() {
     let server = Server::new().await;
     let index = server.index("test");
@@ -1361,7 +1437,7 @@ async fn error_document_field_limit_reached_in_one_document() {
     let documents = json!([big_object]);
 
     let (response, code) = index.update_documents(documents, Some("id")).await;
-    snapshot!(code, @"500 Internal Server Error");
+    snapshot!(code, @"202 Accepted");
 
     let response = index.wait_task(response.uid()).await;
     snapshot!(code, @"202 Accepted");
@@ -1369,16 +1445,22 @@ async fn error_document_field_limit_reached_in_one_document() {
     snapshot!(response,
         @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
+      "batchUid": "[batch_uid]",
       "indexUid": "test",
-      "status": "succeeded",
+      "status": "failed",
       "type": "documentAdditionOrUpdate",
       "canceledBy": null,
       "details": {
         "receivedDocuments": 1,
-        "indexedDocuments": 1
+        "indexedDocuments": 0
+      },
+      "error": {
+        "message": "A document cannot contain more than 65,535 fields.",
+        "code": "max_fields_limit_exceeded",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#max_fields_limit_exceeded"
       },
-      "error": null,
       "duration": "[duration]",
       "enqueuedAt": "[date]",
       "startedAt": "[date]",
@@ -1676,7 +1758,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "The `_geo` field in the document with the id: `11` is not an object. Was expecting an object with the `_geo.lat` and `_geo.lng` fields but instead got `\"foobar\"`.",
+        "message": "Index `test`: The `_geo` field in the document with the id: `\"11\"` is not an object. Was expecting an object with the `_geo.lat` and `_geo.lng` fields but instead got `\"foobar\"`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1714,7 +1796,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not find latitude nor longitude in the document with the id: `11`. Was expecting `_geo.lat` and `_geo.lng` fields.",
+        "message": "Index `test`: Could not find latitude nor longitude in the document with the id: `\"11\"`. Was expecting `_geo.lat` and `_geo.lng` fields.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1752,7 +1834,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not find latitude nor longitude in the document with the id: `11`. Was expecting `_geo.lat` and `_geo.lng` fields.",
+        "message": "Index `test`: Could not find latitude nor longitude in the document with the id: `\"11\"`. Was expecting `_geo.lat` and `_geo.lng` fields.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1790,7 +1872,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not find longitude in the document with the id: `11`. Was expecting a `_geo.lng` field.",
+        "message": "Index `test`: Could not find longitude in the document with the id: `\"11\"`. Was expecting a `_geo.lng` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1828,7 +1910,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not find latitude in the document with the id: `11`. Was expecting a `_geo.lat` field.",
+        "message": "Index `test`: Could not find latitude in the document with the id: `\"11\"`. Was expecting a `_geo.lat` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1866,7 +1948,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not find longitude in the document with the id: `11`. Was expecting a `_geo.lng` field.",
+        "message": "Index `test`: Could not find longitude in the document with the id: `\"11\"`. Was expecting a `_geo.lng` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1904,7 +1986,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not find latitude in the document with the id: `11`. Was expecting a `_geo.lat` field.",
+        "message": "Index `test`: Could not find latitude in the document with the id: `\"11\"`. Was expecting a `_geo.lat` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1942,7 +2024,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not parse latitude nor longitude in the document with the id: `11`. Was expecting finite numbers but instead got `false` and `true`.",
+        "message": "Index `test`: Could not parse latitude nor longitude in the document with the id: `\"11\"`. Was expecting finite numbers but instead got `false` and `true`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1980,7 +2062,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not find longitude in the document with the id: `11`. Was expecting a `_geo.lng` field.",
+        "message": "Index `test`: Could not find longitude in the document with the id: `\"11\"`. Was expecting a `_geo.lng` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2018,7 +2100,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not find latitude in the document with the id: `11`. Was expecting a `_geo.lat` field.",
+        "message": "Index `test`: Could not find latitude in the document with the id: `\"11\"`. Was expecting a `_geo.lat` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2056,7 +2138,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not parse latitude nor longitude in the document with the id: `11`. Was expecting finite numbers but instead got `\"doggo\"` and `\"doggo\"`.",
+        "message": "Index `test`: Could not parse latitude nor longitude in the document with the id: `\"11\"`. Was expecting finite numbers but instead got `\"doggo\"` and `\"doggo\"`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2094,7 +2176,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "The `_geo` field in the document with the id: `11` contains the following unexpected fields: `{\"doggo\":\"are the best\"}`.",
+        "message": "Index `test`: The `_geo` field in the document with the id: `\"11\"` contains the following unexpected fields: `{\"doggo\":\"are the best\"}`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2133,7 +2215,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not parse longitude in the document with the id: `12`. Was expecting a finite number but instead got `null`.",
+        "message": "Index `test`: Could not parse longitude in the document with the id: `\"12\"`. Was expecting a finite number but instead got `null`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2170,7 +2252,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not parse latitude in the document with the id: `12`. Was expecting a finite number but instead got `null`.",
+        "message": "Index `test`: Could not parse latitude in the document with the id: `\"12\"`. Was expecting a finite number but instead got `null`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2207,7 +2289,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Could not parse latitude nor longitude in the document with the id: `13`. Was expecting finite numbers but instead got `null` and `null`.",
+        "message": "Index `test`: Could not parse latitude nor longitude in the document with the id: `\"13\"`. Was expecting finite numbers but instead got `null` and `null`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2227,7 +2309,7 @@ async fn add_invalid_geo_and_then_settings() {
     let index = server.index("test");
     index.create(Some("id")).await;
 
-    // _geo is not an object
+    // _geo is not a correct object
     let documents = json!([
         {
             "id": "11",
@@ -2257,7 +2339,7 @@ async fn add_invalid_geo_and_then_settings() {
     }
     "###);
 
-    let (ret, code) = index.update_settings(json!({"sortableAttributes": ["_geo"]})).await;
+    let (ret, code) = index.update_settings(json!({ "sortableAttributes": ["_geo"] })).await;
     snapshot!(code, @"202 Accepted");
     let ret = index.wait_task(ret.uid()).await;
     snapshot!(ret, @r###"
@@ -2274,7 +2356,7 @@ async fn add_invalid_geo_and_then_settings() {
         ]
       },
       "error": {
-        "message": "Could not parse latitude in the document with the id: `\"11\"`. Was expecting a finite number but instead got `null`.",
+        "message": "Index `test`: Could not parse latitude in the document with the id: `\"11\"`. Was expecting a finite number but instead got `null`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"

crates/meilisearch/tests/documents/errors.rs

@@ -604,7 +604,7 @@ async fn delete_document_by_filter() {
         "originalFilter": "\"doggo = bernese\""
       },
       "error": {
-        "message": "Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
+        "message": "Index `EMPTY_INDEX`: Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
         "code": "invalid_document_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@@ -636,7 +636,7 @@ async fn delete_document_by_filter() {
         "originalFilter": "\"catto = jorts\""
       },
       "error": {
-        "message": "Attribute `catto` is not filterable. Available filterable attributes are: `id`, `title`.\n1:6 catto = jorts",
+        "message": "Index `SHARED_DOCUMENTS`: 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"

crates/meilisearch/tests/documents/update_documents.rs

@@ -172,7 +172,7 @@ async fn error_update_documents_bad_document_id() {
     assert_eq!(
         response["error"]["message"],
         json!(
-            r#"Document identifier `"foo & bar"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 512 bytes."#
+            r#"Document identifier `"foo & bar"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 511 bytes."#
         )
     );
     assert_eq!(response["error"]["code"], json!("invalid_document_id"));

crates/meilisearch/tests/dumps/mod.rs

@@ -79,7 +79,9 @@ async fn import_dump_v1_movie_raw() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -242,7 +244,9 @@ async fn import_dump_v1_movie_with_settings() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -391,7 +395,9 @@ async fn import_dump_v1_rubygems_with_settings() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -526,7 +532,9 @@ async fn import_dump_v2_movie_raw() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -673,7 +681,9 @@ async fn import_dump_v2_movie_with_settings() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -819,7 +829,9 @@ async fn import_dump_v2_rubygems_with_settings() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -954,7 +966,9 @@ async fn import_dump_v3_movie_raw() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -1101,7 +1115,9 @@ async fn import_dump_v3_movie_with_settings() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -1247,7 +1263,9 @@ async fn import_dump_v3_rubygems_with_settings() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -1382,7 +1400,9 @@ async fn import_dump_v4_movie_raw() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -1529,7 +1549,9 @@ async fn import_dump_v4_movie_with_settings() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -1675,7 +1697,9 @@ async fn import_dump_v4_rubygems_with_settings() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###
     );
@@ -1922,7 +1946,9 @@ async fn import_dump_v6_containing_experimental_features() {
         "maxTotalHits": 1000
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###);
 
@@ -2102,7 +2128,9 @@ async fn generate_and_import_dump_containing_vectors() {
         }
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###);
 

crates/meilisearch/tests/index/update_index.rs

@@ -95,7 +95,7 @@ async fn error_update_existing_primary_key() {
     let response = index.wait_task(2).await;
 
     let expected_response = json!({
-        "message": "Index already has a primary key: `id`.",
+        "message": "Index `test`: Index already has a primary key: `id`.",
         "code": "index_primary_key_already_exists",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#index_primary_key_already_exists"

crates/meilisearch/tests/search/errors.rs

@@ -711,7 +711,7 @@ async fn filter_invalid_attribute_array() {
     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",
+        "message": format!("Index `{}`: Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass", index.uid),
         "code": "invalid_search_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -733,7 +733,7 @@ async fn filter_invalid_attribute_string() {
     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",
+        "message": format!("Index `{}`: Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass", index.uid),
         "code": "invalid_search_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -940,7 +940,7 @@ async fn sort_unsortable_attribute() {
     index.wait_task(response.uid()).await.succeeded();
 
     let expected_response = json!({
-        "message": "Attribute `title` is not sortable. Available sortable attributes are: `id`.",
+        "message": format!("Index `{}`: Attribute `title` is not sortable. Available sortable attributes are: `id`.", index.uid),
         "code": "invalid_search_sort",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -998,7 +998,7 @@ async fn sort_unset_ranking_rule() {
     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.",
+        "message": format!("Index `{}`: You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.", index.uid),
         "code": "invalid_search_sort",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -1024,19 +1024,18 @@ async fn search_on_unknown_field() {
         index.update_settings_searchable_attributes(json!(["id", "title"])).await;
     index.wait_task(response.uid()).await.succeeded();
 
+    let expected_response = json!({
+        "message": format!("Index `{}`: Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.", index.uid),
+        "code": "invalid_search_attributes_to_search_on",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
+    });
     index
         .search(
             json!({"q": "Captain Marvel", "attributesToSearchOn": ["unknown"]}),
             |response, code| {
-                snapshot!(code, @"400 Bad Request");
-                snapshot!(json_string!(response), @r###"
-                {
-                  "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
-                  "code": "invalid_search_attributes_to_search_on",
-                  "type": "invalid_request",
-                  "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
-                }
-                "###);
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
             },
         )
         .await;
@@ -1050,19 +1049,18 @@ async fn search_on_unknown_field_plus_joker() {
         index.update_settings_searchable_attributes(json!(["id", "title"])).await;
     index.wait_task(response.uid()).await.succeeded();
 
+    let expected_response = json!({
+        "message": format!("Index `{}`: Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.", index.uid),
+        "code": "invalid_search_attributes_to_search_on",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
+    });
     index
         .search(
             json!({"q": "Captain Marvel", "attributesToSearchOn": ["*", "unknown"]}),
             |response, code| {
-                snapshot!(code, @"400 Bad Request");
-                snapshot!(json_string!(response), @r###"
-                {
-                  "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
-                  "code": "invalid_search_attributes_to_search_on",
-                  "type": "invalid_request",
-                  "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
-                }
-                "###);
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
             },
         )
         .await;
@@ -1071,15 +1069,8 @@ async fn search_on_unknown_field_plus_joker() {
         .search(
             json!({"q": "Captain Marvel", "attributesToSearchOn": ["unknown", "*"]}),
             |response, code| {
-                snapshot!(code, @"400 Bad Request");
-                snapshot!(json_string!(response), @r###"
-                {
-                  "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
-                  "code": "invalid_search_attributes_to_search_on",
-                  "type": "invalid_request",
-                  "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
-                }
-                "###);
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
             },
         )
         .await;
@@ -1092,47 +1083,44 @@ async fn distinct_at_search_time() {
     let (task, _) = index.create(None).await;
     index.wait_task(task.uid()).await.succeeded();
 
+    let expected_response = json!({
+        "message": format!("Index `{}`: Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. This index does not have configured filterable attributes.", index.uid),
+        "code": "invalid_search_distinct",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
+    });
     let (response, code) =
         index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": "doggo.truc"})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(response, @r###"
-    {
-      "message": "Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. This index does not have configured filterable attributes.",
-      "code": "invalid_search_distinct",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
-    }
-    "###);
+    assert_eq!(response, expected_response);
+    assert_eq!(code, 400);
 
     let (task, _) = index.update_settings_filterable_attributes(json!(["color", "machin"])).await;
     index.wait_task(task.uid()).await;
 
+    let expected_response = json!({
+        "message": format!("Index `{}`: Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, machin`.", index.uid),
+        "code": "invalid_search_distinct",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
+    });
     let (response, code) =
         index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": "doggo.truc"})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(response, @r###"
-    {
-      "message": "Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, machin`.",
-      "code": "invalid_search_distinct",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
-    }
-    "###);
+    assert_eq!(response, expected_response);
+    assert_eq!(code, 400);
 
     let (task, _) = index.update_settings_displayed_attributes(json!(["color"])).await;
     index.wait_task(task.uid()).await;
 
+    let expected_response = json!({
+        "message": format!("Index `{}`: Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, <..hidden-attributes>`.", index.uid),
+        "code": "invalid_search_distinct",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
+    });
     let (response, code) =
         index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": "doggo.truc"})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(response, @r###"
-    {
-      "message": "Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, <..hidden-attributes>`.",
-      "code": "invalid_search_distinct",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
-    }
-    "###);
+    assert_eq!(response, expected_response);
+    assert_eq!(code, 400);
 
     let (response, code) =
         index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": true})).await;

crates/meilisearch/tests/search/facet_search.rs

@@ -41,8 +41,8 @@ async fn simple_facet_search() {
 
     let documents = DOCUMENTS.clone();
     index.update_settings_filterable_attributes(json!(["genres"])).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
 
     let (response, code) =
         index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
@@ -57,6 +57,116 @@ async fn simple_facet_search() {
     assert_eq!(response["facetHits"].as_array().unwrap().len(), 1);
 }
 
+#[actix_rt::test]
+async fn simple_facet_search_on_movies() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let documents = json!([
+      {
+        "id": 1,
+        "title": "Carol",
+        "genres": [
+          "Romance",
+          "Drama"
+        ],
+        "color": [
+          "red"
+        ],
+        "platforms": [
+          "MacOS",
+          "Linux",
+          "Windows"
+        ]
+      },
+      {
+        "id": 2,
+        "title": "Wonder Woman",
+        "genres": [
+          "Action",
+          "Adventure"
+        ],
+        "color": [
+          "green"
+        ],
+        "platforms": [
+          "MacOS"
+        ]
+      },
+      {
+        "id": 3,
+        "title": "Life of Pi",
+        "genres": [
+          "Adventure",
+          "Drama"
+        ],
+        "color": [
+          "blue"
+        ],
+        "platforms": [
+          "Windows"
+        ]
+      },
+      {
+        "id": 4,
+        "title": "Mad Max: Fury Road",
+        "genres": [
+          "Adventure",
+          "Science Fiction"
+        ],
+        "color": [
+          "red"
+        ],
+        "platforms": [
+          "MacOS",
+          "Linux"
+        ]
+      },
+      {
+        "id": 5,
+        "title": "Moana",
+        "genres": [
+          "Fantasy",
+          "Action"
+        ],
+        "color": [
+          "red"
+        ],
+        "platforms": [
+          "Windows"
+        ]
+      },
+      {
+        "id": 6,
+        "title": "Philadelphia",
+        "genres": [
+          "Drama"
+        ],
+        "color": [
+          "blue"
+        ],
+        "platforms": [
+          "MacOS",
+          "Linux",
+          "Windows"
+        ]
+      }
+    ]);
+    let (response, code) =
+        index.update_settings_filterable_attributes(json!(["genres", "color"])).await;
+    assert_eq!(202, code, "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
+
+    let (response, code) =
+        index.facet_search(json!({"facetQuery": "", "facetName": "genres", "q": "" })).await;
+
+    assert_eq!(code, 200, "{}", response);
+    snapshot!(response["facetHits"], @r###"[{"value":"Action","count":2},{"value":"Adventure","count":3},{"value":"Drama","count":3},{"value":"Fantasy","count":1},{"value":"Romance","count":1},{"value":"Science Fiction","count":1}]"###);
+}
+
 #[actix_rt::test]
 async fn advanced_facet_search() {
     let server = Server::new().await;
@@ -65,8 +175,8 @@ async fn advanced_facet_search() {
     let documents = DOCUMENTS.clone();
     index.update_settings_filterable_attributes(json!(["genres"])).await;
     index.update_settings_typo_tolerance(json!({ "enabled": false })).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(2).await;
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
 
     let (response, code) =
         index.facet_search(json!({"facetName": "genres", "facetQuery": "adventre"})).await;
@@ -89,8 +199,8 @@ async fn more_advanced_facet_search() {
     let documents = DOCUMENTS.clone();
     index.update_settings_filterable_attributes(json!(["genres"])).await;
     index.update_settings_typo_tolerance(json!({ "disableOnWords": ["adventre"] })).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(2).await;
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
 
     let (response, code) =
         index.facet_search(json!({"facetName": "genres", "facetQuery": "adventre"})).await;
@@ -113,8 +223,8 @@ async fn simple_facet_search_with_max_values() {
     let documents = DOCUMENTS.clone();
     index.update_settings_faceting(json!({ "maxValuesPerFacet": 1 })).await;
     index.update_settings_filterable_attributes(json!(["genres"])).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(2).await;
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
 
     let (response, code) =
         index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
@@ -135,8 +245,8 @@ async fn simple_facet_search_by_count_with_max_values() {
         )
         .await;
     index.update_settings_filterable_attributes(json!(["genres"])).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(2).await;
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
 
     let (response, code) =
         index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
@@ -151,8 +261,8 @@ async fn non_filterable_facet_search_error() {
     let index = server.index("test");
 
     let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
 
     let (response, code) =
         index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
@@ -170,8 +280,8 @@ async fn facet_search_dont_support_words() {
 
     let documents = DOCUMENTS.clone();
     index.update_settings_filterable_attributes(json!(["genres"])).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
 
     let (response, code) =
         index.facet_search(json!({"facetName": "genres", "facetQuery": "words"})).await;
@@ -188,8 +298,8 @@ async fn simple_facet_search_with_sort_by_count() {
     let documents = DOCUMENTS.clone();
     index.update_settings_faceting(json!({ "sortFacetValuesBy": { "*": "count" } })).await;
     index.update_settings_filterable_attributes(json!(["genres"])).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(2).await;
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
 
     let (response, code) =
         index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
@@ -200,3 +310,129 @@ async fn simple_facet_search_with_sort_by_count() {
     assert_eq!(hits[0], json!({ "value": "Action", "count": 3 }));
     assert_eq!(hits[1], json!({ "value": "Adventure", "count": 2 }));
 }
+
+#[actix_rt::test]
+async fn add_documents_and_deactivate_facet_search() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let documents = DOCUMENTS.clone();
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
+    let (response, code) = index
+        .update_settings(json!({
+            "facetSearch": false,
+            "filterableAttributes": ["genres"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    let (response, code) =
+        index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
+
+    assert_eq!(code, 400, "{}", response);
+    snapshot!(response, @r###"
+    {
+      "message": "The facet search is disabled for this index",
+      "code": "facet_search_disabled",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#facet_search_disabled"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn deactivate_facet_search_and_add_documents() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, code) = index
+        .update_settings(json!({
+            "facetSearch": false,
+            "filterableAttributes": ["genres"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+    let documents = DOCUMENTS.clone();
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
+
+    let (response, code) =
+        index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
+
+    assert_eq!(code, 400, "{}", response);
+    snapshot!(response, @r###"
+    {
+      "message": "The facet search is disabled for this index",
+      "code": "facet_search_disabled",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#facet_search_disabled"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn deactivate_facet_search_add_documents_and_activate_facet_search() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, code) = index
+        .update_settings(json!({
+            "facetSearch": false,
+            "filterableAttributes": ["genres"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+    let documents = DOCUMENTS.clone();
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+            "facetSearch": true,
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    let (response, code) =
+        index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
+
+    assert_eq!(code, 200, "{}", response);
+    assert_eq!(dbg!(response)["facetHits"].as_array().unwrap().len(), 2);
+}
+
+#[actix_rt::test]
+async fn deactivate_facet_search_add_documents_and_reset_facet_search() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, code) = index
+        .update_settings(json!({
+            "facetSearch": false,
+            "filterableAttributes": ["genres"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+    let documents = DOCUMENTS.clone();
+    let (response, _code) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+            "facetSearch": serde_json::Value::Null,
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    let (response, code) =
+        index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
+
+    assert_eq!(code, 200, "{}", response);
+    assert_eq!(dbg!(response)["facetHits"].as_array().unwrap().len(), 2);
+}

crates/meilisearch/tests/search/formatted.rs

@@ -4,6 +4,58 @@ use super::*;
 use crate::common::Server;
 use crate::json;
 
+#[actix_rt::test]
+async fn search_formatted_from_sdk() {
+    let server = Server::new_shared();
+    let index = server.unique_index();
+
+    index
+        .update_settings(
+            json!({ "filterableAttributes": ["genre"], "searchableAttributes": ["title"] }),
+        )
+        .await;
+
+    let documents = json!([
+      { "id": 123,  "title": "Pride and Prejudice",                     "genre": "romance" },
+      { "id": 456,  "title": "Le Petit Prince",                         "genre": "adventure" },
+      { "id": 1,    "title": "Alice In Wonderland",                     "genre": "adventure" },
+      { "id": 2,    "title": "Le Rouge et le Noir",                     "genre": "romance" },
+      { "id": 1344, "title": "The Hobbit",                              "genre": "adventure" },
+      { "id": 4,    "title": "Harry Potter and the Half-Blood Prince",  "genre": "fantasy" },
+      { "id": 7,    "title": "Harry Potter and the Chamber of Secrets", "genre": "fantasy" },
+      { "id": 42,   "title": "The Hitchhiker's Guide to the Galaxy" }
+    ]);
+    let (response, _) = index.add_documents(documents, None).await;
+    index.wait_task(response.uid()).await;
+
+    index
+        .search(
+            json!({ "q":"prince",
+              "attributesToCrop": ["title"],
+              "cropLength": 2,
+              "filter": "genre = adventure",
+              "attributesToHighlight": ["title"],
+              "attributesToRetrieve": ["title"]
+            }),
+            |response, code| {
+                assert_eq!(code, 200, "{}", response);
+                allow_duplicates! {
+                  assert_json_snapshot!(response["hits"][0],
+                        { "._rankingScore" => "[score]" },
+                        @r###"
+                  {
+                    "title": "Le Petit Prince",
+                    "_formatted": {
+                      "title": "…Petit <em>Prince</em>"
+                    }
+                  }
+                  "###);
+                }
+            },
+        )
+        .await;
+}
+
 #[actix_rt::test]
 async fn formatted_contain_wildcard() {
     let server = Server::new_shared();

crates/meilisearch/tests/search/geo.rs

@@ -70,8 +70,8 @@ async fn geo_bounding_box_with_string_and_number() {
     let documents = DOCUMENTS.clone();
     index.update_settings_filterable_attributes(json!(["_geo"])).await;
     index.update_settings_sortable_attributes(json!(["_geo"])).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(2).await;
+    let (ret, _code) = index.add_documents(documents, None).await;
+    index.wait_task(ret.uid()).await.succeeded();
 
     index
         .search(

crates/meilisearch/tests/search/mod.rs

@@ -15,6 +15,7 @@ mod pagination;
 mod restrict_searchable;
 mod search_queue;
 
+use meili_snap::{json_string, snapshot};
 use meilisearch::Opt;
 use tempfile::TempDir;
 
@@ -62,6 +63,71 @@ async fn simple_search() {
         .await;
 }
 
+#[actix_rt::test]
+async fn search_with_stop_word() {
+    // related to https://github.com/meilisearch/meilisearch/issues/4984
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (_, code) = index
+        .update_settings(json!({"stopWords": ["the", "The", "a", "an", "to", "in", "of"]}))
+        .await;
+    meili_snap::snapshot!(code, @"202 Accepted");
+
+    let documents = DOCUMENTS.clone();
+    index.add_documents(documents, None).await;
+    index.wait_task(1).await;
+
+    // prefix search
+    index
+        .search(json!({"q": "to the", "attributesToHighlight": ["title"], "attributesToRetrieve": ["title"] }), |response, code| {
+            assert_eq!(code, 200, "{}", response);
+            snapshot!(json_string!(response["hits"]), @"[]");
+        })
+        .await;
+
+    // non-prefix search
+    index
+          .search(json!({"q": "to the ", "attributesToHighlight": ["title"], "attributesToRetrieve": ["title"] }), |response, code| {
+              assert_eq!(code, 200, "{}", response);
+              snapshot!(json_string!(response["hits"]), @r###"
+              [
+                {
+                  "title": "Shazam!",
+                  "_formatted": {
+                    "title": "Shazam!"
+                  }
+                },
+                {
+                  "title": "Captain Marvel",
+                  "_formatted": {
+                    "title": "Captain Marvel"
+                  }
+                },
+                {
+                  "title": "Escape Room",
+                  "_formatted": {
+                    "title": "Escape Room"
+                  }
+                },
+                {
+                  "title": "How to Train Your Dragon: The Hidden World",
+                  "_formatted": {
+                    "title": "How to Train Your Dragon: The Hidden World"
+                  }
+                },
+                {
+                  "title": "Gläss",
+                  "_formatted": {
+                    "title": "Gläss"
+                  }
+                }
+              ]
+              "###);
+          })
+          .await;
+}
+
 #[actix_rt::test]
 async fn phrase_search_with_stop_word() {
     // related to https://github.com/meilisearch/meilisearch/issues/3521
@@ -750,9 +816,9 @@ async fn test_score_details() {
                     ],
                     "_vectors": {
                       "manual": [
-                        -100.0,
-                        231.0,
-                        32.0
+                        -100,
+                        231,
+                        32
                       ]
                     },
                     "_rankingScoreDetails": {
@@ -1543,9 +1609,9 @@ async fn simple_search_with_strange_synonyms() {
                 ],
                 "_vectors": {
                   "manual": [
-                    -100.0,
-                    231.0,
-                    32.0
+                    -100,
+                    231,
+                    32
                   ]
                 }
               }
@@ -1568,9 +1634,9 @@ async fn simple_search_with_strange_synonyms() {
                 ],
                 "_vectors": {
                   "manual": [
-                    -100.0,
-                    231.0,
-                    32.0
+                    -100,
+                    231,
+                    32
                   ]
                 }
               }
@@ -1593,9 +1659,9 @@ async fn simple_search_with_strange_synonyms() {
                 ],
                 "_vectors": {
                   "manual": [
-                    -100.0,
-                    231.0,
-                    32.0
+                    -100,
+                    231,
+                    32
                   ]
                 }
               }
@@ -1604,3 +1670,79 @@ async fn simple_search_with_strange_synonyms() {
         })
         .await;
 }
+
+#[actix_rt::test]
+async fn change_attributes_settings() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    index.update_settings(json!({ "searchableAttributes": ["father", "mother"] })).await;
+
+    let documents = NESTED_DOCUMENTS.clone();
+    index.add_documents(json!(documents), None).await;
+    index.wait_task(1).await;
+
+    index.update_settings(json!({ "searchableAttributes": ["father", "mother", "doggos"], "filterableAttributes": ["doggos"] })).await;
+    index.wait_task(2).await;
+
+    // search
+    index
+        .search(
+            json!({
+                "q": "bobby",
+                "attributesToRetrieve": ["id", "doggos"]
+            }),
+            |response, code| {
+                assert_eq!(code, 200, "{}", response);
+                meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "id": 852,
+                    "doggos": [
+                      {
+                        "name": "bobby",
+                        "age": 2
+                      },
+                      {
+                        "name": "buddy",
+                        "age": 4
+                      }
+                    ]
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+
+    // filter
+    index
+        .search(
+            json!({
+                "q": "",
+                "filter": "doggos.age < 5",
+                "attributesToRetrieve": ["id", "doggos"]
+            }),
+            |response, code| {
+                assert_eq!(code, 200, "{}", response);
+                meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "id": 852,
+                    "doggos": [
+                      {
+                        "name": "bobby",
+                        "age": 2
+                      },
+                      {
+                        "name": "buddy",
+                        "age": 4
+                      }
+                    ]
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+}

crates/meilisearch/tests/search/multi.rs

@@ -113,9 +113,9 @@ async fn simple_search_single_index() {
             ],
             "_vectors": {
               "manual": [
-                -100.0,
-                340.0,
-                90.0
+                -100,
+                340,
+                90
               ]
             }
           }
@@ -138,9 +138,9 @@ async fn simple_search_single_index() {
             ],
             "_vectors": {
               "manual": [
-                1.0,
-                2.0,
-                54.0
+                1,
+                2,
+                54
               ]
             }
           }
@@ -182,9 +182,9 @@ async fn federation_single_search_single_index() {
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              340.0,
-              90.0
+              -100,
+              340,
+              90
             ]
           },
           "_federation": {
@@ -305,9 +305,9 @@ async fn federation_two_search_single_index() {
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              340.0,
-              90.0
+              -100,
+              340,
+              90
             ]
           },
           "_federation": {
@@ -325,9 +325,9 @@ async fn federation_two_search_single_index() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -480,9 +480,9 @@ async fn simple_search_two_indexes() {
             ],
             "_vectors": {
               "manual": [
-                -100.0,
-                340.0,
-                90.0
+                -100,
+                340,
+                90
               ]
             }
           }
@@ -513,9 +513,9 @@ async fn simple_search_two_indexes() {
             "cattos": "pésti",
             "_vectors": {
               "manual": [
-                1.0,
-                2.0,
-                3.0
+                1,
+                2,
+                3
               ]
             }
           },
@@ -535,9 +535,9 @@ async fn simple_search_two_indexes() {
             ],
             "_vectors": {
               "manual": [
-                1.0,
-                2.0,
-                54.0
+                1,
+                2,
+                54
               ]
             }
           }
@@ -585,9 +585,9 @@ async fn federation_two_search_two_indexes() {
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              340.0,
-              90.0
+              -100,
+              340,
+              90
             ]
           },
           "_federation": {
@@ -613,9 +613,9 @@ async fn federation_two_search_two_indexes() {
           "cattos": "pésti",
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              3.0
+              1,
+              2,
+              3
             ]
           },
           "_federation": {
@@ -640,9 +640,9 @@ async fn federation_two_search_two_indexes() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -707,9 +707,9 @@ async fn federation_multiple_search_multiple_indexes() {
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              340.0,
-              90.0
+              -100,
+              340,
+              90
             ]
           },
           "_federation": {
@@ -735,9 +735,9 @@ async fn federation_multiple_search_multiple_indexes() {
           "cattos": "pésti",
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              3.0
+              1,
+              2,
+              3
             ]
           },
           "_federation": {
@@ -773,9 +773,9 @@ async fn federation_multiple_search_multiple_indexes() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -793,9 +793,9 @@ async fn federation_multiple_search_multiple_indexes() {
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              -23.0,
-              32.0
+              10,
+              -23,
+              32
             ]
           },
           "_federation": {
@@ -824,9 +824,9 @@ async fn federation_multiple_search_multiple_indexes() {
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              23.0,
-              32.0
+              10,
+              23,
+              32
             ]
           },
           "_federation": {
@@ -869,9 +869,9 @@ async fn federation_multiple_search_multiple_indexes() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -898,9 +898,9 @@ async fn federation_multiple_search_multiple_indexes() {
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              231.0,
-              32.0
+              -100,
+              231,
+              32
             ]
           },
           "_federation": {
@@ -1070,7 +1070,7 @@ async fn federation_one_query_error() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
+      "message": "Inside `.queries[1]`: Index `nested`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
       "code": "invalid_search_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -1102,7 +1102,7 @@ async fn federation_one_query_sort_error() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
+      "message": "Inside `.queries[1]`: Index `nested`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
       "code": "invalid_search_sort",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -1166,7 +1166,7 @@ async fn federation_multiple_query_errors() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[0]`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
+      "message": "Inside `.queries[0]`: Index `test`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
       "code": "invalid_search_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -1198,7 +1198,7 @@ async fn federation_multiple_query_sort_errors() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[0]`: Attribute `title` is not sortable. This index does not have configured sortable attributes.",
+      "message": "Inside `.queries[0]`: Index `test`: Attribute `title` is not sortable. This index does not have configured sortable attributes.",
       "code": "invalid_search_sort",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -1231,7 +1231,7 @@ async fn federation_multiple_query_errors_interleaved() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Attribute `doggos` is not filterable. This index does not have configured filterable attributes.\n1:7 doggos IN [intel, kefir]",
+      "message": "Inside `.queries[1]`: Index `nested`: Attribute `doggos` is not filterable. This index does not have configured filterable attributes.\n1:7 doggos IN [intel, kefir]",
       "code": "invalid_search_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -1264,7 +1264,7 @@ async fn federation_multiple_query_sort_errors_interleaved() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
+      "message": "Inside `.queries[1]`: Index `nested`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
       "code": "invalid_search_sort",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -1393,9 +1393,9 @@ async fn federation_sort_same_indexes_same_criterion_same_direction() {
           "cattos": "pésti",
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              3.0
+              1,
+              2,
+              3
             ]
           },
           "_federation": {
@@ -1414,9 +1414,9 @@ async fn federation_sort_same_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              23.0,
-              32.0
+              10,
+              23,
+              32
             ]
           },
           "_federation": {
@@ -1442,9 +1442,9 @@ async fn federation_sort_same_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -1474,9 +1474,9 @@ async fn federation_sort_same_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              23.0,
-              32.0
+              10,
+              23,
+              32
             ]
           },
           "_federation": {
@@ -1522,9 +1522,9 @@ async fn federation_sort_same_indexes_same_criterion_same_direction() {
           "cattos": "pésti",
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              3.0
+              1,
+              2,
+              3
             ]
           },
           "_federation": {
@@ -1550,9 +1550,9 @@ async fn federation_sort_same_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -1582,9 +1582,9 @@ async fn federation_sort_same_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              23.0,
-              32.0
+              10,
+              23,
+              32
             ]
           },
           "_federation": {
@@ -1716,9 +1716,9 @@ async fn federation_sort_same_indexes_different_criterion_same_direction() {
           "cattos": "pésti",
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              3.0
+              1,
+              2,
+              3
             ]
           },
           "_federation": {
@@ -1748,9 +1748,9 @@ async fn federation_sort_same_indexes_different_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              23.0,
-              32.0
+              10,
+              23,
+              32
             ]
           },
           "_federation": {
@@ -1769,9 +1769,9 @@ async fn federation_sort_same_indexes_different_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              23.0,
-              32.0
+              10,
+              23,
+              32
             ]
           },
           "_federation": {
@@ -1797,9 +1797,9 @@ async fn federation_sort_same_indexes_different_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -1845,9 +1845,9 @@ async fn federation_sort_same_indexes_different_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -1874,9 +1874,9 @@ async fn federation_sort_same_indexes_different_criterion_same_direction() {
           "cattos": "pésti",
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              3.0
+              1,
+              2,
+              3
             ]
           },
           "_federation": {
@@ -1906,9 +1906,9 @@ async fn federation_sort_same_indexes_different_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              23.0,
-              32.0
+              10,
+              23,
+              32
             ]
           },
           "_federation": {
@@ -2103,9 +2103,9 @@ async fn federation_sort_different_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -2124,9 +2124,9 @@ async fn federation_sort_different_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              -23.0,
-              32.0
+              10,
+              -23,
+              32
             ]
           },
           "_federation": {
@@ -2145,9 +2145,9 @@ async fn federation_sort_different_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              340.0,
-              90.0
+              -100,
+              340,
+              90
             ]
           },
           "_federation": {
@@ -2166,9 +2166,9 @@ async fn federation_sort_different_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              231.0,
-              32.0
+              -100,
+              231,
+              32
             ]
           },
           "_federation": {
@@ -2187,9 +2187,9 @@ async fn federation_sort_different_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              3.0
+              1,
+              2,
+              3
             ]
           },
           "_federation": {
@@ -2228,9 +2228,9 @@ async fn federation_sort_different_indexes_same_criterion_same_direction() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -2415,9 +2415,9 @@ async fn federation_sort_different_ranking_rules() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -2436,9 +2436,9 @@ async fn federation_sort_different_ranking_rules() {
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              -23.0,
-              32.0
+              10,
+              -23,
+              32
             ]
           },
           "_federation": {
@@ -2457,9 +2457,9 @@ async fn federation_sort_different_ranking_rules() {
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              340.0,
-              90.0
+              -100,
+              340,
+              90
             ]
           },
           "_federation": {
@@ -2478,9 +2478,9 @@ async fn federation_sort_different_ranking_rules() {
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              231.0,
-              32.0
+              -100,
+              231,
+              32
             ]
           },
           "_federation": {
@@ -2499,9 +2499,9 @@ async fn federation_sort_different_ranking_rules() {
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              3.0
+              1,
+              2,
+              3
             ]
           },
           "_federation": {
@@ -2716,9 +2716,9 @@ async fn federation_sort_different_indexes_different_criterion_same_direction()
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -2757,9 +2757,9 @@ async fn federation_sort_different_indexes_different_criterion_same_direction()
           ],
           "_vectors": {
             "manual": [
-              10.0,
-              -23.0,
-              32.0
+              10,
+              -23,
+              32
             ]
           },
           "_federation": {
@@ -2778,9 +2778,9 @@ async fn federation_sort_different_indexes_different_criterion_same_direction()
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              340.0,
-              90.0
+              -100,
+              340,
+              90
             ]
           },
           "_federation": {
@@ -2799,9 +2799,9 @@ async fn federation_sort_different_indexes_different_criterion_same_direction()
           ],
           "_vectors": {
             "manual": [
-              -100.0,
-              231.0,
-              32.0
+              -100,
+              231,
+              32
             ]
           },
           "_federation": {
@@ -2820,9 +2820,9 @@ async fn federation_sort_different_indexes_different_criterion_same_direction()
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              3.0
+              1,
+              2,
+              3
             ]
           },
           "_federation": {
@@ -2881,9 +2881,9 @@ async fn federation_sort_different_indexes_different_criterion_same_direction()
           ],
           "_vectors": {
             "manual": [
-              1.0,
-              2.0,
-              54.0
+              1,
+              2,
+              54
             ]
           },
           "_federation": {
@@ -4346,10 +4346,10 @@ async fn federation_vector_two_indexes() {
 
     let (response, code) = server
         .multi_search(json!({"federation": {}, "queries": [
-        {"indexUid" : "vectors-animal", "vector": [1.0, 0.0, 0.5], "hybrid": {"semanticRatio": 1.0, "embedder": "animal"}},
+        {"indexUid" : "vectors-animal", "vector": [1.0, 0.0, 0.5], "hybrid": {"semanticRatio": 1.0, "embedder": "animal"}, "retrieveVectors": true},
         // joyful and energetic first
-        {"indexUid": "vectors-sentiment", "vector": [0.8, 0.6], "hybrid": {"semanticRatio": 1.0, "embedder": "sentiment"}},
-        {"indexUid": "vectors-sentiment", "q": "dog"},
+        {"indexUid": "vectors-sentiment", "vector": [0.8, 0.6], "hybrid": {"semanticRatio": 1.0, "embedder": "sentiment"}, "retrieveVectors": true},
+        {"indexUid": "vectors-sentiment", "q": "dog", "retrieveVectors": true},
         ]}))
         .await;
     snapshot!(code, @"200 OK");
@@ -4364,7 +4364,16 @@ async fn federation_vector_two_indexes() {
               0.8,
               0.09,
               0.8
-            ]
+            ],
+            "sentiment": {
+              "embeddings": [
+                [
+                  0.800000011920929,
+                  0.30000001192092896
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-sentiment",
@@ -4379,7 +4388,17 @@ async fn federation_vector_two_indexes() {
             "sentiment": [
               0.8,
               0.3
-            ]
+            ],
+            "animal": {
+              "embeddings": [
+                [
+                  0.800000011920929,
+                  0.09000000357627869,
+                  0.800000011920929
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-animal",
@@ -4394,7 +4413,17 @@ async fn federation_vector_two_indexes() {
             "sentiment": [
               -1.0,
               0.1
-            ]
+            ],
+            "animal": {
+              "embeddings": [
+                [
+                  0.8500000238418579,
+                  0.019999999552965164,
+                  0.10000000149011612
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-animal",
@@ -4410,7 +4439,16 @@ async fn federation_vector_two_indexes() {
               0.9,
               0.8,
               0.05
-            ]
+            ],
+            "sentiment": {
+              "embeddings": [
+                [
+                  -0.10000000149011612,
+                  0.550000011920929
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-sentiment",
@@ -4426,7 +4464,16 @@ async fn federation_vector_two_indexes() {
               0.85,
               0.02,
               0.1
-            ]
+            ],
+            "sentiment": {
+              "embeddings": [
+                [
+                  -1.0,
+                  0.10000000149011612
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-sentiment",
@@ -4441,7 +4488,17 @@ async fn federation_vector_two_indexes() {
             "sentiment": [
               -0.2,
               0.65
-            ]
+            ],
+            "animal": {
+              "embeddings": [
+                [
+                  0.800000011920929,
+                  0.8999999761581421,
+                  0.5
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-animal",
@@ -4456,7 +4513,17 @@ async fn federation_vector_two_indexes() {
             "sentiment": [
               -0.1,
               0.55
-            ]
+            ],
+            "animal": {
+              "embeddings": [
+                [
+                  0.8999999761581421,
+                  0.800000011920929,
+                  0.05000000074505806
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-animal",
@@ -4472,7 +4539,16 @@ async fn federation_vector_two_indexes() {
               0.8,
               0.9,
               0.5
-            ]
+            ],
+            "sentiment": {
+              "embeddings": [
+                [
+                  -0.20000000298023224,
+                  0.6499999761581421
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-sentiment",
@@ -4492,8 +4568,8 @@ async fn federation_vector_two_indexes() {
     // hybrid search, distinct embedder
     let (response, code) = server
         .multi_search(json!({"federation": {}, "queries": [
-          {"indexUid" : "vectors-animal", "vector": [1.0, 0.0, 0.5], "hybrid": {"semanticRatio": 1.0, "embedder": "animal"}, "showRankingScore": true},
-          {"indexUid": "vectors-sentiment", "vector": [-1, 0.6], "q": "beagle", "hybrid": {"semanticRatio": 1.0, "embedder": "sentiment"}, "showRankingScore": true},
+          {"indexUid" : "vectors-animal", "vector": [1.0, 0.0, 0.5], "hybrid": {"semanticRatio": 1.0, "embedder": "animal"}, "showRankingScore": true, "retrieveVectors": true},
+          {"indexUid": "vectors-sentiment", "vector": [-1, 0.6], "q": "beagle", "hybrid": {"semanticRatio": 1.0, "embedder": "sentiment"}, "showRankingScore": true, "retrieveVectors": true,},
         ]}))
         .await;
     snapshot!(code, @"200 OK");
@@ -4507,7 +4583,17 @@ async fn federation_vector_two_indexes() {
             "sentiment": [
               0.8,
               0.3
-            ]
+            ],
+            "animal": {
+              "embeddings": [
+                [
+                  0.800000011920929,
+                  0.09000000357627869,
+                  0.800000011920929
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-animal",
@@ -4523,7 +4609,17 @@ async fn federation_vector_two_indexes() {
             "sentiment": [
               -1.0,
               0.1
-            ]
+            ],
+            "animal": {
+              "embeddings": [
+                [
+                  0.8500000238418579,
+                  0.019999999552965164,
+                  0.10000000149011612
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-animal",
@@ -4540,7 +4636,16 @@ async fn federation_vector_two_indexes() {
               0.85,
               0.02,
               0.1
-            ]
+            ],
+            "sentiment": {
+              "embeddings": [
+                [
+                  -1.0,
+                  0.10000000149011612
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-sentiment",
@@ -4557,7 +4662,16 @@ async fn federation_vector_two_indexes() {
               0.8,
               0.9,
               0.5
-            ]
+            ],
+            "sentiment": {
+              "embeddings": [
+                [
+                  -0.20000000298023224,
+                  0.6499999761581421
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-sentiment",
@@ -4573,7 +4687,17 @@ async fn federation_vector_two_indexes() {
             "sentiment": [
               -0.2,
               0.65
-            ]
+            ],
+            "animal": {
+              "embeddings": [
+                [
+                  0.800000011920929,
+                  0.8999999761581421,
+                  0.5
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-animal",
@@ -4589,7 +4713,17 @@ async fn federation_vector_two_indexes() {
             "sentiment": [
               -0.1,
               0.55
-            ]
+            ],
+            "animal": {
+              "embeddings": [
+                [
+                  0.8999999761581421,
+                  0.800000011920929,
+                  0.05000000074505806
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-animal",
@@ -4606,7 +4740,16 @@ async fn federation_vector_two_indexes() {
               0.9,
               0.8,
               0.05
-            ]
+            ],
+            "sentiment": {
+              "embeddings": [
+                [
+                  -0.10000000149011612,
+                  0.550000011920929
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-sentiment",
@@ -4623,7 +4766,16 @@ async fn federation_vector_two_indexes() {
               0.8,
               0.09,
               0.8
-            ]
+            ],
+            "sentiment": {
+              "embeddings": [
+                [
+                  0.800000011920929,
+                  0.30000001192092896
+                ]
+              ],
+              "regenerate": false
+            }
           },
           "_federation": {
             "indexUid": "vectors-sentiment",

crates/meilisearch/tests/search/restrict_searchable.rs

@@ -367,3 +367,50 @@ async fn search_on_exact_field() {
         })
         .await;
 }
+
+#[actix_rt::test]
+async fn phrase_search_on_title() {
+    let server = Server::new().await;
+    let documents = json!([
+      { "id": 8, "desc": "Document Review", "title": "Document Review Specialist II" },
+      { "id": 5, "desc": "Document Review", "title": "Document Review Attorney" },
+      { "id": 4, "desc": "Document Review", "title": "Document Review Manager - Cyber Incident Response (Remote)" },
+      { "id": 3, "desc": "Document Review", "title": "Document Review Paralegal" },
+      { "id": 2, "desc": "Document Review", "title": "Document Controller (Saudi National)" },
+      { "id": 1, "desc": "Document Review", "title": "Document Reviewer" },
+      { "id": 7, "desc": "Document Review", "title": "Document Review Specialist II" },
+      { "id": 6, "desc": "Document Review", "title": "Document Review (Entry Level)" }
+    ]);
+    let index = index_with_documents(&server, &documents).await;
+
+    index
+        .search(
+            json!({"q": "\"Document Review\"", "attributesToSearchOn": ["title"], "attributesToRetrieve": ["title"]}),
+            |response, code| {
+                snapshot!(code, @"200 OK");
+                snapshot!(json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "title": "Document Review Specialist II"
+                  },
+                  {
+                    "title": "Document Review Attorney"
+                  },
+                  {
+                    "title": "Document Review Manager - Cyber Incident Response (Remote)"
+                  },
+                  {
+                    "title": "Document Review Paralegal"
+                  },
+                  {
+                    "title": "Document Review Specialist II"
+                  },
+                  {
+                    "title": "Document Review (Entry Level)"
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+}

crates/meilisearch/tests/settings/get_settings.rs

@@ -1,44 +1,185 @@
-use std::collections::HashMap;
-
-use once_cell::sync::Lazy;
-
-use crate::common::{Server, Value};
+use crate::common::Server;
 use crate::json;
 
-static DEFAULT_SETTINGS_VALUES: Lazy<HashMap<&'static str, Value>> = Lazy::new(|| {
-    let mut map = HashMap::new();
-    map.insert("displayed_attributes", json!(["*"]));
-    map.insert("searchable_attributes", json!(["*"]));
-    map.insert("localized_attributes", json!(null));
-    map.insert("filterable_attributes", json!([]));
-    map.insert("distinct_attribute", json!(null));
-    map.insert(
-        "ranking_rules",
-        json!(["words", "typo", "proximity", "attribute", "sort", "exactness"]),
-    );
-    map.insert("stop_words", json!([]));
-    map.insert("non_separator_tokens", json!([]));
-    map.insert("separator_tokens", json!([]));
-    map.insert("dictionary", json!([]));
-    map.insert("synonyms", json!({}));
-    map.insert(
-        "faceting",
-        json!({
-            "maxValuesPerFacet": json!(100),
-            "sortFacetValuesBy": {
-                "*": "alpha"
+macro_rules! test_setting_routes {
+    ($({setting: $setting:ident, update_verb: $update_verb:ident, default_value: $default_value:tt},) *) => {
+        $(
+            mod $setting {
+                use crate::common::Server;
+
+                #[actix_rt::test]
+                async fn get_unexisting_index() {
+                    let server = Server::new().await;
+                    let url = format!("/indexes/test/settings/{}",
+                        stringify!($setting)
+                        .chars()
+                        .map(|c| if c == '_' { '-' } else { c })
+                        .collect::<String>());
+                    let (_response, code) = server.service.get(url).await;
+                    assert_eq!(code, 404);
+                }
+
+                #[actix_rt::test]
+                async fn update_unexisting_index() {
+                    let server = Server::new().await;
+                    let url = format!("/indexes/test/settings/{}",
+                        stringify!($setting)
+                        .chars()
+                        .map(|c| if c == '_' { '-' } else { c })
+                        .collect::<String>());
+                    let (response, code) = server.service.$update_verb(url, serde_json::Value::Null.into()).await;
+                    assert_eq!(code, 202, "{}", response);
+                    server.index("").wait_task(0).await;
+                    let (response, code) = server.index("test").get().await;
+                    assert_eq!(code, 200, "{}", response);
+                }
+
+                #[actix_rt::test]
+                async fn delete_unexisting_index() {
+                    let server = Server::new().await;
+                    let url = format!("/indexes/test/settings/{}",
+                        stringify!($setting)
+                        .chars()
+                        .map(|c| if c == '_' { '-' } else { c })
+                        .collect::<String>());
+                    let (_, code) = server.service.delete(url).await;
+                    assert_eq!(code, 202);
+                    let response = server.index("").wait_task(0).await;
+                    assert_eq!(response["status"], "failed");
+                }
+
+                #[actix_rt::test]
+                async fn get_default() {
+                    let server = Server::new().await;
+                    let index = server.index("test");
+                    let (response, code) = index.create(None).await;
+                    assert_eq!(code, 202, "{}", response);
+                    index.wait_task(0).await;
+                    let url = format!("/indexes/test/settings/{}",
+                        stringify!($setting)
+                        .chars()
+                        .map(|c| if c == '_' { '-' } else { c })
+                        .collect::<String>());
+                    let (response, code) = server.service.get(url).await;
+                    assert_eq!(code, 200, "{}", response);
+                    let expected = crate::json!($default_value);
+                    assert_eq!(expected, response);
+                }
             }
-        }),
-    );
-    map.insert(
-        "pagination",
-        json!({
-            "maxTotalHits": json!(1000),
-        }),
-    );
-    map.insert("search_cutoff_ms", json!(null));
-    map
-});
+        )*
+
+        #[actix_rt::test]
+        async fn all_setting_tested() {
+            let expected = std::collections::BTreeSet::from_iter(meilisearch::routes::indexes::settings::ALL_SETTINGS_NAMES.iter());
+            let tested = std::collections::BTreeSet::from_iter([$(stringify!($setting)),*].iter());
+            let diff: Vec<_> = expected.difference(&tested).collect();
+            assert!(diff.is_empty(), "Not all settings were tested, please add the following settings to the `test_setting_routes!` macro: {:?}", diff);
+        }
+    };
+}
+
+test_setting_routes!(
+    {
+        setting: filterable_attributes,
+        update_verb: put,
+        default_value: []
+    },
+    {
+        setting: displayed_attributes,
+        update_verb: put,
+        default_value: ["*"]
+    },
+    {
+        setting: localized_attributes,
+        update_verb: put,
+        default_value: null
+    },
+    {
+        setting: searchable_attributes,
+        update_verb: put,
+        default_value: ["*"]
+    },
+    {
+        setting: distinct_attribute,
+        update_verb: put,
+        default_value: null
+    },
+    {
+        setting: stop_words,
+        update_verb: put,
+        default_value: []
+    },
+    {
+        setting: separator_tokens,
+        update_verb: put,
+        default_value: []
+    },
+    {
+        setting: non_separator_tokens,
+        update_verb: put,
+        default_value: []
+    },
+    {
+        setting: dictionary,
+        update_verb: put,
+        default_value: []
+    },
+    {
+        setting: ranking_rules,
+        update_verb: put,
+        default_value: ["words", "typo", "proximity", "attribute", "sort", "exactness"]
+    },
+    {
+        setting: synonyms,
+        update_verb: put,
+        default_value: {}
+    },
+    {
+        setting: pagination,
+        update_verb: patch,
+        default_value: {"maxTotalHits": 1000}
+    },
+    {
+        setting: faceting,
+        update_verb: patch,
+        default_value: {"maxValuesPerFacet": 100, "sortFacetValuesBy": {"*": "alpha"}}
+    },
+    {
+        setting: search_cutoff_ms,
+        update_verb: put,
+        default_value: null
+    },
+    {
+        setting: embedders,
+        update_verb: patch,
+        default_value: null
+    },
+    {
+        setting: facet_search,
+        update_verb: put,
+        default_value: true
+    },
+    {
+        setting: prefix_search,
+        update_verb: put,
+        default_value: "indexingTime"
+    },
+    {
+        setting: proximity_precision,
+        update_verb: put,
+        default_value: "byWord"
+    },
+    {
+        setting: sortable_attributes,
+        update_verb: put,
+        default_value: []
+    },
+    {
+        setting: typo_tolerance,
+        update_verb: patch,
+        default_value: {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": []}
+    },
+);
 
 #[actix_rt::test]
 async fn get_settings_unexisting_index() {
@@ -56,7 +197,7 @@ async fn get_settings() {
     let (response, code) = index.settings().await;
     assert_eq!(code, 200);
     let settings = response.as_object().unwrap();
-    assert_eq!(settings.keys().len(), 17);
+    assert_eq!(settings.keys().len(), 19);
     assert_eq!(settings["displayedAttributes"], json!(["*"]));
     assert_eq!(settings["searchableAttributes"], json!(["*"]));
     assert_eq!(settings["filterableAttributes"], json!([]));
@@ -87,6 +228,8 @@ async fn get_settings() {
     );
     assert_eq!(settings["proximityPrecision"], json!("byWord"));
     assert_eq!(settings["searchCutoffMs"], json!(null));
+    assert_eq!(settings["prefixSearch"], json!("indexingTime"));
+    assert_eq!(settings["facetSearch"], json!(true));
 }
 
 #[actix_rt::test]
@@ -199,7 +342,9 @@ async fn secrets_are_hidden_in_settings() {
         }
       },
       "searchCutoffMs": null,
-      "localizedAttributes": null
+      "localizedAttributes": null,
+      "facetSearch": true,
+      "prefixSearch": "indexingTime"
     }
     "###);
 
@@ -338,93 +483,6 @@ async fn error_update_setting_unexisting_index_invalid_uid() {
     "###);
 }
 
-macro_rules! test_setting_routes {
-    ($($setting:ident $write_method:ident), *) => {
-        $(
-            mod $setting {
-                use crate::common::Server;
-                use super::DEFAULT_SETTINGS_VALUES;
-
-                #[actix_rt::test]
-                async fn get_unexisting_index() {
-                    let server = Server::new().await;
-                    let url = format!("/indexes/test/settings/{}",
-                        stringify!($setting)
-                        .chars()
-                        .map(|c| if c == '_' { '-' } else { c })
-                        .collect::<String>());
-                    let (_response, code) = server.service.get(url).await;
-                    assert_eq!(code, 404);
-                }
-
-                #[actix_rt::test]
-                async fn update_unexisting_index() {
-                    let server = Server::new().await;
-                    let url = format!("/indexes/test/settings/{}",
-                        stringify!($setting)
-                        .chars()
-                        .map(|c| if c == '_' { '-' } else { c })
-                        .collect::<String>());
-                    let (response, code) = server.service.$write_method(url, serde_json::Value::Null.into()).await;
-                    assert_eq!(code, 202, "{}", response);
-                    server.index("").wait_task(0).await;
-                    let (response, code) = server.index("test").get().await;
-                    assert_eq!(code, 200, "{}", response);
-                }
-
-                #[actix_rt::test]
-                async fn delete_unexisting_index() {
-                    let server = Server::new().await;
-                    let url = format!("/indexes/test/settings/{}",
-                        stringify!($setting)
-                        .chars()
-                        .map(|c| if c == '_' { '-' } else { c })
-                        .collect::<String>());
-                    let (_, code) = server.service.delete(url).await;
-                    assert_eq!(code, 202);
-                    let response = server.index("").wait_task(0).await;
-                    assert_eq!(response["status"], "failed");
-                }
-
-                #[actix_rt::test]
-                async fn get_default() {
-                    let server = Server::new().await;
-                    let index = server.index("test");
-                    let (response, code) = index.create(None).await;
-                    assert_eq!(code, 202, "{}", response);
-                    index.wait_task(0).await;
-                    let url = format!("/indexes/test/settings/{}",
-                        stringify!($setting)
-                        .chars()
-                        .map(|c| if c == '_' { '-' } else { c })
-                        .collect::<String>());
-                    let (response, code) = server.service.get(url).await;
-                    assert_eq!(code, 200, "{}", response);
-                    let expected = DEFAULT_SETTINGS_VALUES.get(stringify!($setting)).unwrap();
-                    assert_eq!(expected, &response);
-                }
-            }
-        )*
-    };
-}
-
-test_setting_routes!(
-    filterable_attributes put,
-    displayed_attributes put,
-    localized_attributes put,
-    searchable_attributes put,
-    distinct_attribute put,
-    stop_words put,
-    separator_tokens put,
-    non_separator_tokens put,
-    dictionary put,
-    ranking_rules put,
-    synonyms put,
-    pagination patch,
-    faceting patch,
-    search_cutoff_ms put
-);
-
 #[actix_rt::test]
 async fn error_set_invalid_ranking_rules() {
     let server = Server::new().await;

crates/meilisearch/tests/settings/mod.rs

@@ -1,5 +1,6 @@
 mod distinct;
 mod errors;
 mod get_settings;
+mod prefix_search_settings;
 mod proximity_settings;
 mod tokenizer_customization;

crates/meilisearch/tests/settings/prefix_search_settings.rs

@@ -0,0 +1,458 @@
+use meili_snap::{json_string, snapshot};
+use once_cell::sync::Lazy;
+
+use crate::common::Server;
+use crate::json;
+
+static DOCUMENTS: Lazy<crate::common::Value> = Lazy::new(|| {
+    json!([
+        {
+            "id": 1,
+            "a": "Soup of the day",
+            "b": "manythefishou",
+        },
+        {
+            "id": 2,
+            "a": "Soup of day so",
+            "b": "manythe manythelazyfish",
+        },
+        {
+            "id": 3,
+            "a": "the Soup of day",
+            "b": "manythelazyfish",
+        },
+    ])
+});
+
+#[actix_rt::test]
+async fn add_docs_and_disable() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, _code) = index.add_documents(DOCUMENTS.clone(), None).await;
+    index.wait_task(response.uid()).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+            "prefixSearch": "disabled",
+            "rankingRules": ["words", "typo", "proximity"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    // only 1 document should match
+    index
+        .search(json!({"q": "so", "attributesToHighlight": ["a", "b"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 2,
+                "a": "Soup of day so",
+                "b": "manythe manythelazyfish",
+                "_formatted": {
+                  "id": "2",
+                  "a": "Soup of day <em>so</em>",
+                  "b": "manythe manythelazyfish"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    // only 1 document should match
+    index
+        .search(json!({"q": "manythe", "attributesToHighlight": ["a", "b"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 2,
+                "a": "Soup of day so",
+                "b": "manythe manythelazyfish",
+                "_formatted": {
+                  "id": "2",
+                  "a": "Soup of day so",
+                  "b": "<em>manythe</em> manythelazyfish"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn disable_and_add_docs() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, code) = index
+        .update_settings(json!({
+            "prefixSearch": "disabled",
+            "rankingRules": ["words", "typo", "proximity"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    let (response, _code) = index.add_documents(DOCUMENTS.clone(), None).await;
+    index.wait_task(response.uid()).await;
+
+    // only 1 document should match
+    index
+        .search(json!({"q": "so", "attributesToHighlight": ["a", "b"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 2,
+                "a": "Soup of day so",
+                "b": "manythe manythelazyfish",
+                "_formatted": {
+                  "id": "2",
+                  "a": "Soup of day <em>so</em>",
+                  "b": "manythe manythelazyfish"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "manythe", "attributesToHighlight": ["a", "b"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 2,
+                "a": "Soup of day so",
+                "b": "manythe manythelazyfish",
+                "_formatted": {
+                  "id": "2",
+                  "a": "Soup of day so",
+                  "b": "<em>manythe</em> manythelazyfish"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn disable_add_docs_and_enable() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, code) = index
+        .update_settings(json!({
+            "prefixSearch": "disabled",
+            "rankingRules": ["words", "typo", "proximity"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    let (response, _code) = index.add_documents(DOCUMENTS.clone(), None).await;
+    index.wait_task(response.uid()).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+            "prefixSearch": "indexingTime",
+            "rankingRules": ["words", "typo", "proximity"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(2).await;
+
+    // all documents should match
+    index
+        .search(json!({"q": "so", "attributesToHighlight": ["a", "b"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 1,
+                "a": "Soup of the day",
+                "b": "manythefishou",
+                "_formatted": {
+                  "id": "1",
+                  "a": "<em>So</em>up of the day",
+                  "b": "manythefishou"
+                }
+              },
+              {
+                "id": 2,
+                "a": "Soup of day so",
+                "b": "manythe manythelazyfish",
+                "_formatted": {
+                  "id": "2",
+                  "a": "<em>So</em>up of day <em>so</em>",
+                  "b": "manythe manythelazyfish"
+                }
+              },
+              {
+                "id": 3,
+                "a": "the Soup of day",
+                "b": "manythelazyfish",
+                "_formatted": {
+                  "id": "3",
+                  "a": "the <em>So</em>up of day",
+                  "b": "manythelazyfish"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "manythe", "attributesToHighlight": ["a", "b"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 1,
+                "a": "Soup of the day",
+                "b": "manythefishou",
+                "_formatted": {
+                  "id": "1",
+                  "a": "Soup of the day",
+                  "b": "<em>manythe</em>fishou"
+                }
+              },
+              {
+                "id": 2,
+                "a": "Soup of day so",
+                "b": "manythe manythelazyfish",
+                "_formatted": {
+                  "id": "2",
+                  "a": "Soup of day so",
+                  "b": "<em>manythe</em> <em>manythe</em>lazyfish"
+                }
+              },
+              {
+                "id": 3,
+                "a": "the Soup of day",
+                "b": "manythelazyfish",
+                "_formatted": {
+                  "id": "3",
+                  "a": "the Soup of day",
+                  "b": "<em>manythe</em>lazyfish"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn disable_add_docs_and_reset() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, code) = index
+        .update_settings(json!({
+            "prefixSearch": "disabled",
+            "rankingRules": ["words", "typo", "proximity"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    let (response, _code) = index.add_documents(DOCUMENTS.clone(), None).await;
+    index.wait_task(response.uid()).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+            "prefixSearch": serde_json::Value::Null,
+            "rankingRules": ["words", "typo", "proximity"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(2).await;
+
+    // all documents should match
+    index
+        .search(json!({"q": "so", "attributesToHighlight": ["a", "b"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 1,
+                "a": "Soup of the day",
+                "b": "manythefishou",
+                "_formatted": {
+                  "id": "1",
+                  "a": "<em>So</em>up of the day",
+                  "b": "manythefishou"
+                }
+              },
+              {
+                "id": 2,
+                "a": "Soup of day so",
+                "b": "manythe manythelazyfish",
+                "_formatted": {
+                  "id": "2",
+                  "a": "<em>So</em>up of day <em>so</em>",
+                  "b": "manythe manythelazyfish"
+                }
+              },
+              {
+                "id": 3,
+                "a": "the Soup of day",
+                "b": "manythelazyfish",
+                "_formatted": {
+                  "id": "3",
+                  "a": "the <em>So</em>up of day",
+                  "b": "manythelazyfish"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "manythe", "attributesToHighlight": ["a", "b"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 1,
+                "a": "Soup of the day",
+                "b": "manythefishou",
+                "_formatted": {
+                  "id": "1",
+                  "a": "Soup of the day",
+                  "b": "<em>manythe</em>fishou"
+                }
+              },
+              {
+                "id": 2,
+                "a": "Soup of day so",
+                "b": "manythe manythelazyfish",
+                "_formatted": {
+                  "id": "2",
+                  "a": "Soup of day so",
+                  "b": "<em>manythe</em> <em>manythe</em>lazyfish"
+                }
+              },
+              {
+                "id": 3,
+                "a": "the Soup of day",
+                "b": "manythelazyfish",
+                "_formatted": {
+                  "id": "3",
+                  "a": "the Soup of day",
+                  "b": "<em>manythe</em>lazyfish"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn default_behavior() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, code) = index
+        .update_settings(json!({
+            "rankingRules": ["words", "typo", "proximity"],
+        }))
+        .await;
+    assert_eq!("202", code.as_str(), "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    let (response, _code) = index.add_documents(DOCUMENTS.clone(), None).await;
+    index.wait_task(response.uid()).await;
+
+    // all documents should match
+    index
+        .search(json!({"q": "so", "attributesToHighlight": ["a", "b"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 1,
+                "a": "Soup of the day",
+                "b": "manythefishou",
+                "_formatted": {
+                  "id": "1",
+                  "a": "<em>So</em>up of the day",
+                  "b": "manythefishou"
+                }
+              },
+              {
+                "id": 2,
+                "a": "Soup of day so",
+                "b": "manythe manythelazyfish",
+                "_formatted": {
+                  "id": "2",
+                  "a": "<em>So</em>up of day <em>so</em>",
+                  "b": "manythe manythelazyfish"
+                }
+              },
+              {
+                "id": 3,
+                "a": "the Soup of day",
+                "b": "manythelazyfish",
+                "_formatted": {
+                  "id": "3",
+                  "a": "the <em>So</em>up of day",
+                  "b": "manythelazyfish"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "manythe", "attributesToHighlight": ["a", "b"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "id": 1,
+                "a": "Soup of the day",
+                "b": "manythefishou",
+                "_formatted": {
+                  "id": "1",
+                  "a": "Soup of the day",
+                  "b": "<em>manythe</em>fishou"
+                }
+              },
+              {
+                "id": 2,
+                "a": "Soup of day so",
+                "b": "manythe manythelazyfish",
+                "_formatted": {
+                  "id": "2",
+                  "a": "Soup of day so",
+                  "b": "<em>manythe</em> <em>manythe</em>lazyfish"
+                }
+              },
+              {
+                "id": 3,
+                "a": "the Soup of day",
+                "b": "manythelazyfish",
+                "_formatted": {
+                  "id": "3",
+                  "a": "the Soup of day",
+                  "b": "<em>manythe</em>lazyfish"
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+}

crates/meilisearch/tests/similar/errors.rs

@@ -79,7 +79,7 @@ async fn similar_bad_id() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 512 bytes.",
+      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 511 bytes.",
       "code": "invalid_similar_id",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_similar_id"
@@ -172,7 +172,7 @@ async fn similar_invalid_id() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 512 bytes.",
+      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 511 bytes.",
       "code": "invalid_similar_id",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_similar_id"

crates/meilisearch/tests/snapshot/mod.rs

@@ -129,11 +129,11 @@ async fn perform_on_demand_snapshot() {
 
     index.load_test_set().await;
 
-    server.index("doggo").create(Some("bone")).await;
-    index.wait_task(2).await;
+    let (task, _) = server.index("doggo").create(Some("bone")).await;
+    index.wait_task(task.uid()).await.succeeded();
 
-    server.index("doggo").create(Some("bone")).await;
-    index.wait_task(2).await;
+    let (task, _) = server.index("doggo").create(Some("bone")).await;
+    index.wait_task(task.uid()).await.failed();
 
     let (task, code) = server.create_snapshot().await;
     snapshot!(code, @"202 Accepted");

crates/meilisearch/tests/tasks/mod.rs

@@ -448,7 +448,7 @@ async fn test_summarized_delete_documents_by_filter() {
         "originalFilter": "\"doggo = bernese\""
       },
       "error": {
-        "message": "Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
+        "message": "Index `test`: Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
         "code": "invalid_document_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_filter"

crates/meilisearch/tests/vector/binary_quantized.rs

@@ -318,7 +318,7 @@ async fn try_to_disable_binary_quantization() {
         }
       },
       "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.",
+        "message": "Index `doggo`: `.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"

crates/meilisearch/tests/vector/mod.rs

@@ -250,7 +250,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Missing field `regenerate` inside `.manual`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Missing field `._vectors.manual.regenerate`\n  - note: `._vectors.manual` must be an array of floats, an array of arrays of floats, or an object with field `regenerate`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -280,7 +280,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Missing field `regenerate` inside `.manual`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Missing field `._vectors.manual.regenerate`\n  - note: `._vectors.manual` must be an array of floats, an array of arrays of floats, or an object with field `regenerate`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -311,7 +311,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.regenerate`: expected a boolean, but found a string: `\"yes please\"`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Could not parse `._vectors.manual.regenerate`: invalid type: string \"yes please\", expected a boolean at line 1 column 26",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -323,8 +323,7 @@ async fn user_provided_embeddings_error() {
     }
     "###);
 
-    let documents =
-        json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": true }}});
+    let documents = json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": true, "regenerate": true }}});
     let (value, code) = index.add_documents(documents, None).await;
     snapshot!(code, @"202 Accepted");
     let task = index.wait_task(value.uid()).await;
@@ -341,7 +340,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings`: expected null or an array, but found a boolean: `true`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings`: expected null or an array, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -353,8 +352,7 @@ async fn user_provided_embeddings_error() {
     }
     "###);
 
-    let documents =
-        json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": [true] }}});
+    let documents = json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": [true], "regenerate": true }}});
     let (value, code) = index.add_documents(documents, None).await;
     snapshot!(code, @"202 Accepted");
     let task = index.wait_task(value.uid()).await;
@@ -371,7 +369,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0]`: expected a number or an array, but found a boolean: `true`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[0]`: expected a number or an array, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -383,8 +381,7 @@ async fn user_provided_embeddings_error() {
     }
     "###);
 
-    let documents =
-        json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": [[true]] }}});
+    let documents = json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": [[true]], "regenerate": false }}});
     let (value, code) = index.add_documents(documents, None).await;
     snapshot!(code, @"202 Accepted");
     let task = index.wait_task(value.uid()).await;
@@ -401,7 +398,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0][0]`: expected a number, but found a boolean: `true`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[0][0]`: expected a number, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -443,7 +440,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[1]`: expected a number, but found an array: `[0.2,0.3]`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[1]`: expected a number, but found an array: `[0.2,0.3]`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -472,7 +469,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[1]`: expected an array, but found a number: `0.3`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[1]`: expected an array, but found a number: `0.3`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -501,7 +498,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0][1]`: expected a number, but found a boolean: `true`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[0][1]`: expected a number, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -542,7 +539,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"40\" and at least 4 other document(s)\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
+        "message": "Index `doggo`: While embedding documents for embedder `manual`: no vectors provided for document `40` and at least 4 other document(s)\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -572,7 +569,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
+        "message": "Index `doggo`: While embedding documents for embedder `manual`: no vectors provided for document `42`\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -602,7 +599,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
+        "message": "Index `doggo`: While embedding documents for embedder `manual`: no vectors provided for document `42`\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"

crates/meilisearch/tests/vector/openai.rs

@@ -137,13 +137,14 @@ fn long_text() -> &'static str {
 }
 
 async fn create_mock_tokenized() -> (MockServer, Value) {
-    create_mock_with_template("{{doc.text}}", ModelDimensions::Large, false).await
+    create_mock_with_template("{{doc.text}}", ModelDimensions::Large, false, false).await
 }
 
 async fn create_mock_with_template(
     document_template: &str,
     model_dimensions: ModelDimensions,
     fallible: bool,
+    slow: bool,
 ) -> (MockServer, Value) {
     let mock_server = MockServer::start().await;
     const API_KEY: &str = "my-api-key";
@@ -154,7 +155,11 @@ async fn create_mock_with_template(
     Mock::given(method("POST"))
         .and(path("/"))
         .respond_with(move |req: &Request| {
-            // 0. maybe return 500
+            // 0. wait for a long time
+            if slow {
+              std::thread::sleep(std::time::Duration::from_secs(1));
+            }
+            // 1. maybe return 500
             if fallible {
              let attempt = attempt.fetch_add(1, Ordering::Relaxed);
              let failed = matches!(attempt % 4, 0 | 1 | 3);
@@ -167,7 +172,7 @@ async fn create_mock_with_template(
                 }))
              }
             }
-            // 1. check API key
+            // 2. check API key
             match req.headers.get("Authorization") {
                 Some(api_key) if api_key == API_KEY_BEARER => {
                     {}
@@ -202,7 +207,7 @@ async fn create_mock_with_template(
                     )
                 }
             }
-            // 2. parse text inputs
+            // 3. parse text inputs
             let query: serde_json::Value = match req.body_json() {
                 Ok(query) => query,
                 Err(_error) => return ResponseTemplate::new(400).set_body_json(
@@ -223,7 +228,7 @@ async fn create_mock_with_template(
                 panic!("Expected {model_dimensions:?}, got {query_model_dimensions:?}")
             }
 
-            // 3. for each text, find embedding in responses
+            // 4. for each text, find embedding in responses
             let serde_json::Value::Array(inputs) = &query["input"] else {
                 panic!("Unexpected `input` value")
             };
@@ -283,7 +288,7 @@ async fn create_mock_with_template(
                 "embedding": embedding,
             })).collect();
 
-            // 4. produce output from embeddings
+            // 5. produce output from embeddings
             ResponseTemplate::new(200).set_body_json(json!({
                 "object": "list",
                 "data": data,
@@ -317,23 +322,27 @@ const DOGGO_TEMPLATE: &str = r#"{%- if doc.gender == "F" -%}Une chienne nommée
         {%- endif %}, de race {{doc.breed}}."#;
 
 async fn create_mock() -> (MockServer, Value) {
-    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Large, false).await
+    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Large, false, false).await
 }
 
 async fn create_mock_dimensions() -> (MockServer, Value) {
-    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Large512, false).await
+    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Large512, false, false).await
 }
 
 async fn create_mock_small_embedding_model() -> (MockServer, Value) {
-    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Small, false).await
+    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Small, false, false).await
 }
 
 async fn create_mock_legacy_embedding_model() -> (MockServer, Value) {
-    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Ada, false).await
+    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Ada, false, false).await
 }
 
 async fn create_fallible_mock() -> (MockServer, Value) {
-    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Large, true).await
+    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Large, true, false).await
+}
+
+async fn create_slow_mock() -> (MockServer, Value) {
+    create_mock_with_template(DOGGO_TEMPLATE, ModelDimensions::Large, true, true).await
 }
 
 // basic test "it works"
@@ -704,7 +713,7 @@ async fn bad_api_key() {
         }
       },
       "error": {
-        "message": "While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"Incorrect API key provided: Bearer doggo. You can find your API key at https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":\"invalid_api_key\"}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
+        "message": "Index `doggo`: While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"Incorrect API key provided: Bearer doggo. You can find your API key at https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":\"invalid_api_key\"}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -748,7 +757,7 @@ async fn bad_api_key() {
         }
       },
       "error": {
-        "message": "While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY), or as the password field (with blank username) if you're accessing the API from your browser and are prompted for a username and password. You can obtain an API key from https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":null}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
+        "message": "Index `doggo`: While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY), or as the password field (with blank username) if you're accessing the API from your browser and are prompted for a username and password. You can obtain an API key from https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":null}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1884,4 +1893,115 @@ async fn it_still_works() {
     ]
     "###);
 }
+
+// test with a server that responds 500 on 3 out of 4 calls
+#[actix_rt::test]
+async fn timeout() {
+    let (_mock, setting) = create_slow_mock().await;
+    let server = get_server_vector().await;
+    let index = server.index("doggo");
+
+    let (response, code) = index
+        .update_settings(json!({
+          "embedders": {
+              "default": setting,
+          },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    let task = server.wait_task(response.uid()).await;
+    snapshot!(task["status"], @r###""succeeded""###);
+    let documents = json!([
+      {"id": 0, "name": "kefir", "gender": "M", "birthyear": 2023, "breed": "Patou"},
+    ]);
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    let task = index.wait_task(value.uid()).await;
+    snapshot!(task, @r###"
+    {
+      "uid": "[uid]",
+      "batchUid": "[batch_uid]",
+      "indexUid": "doggo",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    let (documents, _code) = index
+        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
+        .await;
+    snapshot!(json_string!(documents, {".results.*._vectors.default.embeddings" => "[vector]"}), @r###"
+    {
+      "results": [
+        {
+          "id": 0,
+          "name": "kefir",
+          "gender": "M",
+          "birthyear": 2023,
+          "breed": "Patou",
+          "_vectors": {
+            "default": {
+              "embeddings": "[vector]",
+              "regenerate": true
+            }
+          }
+        }
+      ],
+      "offset": 0,
+      "limit": 20,
+      "total": 1
+    }
+    "###);
+
+    let (response, code) = index
+        .search_post(json!({
+            "q": "grand chien de berger des montagnes",
+            "hybrid": {"semanticRatio": 0.99, "embedder": "default"}
+        }))
+        .await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["semanticHitCount"]), @"0");
+    snapshot!(json_string!(response["hits"]), @"[]");
+
+    let (response, code) = index
+        .search_post(json!({
+            "q": "grand chien de berger des montagnes",
+            "hybrid": {"semanticRatio": 0.99, "embedder": "default"}
+        }))
+        .await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["semanticHitCount"]), @"1");
+    snapshot!(json_string!(response["hits"]), @r###"
+    [
+      {
+        "id": 0,
+        "name": "kefir",
+        "gender": "M",
+        "birthyear": 2023,
+        "breed": "Patou"
+      }
+    ]
+    "###);
+
+    let (response, code) = index
+        .search_post(json!({
+            "q": "grand chien de berger des montagnes",
+            "hybrid": {"semanticRatio": 0.99, "embedder": "default"}
+        }))
+        .await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["semanticHitCount"]), @"0");
+    snapshot!(json_string!(response["hits"]), @"[]");
+}
+
 // test with a server that wrongly responds 400

crates/meilisearch/tests/vector/rest.rs

@@ -1,5 +1,4 @@
 use std::collections::BTreeMap;
-use std::sync::atomic::{AtomicUsize, Ordering};
 
 use meili_snap::{json_string, snapshot};
 use reqwest::IntoUrl;
@@ -13,13 +12,22 @@ use crate::vector::{get_server_vector, GetAllDocumentsOptions};
 async fn create_mock() -> (MockServer, Value) {
     let mock_server = MockServer::start().await;
 
-    let counter = AtomicUsize::new(0);
+    let text_to_embedding: BTreeMap<_, _> = vec![
+        // text -> embedding
+        ("kefir", [0.0, 0.0, 0.0]),
+        ("intel", [1.0, 1.0, 1.0]),
+    ]
+    // turn into btree
+    .into_iter()
+    .collect();
 
     Mock::given(method("POST"))
         .and(path("/"))
-        .respond_with(move |_req: &Request| {
-            let counter = counter.fetch_add(1, Ordering::Relaxed);
-            ResponseTemplate::new(200).set_body_json(json!({ "data": vec![counter; 3] }))
+        .respond_with(move |req: &Request| {
+            let text: String = req.body_json().unwrap();
+            ResponseTemplate::new(200).set_body_json(
+                json!({ "data": text_to_embedding.get(text.as_str()).unwrap_or(&[99., 99., 99.]) }),
+            )
         })
         .mount(&mock_server)
         .await;
@@ -32,13 +40,14 @@ async fn create_mock() -> (MockServer, Value) {
         "request": "{{text}}",
         "response": {
           "data": "{{embedding}}"
-        }
+        },
+        "documentTemplate": "{{doc.name}}",
     });
 
     (mock_server, embedder_settings)
 }
 
-async fn create_mock_map() -> (MockServer, Value) {
+async fn create_mock_default_template() -> (MockServer, Value) {
     let mock_server = MockServer::start().await;
 
     let text_to_embedding: BTreeMap<_, _> = vec![
@@ -97,7 +106,14 @@ struct SingleResponse {
 async fn create_mock_multiple() -> (MockServer, Value) {
     let mock_server = MockServer::start().await;
 
-    let counter = AtomicUsize::new(0);
+    let text_to_embedding: BTreeMap<_, _> = vec![
+        // text -> embedding
+        ("kefir", [0.0, 0.0, 0.0]),
+        ("intel", [1.0, 1.0, 1.0]),
+    ]
+    // turn into btree
+    .into_iter()
+    .collect();
 
     Mock::given(method("POST"))
         .and(path("/"))
@@ -115,8 +131,11 @@ async fn create_mock_multiple() -> (MockServer, Value) {
                 .input
                 .into_iter()
                 .map(|text| SingleResponse {
+                    embedding: text_to_embedding
+                        .get(text.as_str())
+                        .unwrap_or(&[99., 99., 99.])
+                        .to_vec(),
                     text,
-                    embedding: vec![counter.fetch_add(1, Ordering::Relaxed) as f32; 3],
                 })
                 .collect();
 
@@ -142,7 +161,8 @@ async fn create_mock_multiple() -> (MockServer, Value) {
             },
             "{{..}}"
           ]
-        }
+        },
+        "documentTemplate": "{{doc.name}}"
     });
 
     (mock_server, embedder_settings)
@@ -156,7 +176,14 @@ struct SingleRequest {
 async fn create_mock_single_response_in_array() -> (MockServer, Value) {
     let mock_server = MockServer::start().await;
 
-    let counter = AtomicUsize::new(0);
+    let text_to_embedding: BTreeMap<_, _> = vec![
+        // text -> embedding
+        ("kefir", [0.0, 0.0, 0.0]),
+        ("intel", [1.0, 1.0, 1.0]),
+    ]
+    // turn into btree
+    .into_iter()
+    .collect();
 
     Mock::given(method("POST"))
         .and(path("/"))
@@ -171,8 +198,11 @@ async fn create_mock_single_response_in_array() -> (MockServer, Value) {
             };
 
             let output = vec![SingleResponse {
+                embedding: text_to_embedding
+                    .get(req.input.as_str())
+                    .unwrap_or(&[99., 99., 99.])
+                    .to_vec(),
                 text: req.input,
-                embedding: vec![counter.fetch_add(1, Ordering::Relaxed) as f32; 3],
             }];
 
             let response = MultipleResponse { output };
@@ -196,7 +226,8 @@ async fn create_mock_single_response_in_array() -> (MockServer, Value) {
               "embedding": "{{embedding}}"
             }
           ]
-        }
+        },
+        "documentTemplate": "{{doc.name}}"
     });
 
     (mock_server, embedder_settings)
@@ -205,7 +236,14 @@ async fn create_mock_single_response_in_array() -> (MockServer, Value) {
 async fn create_mock_raw_with_custom_header() -> (MockServer, Value) {
     let mock_server = MockServer::start().await;
 
-    let counter = AtomicUsize::new(0);
+    let text_to_embedding: BTreeMap<_, _> = vec![
+        // text -> embedding
+        ("kefir", [0.0, 0.0, 0.0]),
+        ("intel", [1.0, 1.0, 1.0]),
+    ]
+    // turn into btree
+    .into_iter()
+    .collect();
 
     Mock::given(method("POST"))
         .and(path("/"))
@@ -223,7 +261,7 @@ async fn create_mock_raw_with_custom_header() -> (MockServer, Value) {
                 }
             }
 
-            let _req: String = match req.body_json() {
+            let req: String = match req.body_json() {
                 Ok(req) => req,
                 Err(error) => {
                     return ResponseTemplate::new(400).set_body_json(json!({
@@ -232,7 +270,7 @@ async fn create_mock_raw_with_custom_header() -> (MockServer, Value) {
                 }
             };
 
-            let output = vec![counter.fetch_add(1, Ordering::Relaxed) as f32; 3];
+            let output = text_to_embedding.get(req.as_str()).unwrap_or(&[99., 99., 99.]).to_vec();
 
             ResponseTemplate::new(200).set_body_json(output)
         })
@@ -245,7 +283,8 @@ async fn create_mock_raw_with_custom_header() -> (MockServer, Value) {
         "url": url,
         "request": "{{text}}",
         "response": "{{embedding}}",
-        "headers": {"my-nonstandard-auth": "bearer of the ring"}
+        "headers": {"my-nonstandard-auth": "bearer of the ring"},
+        "documentTemplate": "{{doc.name}}"
     });
 
     (mock_server, embedder_settings)
@@ -254,12 +293,19 @@ async fn create_mock_raw_with_custom_header() -> (MockServer, Value) {
 async fn create_mock_raw() -> (MockServer, Value) {
     let mock_server = MockServer::start().await;
 
-    let counter = AtomicUsize::new(0);
+    let text_to_embedding: BTreeMap<_, _> = vec![
+        // text -> embedding
+        ("kefir", [0.0, 0.0, 0.0]),
+        ("intel", [1.0, 1.0, 1.0]),
+    ]
+    // turn into btree
+    .into_iter()
+    .collect();
 
     Mock::given(method("POST"))
         .and(path("/"))
         .respond_with(move |req: &Request| {
-            let _req: String = match req.body_json() {
+            let req: String = match req.body_json() {
                 Ok(req) => req,
                 Err(error) => {
                     return ResponseTemplate::new(400).set_body_json(json!({
@@ -268,7 +314,7 @@ async fn create_mock_raw() -> (MockServer, Value) {
                 }
             };
 
-            let output = vec![counter.fetch_add(1, Ordering::Relaxed) as f32; 3];
+            let output = text_to_embedding.get(req.as_str()).unwrap_or(&[99., 99., 99.]).to_vec();
 
             ResponseTemplate::new(200).set_body_json(output)
         })
@@ -281,29 +327,30 @@ async fn create_mock_raw() -> (MockServer, Value) {
         "url": url,
         "dimensions": 3,
         "request": "{{text}}",
-        "response": "{{embedding}}"
+        "response": "{{embedding}}",
+        "documentTemplate": "{{doc.name}}"
     });
 
     (mock_server, embedder_settings)
 }
 
-pub async fn post<T: IntoUrl>(url: T) -> reqwest::Result<reqwest::Response> {
-    reqwest::Client::builder().build()?.post(url).send().await
+pub async fn post<T: IntoUrl>(url: T, text: &str) -> reqwest::Result<reqwest::Response> {
+    reqwest::Client::builder().build()?.post(url).json(&json!(text)).send().await
 }
 
 #[actix_rt::test]
 async fn dummy_testing_the_mock() {
     let (mock, _setting) = create_mock().await;
-    let body = post(&mock.uri()).await.unwrap().text().await.unwrap();
-    snapshot!(body, @r###"{"data":[0,0,0]}"###);
-    let body = post(&mock.uri()).await.unwrap().text().await.unwrap();
-    snapshot!(body, @r###"{"data":[1,1,1]}"###);
-    let body = post(&mock.uri()).await.unwrap().text().await.unwrap();
-    snapshot!(body, @r###"{"data":[2,2,2]}"###);
-    let body = post(&mock.uri()).await.unwrap().text().await.unwrap();
-    snapshot!(body, @r###"{"data":[3,3,3]}"###);
-    let body = post(&mock.uri()).await.unwrap().text().await.unwrap();
-    snapshot!(body, @r###"{"data":[4,4,4]}"###);
+    let body = post(&mock.uri(), "kefir").await.unwrap().text().await.unwrap();
+    snapshot!(body, @r###"{"data":[0.0,0.0,0.0]}"###);
+    let body = post(&mock.uri(), "intel").await.unwrap().text().await.unwrap();
+    snapshot!(body, @r###"{"data":[1.0,1.0,1.0]}"###);
+    let body = post(&mock.uri(), "kefir").await.unwrap().text().await.unwrap();
+    snapshot!(body, @r###"{"data":[0.0,0.0,0.0]}"###);
+    let body = post(&mock.uri(), "kefir").await.unwrap().text().await.unwrap();
+    snapshot!(body, @r###"{"data":[0.0,0.0,0.0]}"###);
+    let body = post(&mock.uri(), "intel").await.unwrap().text().await.unwrap();
+    snapshot!(body, @r###"{"data":[1.0,1.0,1.0]}"###);
 }
 
 #[actix_rt::test]
@@ -938,7 +985,7 @@ async fn bad_settings() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting a single \"{{embedding}}\", expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting a single \"{{embedding}}\", expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -954,7 +1001,7 @@ async fn bad_settings() {
     let (response, code) = index
         .update_settings(json!({
           "embedders": {
-              "rest": json!({ "source": "rest", "url": mock.uri(), "request": "{{text}}", "response": { "data": "{{embedding}}" }, "dimensions": 2 }),
+              "rest": json!({ "source": "rest", "url": mock.uri(), "request": "{{text}}", "response": { "data": "{{embedding}}" }, "dimensions": 2, "documentTemplate": "{{doc.name}}" }),
           },
         }))
         .await;
@@ -978,7 +1025,7 @@ async fn bad_settings() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `rest`: runtime error: was expecting embeddings of dimension `2`, got embeddings of dimensions `3`",
+        "message": "Index `doggo`: While embedding documents for embedder `rest`: runtime error: was expecting embeddings of dimension `2`, got embeddings of dimensions `3`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1131,7 +1178,7 @@ async fn server_returns_bad_request() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with 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 \\\"test\\\", expected struct MultipleRequest at line 1 column 6\"}`",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with 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 \\\"test\\\", expected struct MultipleRequest at line 1 column 6\"}`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1200,7 +1247,7 @@ 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 \\\"name: kefir\\\\n\\\", expected struct MultipleRequest at line 1 column 15\"}`",
+        "message": "Index `doggo`: 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"
@@ -1259,7 +1306,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting the array of \"{{embedding}}\"s, configuration expects `response` to be an array with at least 1 item(s) but server sent an object with 1 field(s)",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting the array of \"{{embedding}}\"s, configuration expects `response` to be an array with at least 1 item(s) but server sent an object with 1 field(s)",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1315,7 +1362,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting item #0 from the array of \"{{embedding}}\"s, expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting item #0 from the array of \"{{embedding}}\"s, expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1367,7 +1414,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output`, while extracting a single \"{{embedding}}\", expected `output` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected f32",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output`, while extracting a single \"{{embedding}}\", expected `output` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected f32",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1431,7 +1478,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.embedding`, while extracting item #0 from the array of \"{{embedding}}\"s, configuration expects `embedding` to be an object with key `data` but server sent an array of size 3",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.embedding`, while extracting item #0 from the array of \"{{embedding}}\"s, configuration expects `embedding` to be an object with key `data` but server sent an array of size 3",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1495,7 +1542,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output[0]`, while extracting a single \"{{embedding}}\", configuration expects key \"embeddings\", which is missing in response\n  - Hint: item #0 inside `output` has key `embedding`, did you mean `response.output[0].embedding` in embedder configuration?",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output[0]`, while extracting a single \"{{embedding}}\", configuration expects key \"embeddings\", which is missing in response\n  - Hint: item #0 inside `output` has key `embedding`, did you mean `response.output[0].embedding` in embedder configuration?",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1861,7 +1908,7 @@ async fn server_custom_header() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"missing header 'my-nonstandard-auth'\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"missing header 'my-nonstandard-auth'\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1904,7 +1951,7 @@ async fn server_custom_header() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"thou shall not pass, Balrog\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"thou shall not pass, Balrog\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1937,6 +1984,7 @@ async fn server_custom_header() {
         "embedders": {
           "rest": {
             "source": "rest",
+            "documentTemplate": "{{doc.name}}",
             "url": "[url]",
             "request": "{{text}}",
             "response": "{{embedding}}",
@@ -1957,7 +2005,7 @@ async fn server_custom_header() {
 
 #[actix_rt::test]
 async fn searchable_reindex() {
-    let (_mock, setting) = create_mock_map().await;
+    let (_mock, setting) = create_mock_default_template().await;
     let server = get_server_vector().await;
     let index = server.index("doggo");
 
@@ -2051,7 +2099,7 @@ async fn searchable_reindex() {
         ]
       },
       "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\"}`",
+        "message": "Index `doggo`: 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"