Change implementation of MergedDocuments::iter_top_level_fields

5131: Ignore documents whose selected fields didn't change r=dureuill a=dureuill

Attempts to improve the new indexer performance by ignoring documents whose selected fields didn't change:

- Add `Update::has_changed_for_fields` function
- Ignore documents whose searchable attributes didn't change for word docids and word pair proximity extraction
- Ignore documents whose faceted attributes didn't change for facet extraction

Co-authored-by: Louis Dureuil <louis@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 +701,10 @@ name = "bumpalo"
 version = "3.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c"
+dependencies = [
+ "allocator-api2",
+ "serde",
+]
 
 [[package]]
 name = "byte-unit"
@@ -741,7 +762,7 @@ checksum = "4da9a32f3fed317401fa3c862968128267c3106685286e15d5aaa3d7389c2f60"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -953,9 +974,9 @@ 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 +1073,7 @@ dependencies = [
  "heck 0.5.0",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1230,19 +1251,6 @@ 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 +1386,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "strsim 0.11.1",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1400,7 +1408,7 @@ checksum = "733cabb43482b1a1b53eee8583c2b9e8684d592215ea83efd305dd31bc2f0178"
 dependencies = [
  "darling_core 0.20.9",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1454,7 +1462,7 @@ checksum = "67e77553c4162a157adbf834ebae5b415acbecbeafc7a74b0e886657506a7611"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1496,7 +1504,7 @@ dependencies = [
  "darling 0.20.9",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1516,7 +1524,7 @@ 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 +1566,7 @@ dependencies = [
  "convert_case 0.6.0",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1622,7 +1630,7 @@ checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1642,7 +1650,7 @@ dependencies = [
 
 [[package]]
 name = "dump"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "anyhow",
  "big_s",
@@ -1780,7 +1788,7 @@ dependencies = [
  "heck 0.4.1",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1800,7 +1808,7 @@ checksum = "a1ab991c1362ac86c61ab6f556cff143daa22e5a15e4e189df818b2fd19fe65b"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -1848,13 +1856,13 @@ 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 +1884,7 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "insta",
  "nom",
@@ -1896,18 +1904,33 @@ 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 +2008,7 @@ checksum = "87750cf4b7a4c0625b1529e4c543c2182106e4dedc60a2a6455e00d212c489ac"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -2020,10 +2043,12 @@ dependencies = [
 
 [[package]]
 name = "fuzzers"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "arbitrary",
+ "bumpalo",
  "clap",
+ "either",
  "fastrand",
  "milli",
  "serde",
@@ -2240,12 +2265,13 @@ 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 +2362,18 @@ 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 +2610,14 @@ 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",
+ "crossbeam-channel",
  "csv",
  "derive_builder 0.20.0",
  "dump",
@@ -2590,7 +2629,9 @@ dependencies = [
  "meili-snap",
  "meilisearch-auth",
  "meilisearch-types",
+ "memmap2",
  "page_size",
+ "raw-collections",
  "rayon",
  "roaring",
  "serde",
@@ -2766,7 +2807,7 @@ dependencies = [
 
 [[package]]
 name = "json-depth-checker"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "criterion",
  "serde_json",
@@ -2835,9 +2876,9 @@ 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 +3262,9 @@ 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 +3305,7 @@ checksum = "915f6d0a2963a27cd5205c1902f32ddfe3bc035816afd268cf88c0fc0f8d287e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -3368,7 +3409,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -3385,7 +3426,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
 
 [[package]]
 name = "meili-snap"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "insta",
  "md5",
@@ -3394,7 +3435,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "actix-cors",
  "actix-http",
@@ -3484,7 +3525,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-auth"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "base64 0.22.1",
  "enum-iterator",
@@ -3503,10 +3544,11 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-types"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "actix-web",
  "anyhow",
+ "bumpalo",
  "convert_case 0.6.0",
  "csv",
  "deserr",
@@ -3519,6 +3561,7 @@ dependencies = [
  "meili-snap",
  "memmap2",
  "milli",
+ "raw-collections",
  "roaring",
  "serde",
  "serde-cs",
@@ -3533,7 +3576,7 @@ 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)",
@@ -3555,9 +3598,9 @@ 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 +3608,16 @@ 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",
  "bytemuck",
  "byteorder",
  "candle-core",
@@ -3583,12 +3629,15 @@ dependencies = [
  "csv",
  "deserr",
  "either",
+ "enum-iterator",
  "filter-parser",
  "flatten-serde-json",
+ "flume",
  "fst",
  "fxhash",
  "geoutils",
  "grenad",
+ "hashbrown 0.15.1",
  "heed",
  "hf-hub",
  "indexmap",
@@ -3607,11 +3656,13 @@ dependencies = [
  "once_cell",
  "ordered-float",
  "rand",
+ "raw-collections",
  "rayon",
  "rayon-par-bridge",
  "rhai",
  "roaring",
  "rstar",
+ "rustc-hash 2.0.0",
  "serde",
  "serde_json",
  "slice-group-by",
@@ -3620,10 +3671,12 @@ dependencies = [
  "smartstring",
  "tempfile",
  "thiserror",
+ "thread_local",
  "tiktoken-rs",
  "time",
  "tokenizers",
  "tracing",
+ "uell",
  "ureq",
  "url",
  "uuid",
@@ -3699,7 +3752,7 @@ checksum = "371717c0a5543d6a800cac822eac735aa7d2d2fbb41002e9856a4089532dbdce"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -3835,7 +3888,7 @@ dependencies = [
  "proc-macro-crate",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -3864,9 +3917,9 @@ 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 +4064,7 @@ checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
 
 [[package]]
 name = "permissive-json-pointer"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "big_s",
  "serde_json",
@@ -4047,7 +4100,7 @@ dependencies = [
  "pest_meta",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -4101,7 +4154,7 @@ dependencies = [
  "phf_shared",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -4130,7 +4183,7 @@ checksum = "266c042b60c9c76b8d53061e52b2e0d1116abc57cefc8c5cd671619a56ac3690"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -4247,9 +4300,9 @@ 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",
 ]
@@ -4434,6 +4487,19 @@ dependencies = [
  "rand",
 ]
 
+[[package]]
+name = "raw-collections"
+version = "0.1.0"
+source = "git+https://github.com/meilisearch/raw-collections.git#15e5d7bdebc0c149b2a28b2454f307c717d07f8a"
+dependencies = [
+ "allocator-api2",
+ "bitpacking",
+ "bumpalo",
+ "hashbrown 0.15.1",
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "raw-cpuid"
 version = "10.7.0"
@@ -4631,7 +4697,7 @@ source = "git+https://github.com/rhaiscript/rhai?rev=ef3df63121d27aacd838f366f2b
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -4680,9 +4746,9 @@ 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",
@@ -4746,9 +4812,9 @@ 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 +4939,9 @@ 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 +4957,24 @@ 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 = "1.0.132"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4e0d21c9a8cae1235ad58a00c11cb40d4b1e5c784f1ef2c537876ed6ffd8b7c5"
+checksum = "d726bfaff4b320266d395898905d0eba0345aae23b54aee3a737e260fd46db03"
 dependencies = [
  "indexmap",
  "itoa",
+ "memchr",
  "ryu",
  "serde",
 ]
@@ -5123,6 +5190,9 @@ 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 +5260,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "rustversion",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -5212,9 +5282,9 @@ 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 +5300,7 @@ dependencies = [
  "proc-macro-error",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -5256,7 +5326,7 @@ checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -5316,12 +5386,13 @@ 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 +5432,14 @@ 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 +5584,7 @@ checksum = "5f5ae998a069d4b5aba8ee9dad856af7d520c3699e6159b185c2acd48155d39a"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -5645,7 +5716,7 @@ checksum = "34704c8d6ebcbc939824180af020566b01a7c01f80641264eba0999f6c2b6be7"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -5740,6 +5811,15 @@ 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 +6026,9 @@ 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 +6071,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
  "wasm-bindgen-shared",
 ]
 
@@ -6025,7 +6105,7 @@ checksum = "e94f17b526d0a461a191c78ea52bbce64071ed5c04c9ffe424dcb38f74171bb7"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
@@ -6400,7 +6480,7 @@ dependencies = [
 
 [[package]]
 name = "xtask"
-version = "1.11.0"
+version = "1.12.0"
 dependencies = [
  "anyhow",
  "build-info",
@@ -6458,7 +6538,7 @@ checksum = "9e6936f0cce458098a201c245a11bef556c6a0181129c7034d10d76d1ec3a2b8"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
  "synstructure",
 ]
 
@@ -6479,7 +6559,7 @@ checksum = "9ce1b18ccd8e73a9321186f97e46f9f04b778851177567b1975109d26a08d2a6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
 ]
 
 [[package]]
@@ -6499,7 +6579,7 @@ checksum = "e6a647510471d372f2e6c2e6b7219e44d8c574d24fdc11c610a61455782f18c3"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.60",
+ "syn 2.0.87",
  "synstructure",
 ]
 
@@ -6520,7 +6600,7 @@ 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 +1,18 @@
 #![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::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 +66,7 @@ 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 +93,44 @@ 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| (),
+        )
+        .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,
+        &|_| (),
+    )
+    .unwrap();
+
     wtxn.commit().unwrap();
+    drop(rtxn);
 
     index
 }
@@ -140,49 +167,96 @@ 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 +265,9 @@ 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 +305,13 @@ 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/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 +4,17 @@ 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::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 +64,6 @@ 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 +80,72 @@ 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| (),
+                                )
+                                .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,
+                                &|_| (),
+                            )
+                            .unwrap();
 
                             // after executing a batch we check if the database is corrupted
                             let res = index.search(&wtxn).execute().unwrap();

crates/index-scheduler/Cargo.toml

@@ -22,13 +22,15 @@ flate2 = "1.0.30"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 page_size = "0.6.0"
+raw-collections = { git = "https://github.com/meilisearch/raw-collections.git", version = "0.1.0" }
 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"
 tempfile = "3.10.1"
 thiserror = "1.0.61"
+memmap2 = "0.9.4"
 time = { version = "0.3.36", features = [
     "serde-well-known",
     "formatting",
@@ -38,11 +40,12 @@ time = { version = "0.3.36", features = [
 tracing = "0.1.40"
 ureq = "2.10.0"
 uuid = { version = "1.10.0", features = ["serde", "v4"] }
+bumpalo = "3.16.0"
 
 [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/batch.rs

@@ -22,22 +22,27 @@ use std::ffi::OsStr;
 use std::fmt;
 use std::fs::{self, File};
 use std::io::BufWriter;
+use std::sync::atomic::{self, AtomicU64};
+use std::time::Duration;
 
+use bumpalo::collections::CollectIn;
+use bumpalo::Bump;
 use dump::IndexMetadata;
 use meilisearch_types::batches::BatchId;
 use meilisearch_types::error::Code;
 use meilisearch_types::heed::{RoTxn, RwTxn};
-use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader};
+use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader, PrimaryKey};
 use meilisearch_types::milli::heed::CompactionOption;
-use meilisearch_types::milli::update::{
-    IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings as MilliSettings,
-};
+use meilisearch_types::milli::update::new::indexer::{self, UpdateByFunction};
+use meilisearch_types::milli::update::{IndexDocumentsMethod, Settings as MilliSettings};
 use meilisearch_types::milli::vector::parsed_vectors::{
     ExplicitVectors, VectorOrArrayOfVectors, RESERVED_VECTORS_FIELD_NAME,
 };
-use meilisearch_types::milli::{self, Filter, Object};
+use meilisearch_types::milli::{self, Filter, ThreadPoolNoAbortBuilder};
 use meilisearch_types::settings::{apply_settings_to_builder, Settings, Unchecked};
-use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status, Task};
+use meilisearch_types::tasks::{
+    Details, IndexSwap, Kind, KindWithContent, Status, Task, TaskProgress,
+};
 use meilisearch_types::{compression, Index, VERSION_FILE_NAME};
 use roaring::RoaringBitmap;
 use time::macros::format_description;
@@ -46,7 +51,7 @@ use uuid::Uuid;
 
 use crate::autobatcher::{self, BatchKind};
 use crate::utils::{self, swap_index_uid_in_task, ProcessingBatch};
-use crate::{Error, IndexScheduler, MustStopProcessing, Result, TaskId};
+use crate::{Error, IndexScheduler, Result, TaskId};
 
 /// Represents a combination of tasks that can all be processed at the same time.
 ///
@@ -99,7 +104,6 @@ pub(crate) enum IndexOperation {
         index_uid: String,
         primary_key: Option<String>,
         method: IndexDocumentsMethod,
-        documents_counts: Vec<u64>,
         operations: Vec<DocumentOperation>,
         tasks: Vec<Task>,
     },
@@ -125,19 +129,6 @@ pub(crate) enum IndexOperation {
         index_uid: String,
         cleared_tasks: Vec<Task>,
 
-        // The boolean indicates if it's a settings deletion or creation.
-        settings: Vec<(bool, Settings<Unchecked>)>,
-        settings_tasks: Vec<Task>,
-    },
-    SettingsAndDocumentOperation {
-        index_uid: String,
-
-        primary_key: Option<String>,
-        method: IndexDocumentsMethod,
-        documents_counts: Vec<u64>,
-        operations: Vec<DocumentOperation>,
-        document_import_tasks: Vec<Task>,
-
         // The boolean indicates if it's a settings deletion or creation.
         settings: Vec<(bool, Settings<Unchecked>)>,
         settings_tasks: Vec<Task>,
@@ -169,12 +160,7 @@ impl Batch {
                 IndexOperation::DocumentEdition { task, .. } => {
                     RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
                 }
-                IndexOperation::SettingsAndDocumentOperation {
-                    document_import_tasks: tasks,
-                    settings_tasks: other,
-                    ..
-                }
-                | IndexOperation::DocumentClearAndSetting {
+                IndexOperation::DocumentClearAndSetting {
                     cleared_tasks: tasks,
                     settings_tasks: other,
                     ..
@@ -234,8 +220,7 @@ impl IndexOperation {
             | IndexOperation::DocumentDeletion { index_uid, .. }
             | IndexOperation::DocumentClear { index_uid, .. }
             | IndexOperation::Settings { index_uid, .. }
-            | IndexOperation::DocumentClearAndSetting { index_uid, .. }
-            | IndexOperation::SettingsAndDocumentOperation { index_uid, .. } => index_uid,
+            | IndexOperation::DocumentClearAndSetting { index_uid, .. } => index_uid,
         }
     }
 }
@@ -257,9 +242,6 @@ impl fmt::Display for IndexOperation {
             IndexOperation::DocumentClearAndSetting { .. } => {
                 f.write_str("IndexOperation::DocumentClearAndSetting")
             }
-            IndexOperation::SettingsAndDocumentOperation { .. } => {
-                f.write_str("IndexOperation::SettingsAndDocumentOperation")
-            }
         }
     }
 }
@@ -325,21 +307,14 @@ impl IndexScheduler {
                     })
                     .flatten();
 
-                let mut documents_counts = Vec::new();
                 let mut operations = Vec::new();
 
                 for task in tasks.iter() {
                     match task.kind {
-                        KindWithContent::DocumentAdditionOrUpdate {
-                            content_file,
-                            documents_count,
-                            ..
-                        } => {
-                            documents_counts.push(documents_count);
+                        KindWithContent::DocumentAdditionOrUpdate { content_file, .. } => {
                             operations.push(DocumentOperation::Add(content_file));
                         }
                         KindWithContent::DocumentDeletion { ref documents_ids, .. } => {
-                            documents_counts.push(documents_ids.len() as u64);
                             operations.push(DocumentOperation::Delete(documents_ids.clone()));
                         }
                         _ => unreachable!(),
@@ -351,7 +326,6 @@ impl IndexScheduler {
                         index_uid,
                         primary_key,
                         method,
-                        documents_counts,
                         operations,
                         tasks,
                     },
@@ -436,67 +410,6 @@ impl IndexScheduler {
                     must_create_index,
                 }))
             }
-            BatchKind::SettingsAndDocumentOperation {
-                settings_ids,
-                method,
-                allow_index_creation,
-                primary_key,
-                operation_ids,
-            } => {
-                let settings = self.create_next_batch_index(
-                    rtxn,
-                    index_uid.clone(),
-                    BatchKind::Settings { settings_ids, allow_index_creation },
-                    current_batch,
-                    must_create_index,
-                )?;
-
-                let document_import = self.create_next_batch_index(
-                    rtxn,
-                    index_uid.clone(),
-                    BatchKind::DocumentOperation {
-                        method,
-                        allow_index_creation,
-                        primary_key,
-                        operation_ids,
-                    },
-                    current_batch,
-                    must_create_index,
-                )?;
-
-                match (document_import, settings) {
-                    (
-                        Some(Batch::IndexOperation {
-                            op:
-                                IndexOperation::DocumentOperation {
-                                    primary_key,
-                                    documents_counts,
-                                    operations,
-                                    tasks: document_import_tasks,
-                                    ..
-                                },
-                            ..
-                        }),
-                        Some(Batch::IndexOperation {
-                            op: IndexOperation::Settings { settings, tasks: settings_tasks, .. },
-                            ..
-                        }),
-                    ) => Ok(Some(Batch::IndexOperation {
-                        op: IndexOperation::SettingsAndDocumentOperation {
-                            index_uid,
-                            primary_key,
-                            method,
-                            documents_counts,
-                            operations,
-                            document_import_tasks,
-                            settings,
-                            settings_tasks,
-                        },
-                        must_create_index,
-                    })),
-                    _ => unreachable!(),
-                }
-            }
             BatchKind::IndexCreation { id } => {
                 let mut task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
                 current_batch.processing(Some(&mut task));
@@ -584,7 +497,6 @@ impl IndexScheduler {
         // 5. We make a batch from the unprioritised tasks. Start by taking the next enqueued task.
         let task_id = if let Some(task_id) = enqueued.min() { task_id } else { return Ok(None) };
         let mut task = self.get_task(rtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
-        current_batch.processing(Some(&mut task));
 
         // If the task is not associated with any index, verify that it is an index swap and
         // create the batch directly. Otherwise, get the index name associated with the task
@@ -594,6 +506,7 @@ impl IndexScheduler {
             index_name
         } else {
             assert!(matches!(&task.kind, KindWithContent::IndexSwap { swaps } if swaps.is_empty()));
+            current_batch.processing(Some(&mut task));
             return Ok(Some((Batch::IndexSwap { task }, current_batch)));
         };
 
@@ -886,10 +799,8 @@ impl IndexScheduler {
                             while let Some(doc) =
                                 cursor.next_document().map_err(milli::Error::from)?
                             {
-                                dump_content_file.push_document(&obkv_to_object(
-                                    &doc,
-                                    &documents_batch_index,
-                                )?)?;
+                                dump_content_file
+                                    .push_document(&obkv_to_object(doc, &documents_batch_index)?)?;
                             }
                             dump_content_file.flush()?;
                         }
@@ -1021,7 +932,13 @@ impl IndexScheduler {
 
                 let mut index_wtxn = index.write_txn()?;
                 let tasks = self.apply_index_operation(&mut index_wtxn, &index, op)?;
-                index_wtxn.commit()?;
+
+                {
+                    let span = tracing::trace_span!(target: "indexing::scheduler", "commit");
+                    let _entered = span.enter();
+
+                    index_wtxn.commit()?;
+                }
 
                 // if the update processed successfully, we're going to store the new
                 // stats of the index. Since the tasks have already been processed and
@@ -1232,6 +1149,44 @@ impl IndexScheduler {
         index: &'i Index,
         operation: IndexOperation,
     ) -> Result<Vec<Task>> {
+        let indexer_alloc = Bump::new();
+
+        let started_processing_at = std::time::Instant::now();
+        let secs_since_started_processing_at = AtomicU64::new(0);
+        const PRINT_SECS_DELTA: u64 = 5;
+
+        let processing_tasks = self.processing_tasks.clone();
+        let must_stop_processing = self.must_stop_processing.clone();
+        let send_progress = |progress| {
+            let now = std::time::Instant::now();
+            let elapsed = secs_since_started_processing_at.load(atomic::Ordering::Relaxed);
+            let previous = started_processing_at + Duration::from_secs(elapsed);
+            let elapsed = now - previous;
+
+            if elapsed.as_secs() < PRINT_SECS_DELTA {
+                return;
+            }
+
+            secs_since_started_processing_at
+                .store((now - started_processing_at).as_secs(), atomic::Ordering::Relaxed);
+
+            let TaskProgress {
+                current_step,
+                finished_steps,
+                total_steps,
+                finished_substeps,
+                total_substeps,
+            } = processing_tasks.write().unwrap().update_progress(progress);
+
+            tracing::info!(
+                current_step,
+                finished_steps,
+                total_steps,
+                finished_substeps,
+                total_substeps
+            );
+        };
+
         match operation {
             IndexOperation::DocumentClear { mut tasks, .. } => {
                 let count = milli::update::ClearDocuments::new(index_wtxn, index).execute()?;
@@ -1257,159 +1212,148 @@ impl IndexScheduler {
                 index_uid: _,
                 primary_key,
                 method,
-                documents_counts: _,
                 operations,
                 mut tasks,
             } => {
-                let started_processing_at = std::time::Instant::now();
-                let mut primary_key_has_been_set = false;
-                let must_stop_processing = self.must_stop_processing.clone();
-                let indexer_config = self.index_mapper.indexer_config();
-
-                if let Some(primary_key) = primary_key {
-                    match index.primary_key(index_wtxn)? {
-                        // if a primary key was set AND had already been defined in the index
-                        // but to a different value, we can make the whole batch fail.
-                        Some(pk) => {
-                            if primary_key != pk {
-                                return Err(milli::Error::from(
-                                    milli::UserError::PrimaryKeyCannotBeChanged(pk.to_string()),
-                                )
-                                .into());
-                            }
-                        }
-                        // if the primary key was set and there was no primary key set for this index
-                        // we set it to the received value before starting the indexing process.
-                        None => {
-                            let mut builder =
-                                milli::update::Settings::new(index_wtxn, index, indexer_config);
-                            builder.set_primary_key(primary_key);
-                            builder.execute(
-                                |indexing_step| tracing::debug!(update = ?indexing_step),
-                                || must_stop_processing.clone().get(),
-                            )?;
-                            primary_key_has_been_set = true;
+                // TODO: at some point, for better efficiency we might want to reuse the bumpalo for successive batches.
+                // this is made difficult by the fact we're doing private clones of the index scheduler and sending it
+                // to a fresh thread.
+                let mut content_files = Vec::new();
+                for operation in &operations {
+                    if let DocumentOperation::Add(content_uuid) = operation {
+                        let content_file = self.file_store.get_update(*content_uuid)?;
+                        let mmap = unsafe { memmap2::Mmap::map(&content_file)? };
+                        if !mmap.is_empty() {
+                            content_files.push(mmap);
                         }
                     }
                 }
 
-                let config = IndexDocumentsConfig { update_method: method, ..Default::default() };
+                let rtxn = index.read_txn()?;
+                let db_fields_ids_map = index.fields_ids_map(&rtxn)?;
+                let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let embedder_configs = index.embedding_configs(index_wtxn)?;
-                // TODO: consider Arc'ing the map too (we only need read access + we'll be cloning it multiple times, so really makes sense)
-                let embedders = self.embedders(embedder_configs)?;
-
-                let mut builder = milli::update::IndexDocuments::new(
-                    index_wtxn,
-                    index,
-                    indexer_config,
-                    config,
-                    |indexing_step| tracing::trace!(?indexing_step, "Update"),
-                    || must_stop_processing.get(),
-                )?;
-
-                for (operation, task) in operations.into_iter().zip(tasks.iter_mut()) {
+                let mut content_files_iter = content_files.iter();
+                let mut indexer = indexer::DocumentOperation::new(method);
+                let embedders = index.embedding_configs(index_wtxn)?;
+                let embedders = self.embedders(embedders)?;
+                for operation in operations {
                     match operation {
-                        DocumentOperation::Add(content_uuid) => {
-                            let content_file = self.file_store.get_update(content_uuid)?;
-                            let reader = DocumentsBatchReader::from_reader(content_file)
-                                .map_err(milli::Error::from)?;
-                            let (new_builder, user_result) = builder.add_documents(reader)?;
-                            builder = new_builder;
-
-                            builder = builder.with_embedders(embedders.clone());
-
-                            let received_documents =
-                                if let Some(Details::DocumentAdditionOrUpdate {
-                                    received_documents,
-                                    ..
-                                }) = task.details
-                                {
-                                    received_documents
-                                } else {
-                                    // In the case of a `documentAdditionOrUpdate` the details MUST be set
-                                    unreachable!();
-                                };
-
-                            match user_result {
-                                Ok(count) => {
-                                    task.status = Status::Succeeded;
-                                    task.details = Some(Details::DocumentAdditionOrUpdate {
-                                        received_documents,
-                                        indexed_documents: Some(count),
-                                    })
-                                }
-                                Err(e) => {
-                                    task.status = Status::Failed;
-                                    task.details = Some(Details::DocumentAdditionOrUpdate {
-                                        received_documents,
-                                        indexed_documents: Some(0),
-                                    });
-                                    task.error = Some(milli::Error::from(e).into());
-                                }
-                            }
+                        DocumentOperation::Add(_content_uuid) => {
+                            let mmap = content_files_iter.next().unwrap();
+                            indexer.add_documents(mmap)?;
                         }
                         DocumentOperation::Delete(document_ids) => {
-                            let (new_builder, user_result) =
-                                builder.remove_documents(document_ids)?;
-                            builder = new_builder;
-                            // Uses Invariant: remove documents actually always returns Ok for the inner result
-                            let count = user_result.unwrap();
-                            let provided_ids =
-                                if let Some(Details::DocumentDeletion { provided_ids, .. }) =
-                                    task.details
-                                {
-                                    provided_ids
-                                } else {
-                                    // In the case of a `documentAdditionOrUpdate` the details MUST be set
-                                    unreachable!();
-                                };
-
-                            task.status = Status::Succeeded;
-                            task.details = Some(Details::DocumentDeletion {
-                                provided_ids,
-                                deleted_documents: Some(count),
-                            });
+                            let document_ids: bumpalo::collections::vec::Vec<_> = document_ids
+                                .iter()
+                                .map(|s| &*indexer_alloc.alloc_str(s))
+                                .collect_in(&indexer_alloc);
+                            indexer.delete_documents(document_ids.into_bump_slice());
                         }
                     }
                 }
 
-                if !tasks.iter().all(|res| res.error.is_some()) {
-                    let addition = builder.execute()?;
-                    tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
-                } else if primary_key_has_been_set {
-                    // Everything failed but we've set a primary key.
-                    // We need to remove it.
-                    let mut builder =
-                        milli::update::Settings::new(index_wtxn, index, indexer_config);
-                    builder.reset_primary_key();
-                    builder.execute(
-                        |indexing_step| tracing::trace!(update = ?indexing_step),
-                        || must_stop_processing.clone().get(),
+                let local_pool;
+                let indexer_config = self.index_mapper.indexer_config();
+                let pool = match &indexer_config.thread_pool {
+                    Some(pool) => pool,
+                    None => {
+                        local_pool = ThreadPoolNoAbortBuilder::new()
+                            .thread_name(|i| format!("indexing-thread-{i}"))
+                            .build()
+                            .unwrap();
+                        &local_pool
+                    }
+                };
+
+                let (document_changes, operation_stats, primary_key) = indexer.into_changes(
+                    &indexer_alloc,
+                    index,
+                    &rtxn,
+                    primary_key.as_deref(),
+                    &mut new_fields_ids_map,
+                    &|| must_stop_processing.get(),
+                    &send_progress,
+                )?;
+
+                let mut addition = 0;
+                for (stats, task) in operation_stats.into_iter().zip(&mut tasks) {
+                    addition += stats.document_count;
+                    match stats.error {
+                        Some(error) => {
+                            task.status = Status::Failed;
+                            task.error = Some(milli::Error::UserError(error).into());
+                        }
+                        None => task.status = Status::Succeeded,
+                    }
+
+                    task.details = match task.details {
+                        Some(Details::DocumentAdditionOrUpdate { received_documents, .. }) => {
+                            Some(Details::DocumentAdditionOrUpdate {
+                                received_documents,
+                                indexed_documents: Some(stats.document_count),
+                            })
+                        }
+                        Some(Details::DocumentDeletion { provided_ids, .. }) => {
+                            Some(Details::DocumentDeletion {
+                                provided_ids,
+                                deleted_documents: Some(stats.document_count),
+                            })
+                        }
+                        _ => {
+                            // In the case of a `documentAdditionOrUpdate` or `DocumentDeletion`
+                            // the details MUST be set to either addition or deletion
+                            unreachable!();
+                        }
+                    }
+                }
+
+                if tasks.iter().any(|res| res.error.is_none()) {
+                    indexer::index(
+                        index_wtxn,
+                        index,
+                        pool,
+                        indexer_config.grenad_parameters(),
+                        &db_fields_ids_map,
+                        new_fields_ids_map,
+                        primary_key,
+                        &document_changes,
+                        embedders,
+                        &|| must_stop_processing.get(),
+                        &send_progress,
                     )?;
+
+                    tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 }
 
                 Ok(tasks)
             }
             IndexOperation::DocumentEdition { mut task, .. } => {
-                let (filter, context, function) =
-                    if let KindWithContent::DocumentEdition {
-                        filter_expr, context, function, ..
-                    } = &task.kind
-                    {
-                        (filter_expr, context, function)
-                    } else {
-                        unreachable!()
-                    };
-                let result_count = edit_documents_by_function(
-                    index_wtxn,
-                    filter,
-                    context.clone(),
+                let (filter, code) = if let KindWithContent::DocumentEdition {
+                    filter_expr,
+                    context: _,
                     function,
-                    self.index_mapper.indexer_config(),
-                    self.must_stop_processing.clone(),
-                    index,
-                );
+                    ..
+                } = &task.kind
+                {
+                    (filter_expr, function)
+                } else {
+                    unreachable!()
+                };
+
+                let candidates = match filter.as_ref().map(Filter::from_json) {
+                    Some(Ok(Some(filter))) => {
+                        filter.evaluate(index_wtxn, index).map_err(|err| match err {
+                            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
+                                Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
+                            }
+                            e => e.into(),
+                        })?
+                    }
+                    None | Some(Ok(None)) => index.documents_ids(index_wtxn)?,
+                    Some(Err(e)) => return Err(e.into()),
+                };
+
                 let (original_filter, context, function) = if let Some(Details::DocumentEdition {
                     original_filter,
                     context,
@@ -1423,6 +1367,68 @@ impl IndexScheduler {
                     unreachable!();
                 };
 
+                if candidates.is_empty() {
+                    task.status = Status::Succeeded;
+                    task.details = Some(Details::DocumentEdition {
+                        original_filter,
+                        context,
+                        function,
+                        deleted_documents: Some(0),
+                        edited_documents: Some(0),
+                    });
+
+                    return Ok(vec![task]);
+                }
+
+                let rtxn = index.read_txn()?;
+                let db_fields_ids_map = index.fields_ids_map(&rtxn)?;
+                let mut new_fields_ids_map = db_fields_ids_map.clone();
+                // candidates not empty => index not empty => a primary key is set
+                let primary_key = index.primary_key(&rtxn)?.unwrap();
+
+                let primary_key = PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
+                    .map_err(milli::Error::from)?;
+
+                let result_count = Ok((candidates.len(), candidates.len())) as Result<_>;
+
+                if task.error.is_none() {
+                    let local_pool;
+                    let indexer_config = self.index_mapper.indexer_config();
+                    let pool = match &indexer_config.thread_pool {
+                        Some(pool) => pool,
+                        None => {
+                            local_pool = ThreadPoolNoAbortBuilder::new()
+                                .thread_name(|i| format!("indexing-thread-{i}"))
+                                .build()
+                                .unwrap();
+                            &local_pool
+                        }
+                    };
+
+                    let indexer = UpdateByFunction::new(candidates, context.clone(), code.clone());
+                    let document_changes =
+                        pool.install(|| indexer.into_changes(&primary_key)).unwrap()?;
+
+                    let embedders = index.embedding_configs(index_wtxn)?;
+                    let embedders = self.embedders(embedders)?;
+
+                    indexer::index(
+                        index_wtxn,
+                        index,
+                        pool,
+                        indexer_config.grenad_parameters(),
+                        &db_fields_ids_map,
+                        new_fields_ids_map,
+                        None, // cannot change primary key in DocumentEdition
+                        &document_changes,
+                        embedders,
+                        &|| must_stop_processing.get(),
+                        &send_progress,
+                    )?;
+
+                    // tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
+                }
+
                 match result_count {
                     Ok((deleted_documents, edited_documents)) => {
                         task.status = Status::Succeeded;
@@ -1523,26 +1529,56 @@ impl IndexScheduler {
                     }
                 }
 
-                let config = IndexDocumentsConfig {
-                    update_method: IndexDocumentsMethod::ReplaceDocuments,
-                    ..Default::default()
-                };
+                if to_delete.is_empty() {
+                    return Ok(tasks);
+                }
 
-                let must_stop_processing = self.must_stop_processing.clone();
-                let mut builder = milli::update::IndexDocuments::new(
-                    index_wtxn,
-                    index,
-                    self.index_mapper.indexer_config(),
-                    config,
-                    |indexing_step| tracing::debug!(update = ?indexing_step),
-                    || must_stop_processing.get(),
-                )?;
+                let rtxn = index.read_txn()?;
+                let db_fields_ids_map = index.fields_ids_map(&rtxn)?;
+                let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let (new_builder, _count) =
-                    builder.remove_documents_from_db_no_batch(&to_delete)?;
-                builder = new_builder;
+                // to_delete not empty => index not empty => primary key set
+                let primary_key = index.primary_key(&rtxn)?.unwrap();
 
-                let _ = builder.execute()?;
+                let primary_key = PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
+                    .map_err(milli::Error::from)?;
+
+                if !tasks.iter().all(|res| res.error.is_some()) {
+                    let local_pool;
+                    let indexer_config = self.index_mapper.indexer_config();
+                    let pool = match &indexer_config.thread_pool {
+                        Some(pool) => pool,
+                        None => {
+                            local_pool = ThreadPoolNoAbortBuilder::new()
+                                .thread_name(|i| format!("indexing-thread-{i}"))
+                                .build()
+                                .unwrap();
+                            &local_pool
+                        }
+                    };
+
+                    let mut indexer = indexer::DocumentDeletion::new();
+                    indexer.delete_documents_by_docids(to_delete);
+                    let document_changes = indexer.into_changes(&indexer_alloc, primary_key);
+                    let embedders = index.embedding_configs(index_wtxn)?;
+                    let embedders = self.embedders(embedders)?;
+
+                    indexer::index(
+                        index_wtxn,
+                        index,
+                        pool,
+                        indexer_config.grenad_parameters(),
+                        &db_fields_ids_map,
+                        new_fields_ids_map,
+                        None, // document deletion never changes primary key
+                        &document_changes,
+                        embedders,
+                        &|| must_stop_processing.get(),
+                        &send_progress,
+                    )?;
+
+                    // tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
+                }
 
                 Ok(tasks)
             }
@@ -1560,7 +1596,6 @@ impl IndexScheduler {
                     task.status = Status::Succeeded;
                 }
 
-                let must_stop_processing = self.must_stop_processing.clone();
                 builder.execute(
                     |indexing_step| tracing::debug!(update = ?indexing_step),
                     || must_stop_processing.get(),
@@ -1568,43 +1603,6 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
-            IndexOperation::SettingsAndDocumentOperation {
-                index_uid,
-                primary_key,
-                method,
-                documents_counts,
-                operations,
-                document_import_tasks,
-                settings,
-                settings_tasks,
-            } => {
-                let settings_tasks = self.apply_index_operation(
-                    index_wtxn,
-                    index,
-                    IndexOperation::Settings {
-                        index_uid: index_uid.clone(),
-                        settings,
-                        tasks: settings_tasks,
-                    },
-                )?;
-
-                let mut import_tasks = self.apply_index_operation(
-                    index_wtxn,
-                    index,
-                    IndexOperation::DocumentOperation {
-                        index_uid,
-                        primary_key,
-                        method,
-                        documents_counts,
-                        operations,
-                        tasks: document_import_tasks,
-                    },
-                )?;
-
-                let mut tasks = settings_tasks;
-                tasks.append(&mut import_tasks);
-                Ok(tasks)
-            }
             IndexOperation::DocumentClearAndSetting {
                 index_uid,
                 cleared_tasks,
@@ -1784,44 +1782,3 @@ impl IndexScheduler {
         Ok(tasks)
     }
 }
-
-fn edit_documents_by_function<'a>(
-    wtxn: &mut RwTxn<'a>,
-    filter: &Option<serde_json::Value>,
-    context: Option<Object>,
-    code: &str,
-    indexer_config: &IndexerConfig,
-    must_stop_processing: MustStopProcessing,
-    index: &'a Index,
-) -> Result<(u64, u64)> {
-    let candidates = match filter.as_ref().map(Filter::from_json) {
-        Some(Ok(Some(filter))) => filter.evaluate(wtxn, index).map_err(|err| match err {
-            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
-                Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
-            }
-            e => e.into(),
-        })?,
-        None | Some(Ok(None)) => index.documents_ids(wtxn)?,
-        Some(Err(e)) => return Err(e.into()),
-    };
-
-    let config = IndexDocumentsConfig {
-        update_method: IndexDocumentsMethod::ReplaceDocuments,
-        ..Default::default()
-    };
-
-    let mut builder = milli::update::IndexDocuments::new(
-        wtxn,
-        index,
-        indexer_config,
-        config,
-        |indexing_step| tracing::debug!(update = ?indexing_step),
-        || must_stop_processing.get(),
-    )?;
-
-    let (new_builder, count) = builder.edit_documents(&candidates, context, code)?;
-    builder = new_builder;
-
-    let _ = builder.execute()?;
-    Ok(count.unwrap())
-}

crates/index-scheduler/src/lib.rs

@@ -56,11 +56,12 @@ use meilisearch_types::heed::types::{SerdeBincode, SerdeJson, Str, I128};
 use meilisearch_types::heed::{self, Database, Env, PutFlags, RoTxn, RwTxn};
 use meilisearch_types::milli::documents::DocumentsBatchBuilder;
 use meilisearch_types::milli::index::IndexEmbeddingConfig;
+use meilisearch_types::milli::update::new::indexer::document_changes::Progress;
 use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::vector::{Embedder, EmbedderOptions, EmbeddingConfigs};
 use meilisearch_types::milli::{self, CboRoaringBitmapCodec, Index, RoaringBitmapCodec, BEU32};
 use meilisearch_types::task_view::TaskView;
-use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
+use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task, TaskProgress};
 use rayon::current_num_threads;
 use rayon::prelude::{IntoParallelIterator, ParallelIterator};
 use roaring::RoaringBitmap;
@@ -167,12 +168,14 @@ pub struct ProcessingTasks {
     batch: Option<ProcessingBatch>,
     /// The list of tasks ids that are currently running.
     processing: RoaringBitmap,
+    /// The progress on processing tasks
+    progress: Option<TaskProgress>,
 }
 
 impl ProcessingTasks {
     /// Creates an empty `ProcessingAt` struct.
     fn new() -> ProcessingTasks {
-        ProcessingTasks { batch: None, processing: RoaringBitmap::new() }
+        ProcessingTasks { batch: None, processing: RoaringBitmap::new(), progress: None }
     }
 
     /// Stores the currently processing tasks, and the date time at which it started.
@@ -181,11 +184,18 @@ impl ProcessingTasks {
         self.processing = processing;
     }
 
+    fn update_progress(&mut self, progress: Progress) -> TaskProgress {
+        self.progress.get_or_insert_with(TaskProgress::default).update(progress)
+    }
+
     /// Set the processing tasks to an empty list
     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,
         }
     }
 
@@ -397,7 +407,7 @@ 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 +476,7 @@ 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 +778,7 @@ 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,
@@ -1352,9 +1362,12 @@ 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 +1440,7 @@ 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);
         }
@@ -1725,11 +1738,8 @@ 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 +1747,10 @@ 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");
 
@@ -2224,7 +2238,7 @@ 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 +2290,7 @@ 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 +2304,7 @@ 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 +2422,7 @@ 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 +4319,35 @@ 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 +5225,10 @@ 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 +5288,7 @@ 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 +5367,8 @@ 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 +5528,7 @@ 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.
@@ -6136,9 +6173,10 @@ mod tests {
 
             let configs = index_scheduler.embedders(configs).unwrap();
             let (hf_embedder, _, _) = configs.get(&simple_hf_name).unwrap();
-            let beagle_embed = hf_embedder.embed_one(S("Intel the beagle best doggo")).unwrap();
-            let lab_embed = hf_embedder.embed_one(S("Max the lab best doggo")).unwrap();
-            let patou_embed = hf_embedder.embed_one(S("kefir the patou best doggo")).unwrap();
+            let 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/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

@@ -1,13 +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, 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) }}

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

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 +24,8 @@ flate2 = "1.0.30"
 fst = "0.4.7"
 memmap2 = "0.9.4"
 milli = { path = "../milli" }
-roaring = { version = "0.10.6", features = ["serde"] }
+raw-collections = { git = "https://github.com/meilisearch/raw-collections.git", version = "0.1.0" }
+roaring = { version = "0.10.7", features = ["serde"] }
 serde = { version = "1.0.204", features = ["derive"] }
 serde-cs = "0.2.4"
 serde_json = "1.0.120"
@@ -70,4 +72,3 @@ swedish-recomposition = ["milli/swedish-recomposition"]
 german = ["milli/german"]
 # allow turkish normalization
 turkish = ["milli/turkish"]
-

crates/meilisearch-types/src/document_formats.rs

@@ -1,20 +1,24 @@
 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 memmap2::Mmap;
+use milli::documents::Error;
 use milli::Object;
+use raw_collections::RawMap;
 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 +92,26 @@ 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 +127,152 @@ 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(obj, &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())),
     }
-
-    let count = builder.documents_count();
-    let _ = builder.into_inner().map_err(DocumentFormatError::Io)?;
-
-    Ok(count as u64)
 }
 
-/// Reads JSON from temporary file  and write an obkv batch to writer.
-pub fn read_ndjson(file: &File, writer: impl Write) -> Result<u64> {
-    let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
-    let mmap = unsafe { MmapOptions::new().map(file)? };
+/// Reads NDJSON from file and write it in NDJSON in a file checking it along the way.
+pub fn read_ndjson(input: &File, output: impl io::Write) -> Result<u64> {
+    // We memory map to be able to 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 output = BufWriter::new(output);
 
-    for result in serde_json::Deserializer::from_slice(&mmap).into_iter() {
-        let object = result.map_err(Error::Json).map_err(|e| (PayloadType::Ndjson, e))?;
-        builder.append_json_object(&object).map_err(Into::into).map_err(DocumentFormatError::Io)?;
+    let mut bump = Bump::with_capacity(1024 * 1024);
+
+    let mut count = 0;
+    for result in serde_json::Deserializer::from_slice(&input).into_iter() {
+        bump.reset();
+        count += 1;
+        result
+            .and_then(|raw: &RawValue| {
+                // try to deserialize as a map
+                let map = RawMap::from_raw_value(raw, &bump)?;
+                to_writer(&mut output, &map)
+            })
+            .map_err(|e| DocumentFormatError::from((PayloadType::Ndjson, e)))?;
     }
 
-    let count = builder.documents_count();
-    let _ = builder.into_inner().map_err(Into::into).map_err(DocumentFormatError::Io)?;
-
-    Ok(count as u64)
+    Ok(count)
 }
 
 /// The actual handling of the deserialization process in serde
@@ -172,20 +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 ;

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-types/src/tasks.rs

@@ -4,6 +4,7 @@ use std::fmt::{Display, Write};
 use std::str::FromStr;
 
 use enum_iterator::Sequence;
+use milli::update::new::indexer::document_changes::Progress;
 use milli::update::IndexDocumentsMethod;
 use milli::Object;
 use roaring::RoaringBitmap;
@@ -40,6 +41,62 @@ pub struct Task {
     pub kind: KindWithContent,
 }
 
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(rename_all = "camelCase")]
+pub struct TaskProgress {
+    pub current_step: &'static str,
+    pub finished_steps: u16,
+    pub total_steps: u16,
+    pub finished_substeps: Option<u32>,
+    pub total_substeps: Option<u32>,
+}
+
+impl Default for TaskProgress {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl TaskProgress {
+    pub fn new() -> Self {
+        Self {
+            current_step: "start",
+            finished_steps: 0,
+            total_steps: 1,
+            finished_substeps: None,
+            total_substeps: None,
+        }
+    }
+
+    pub fn update(&mut self, progress: Progress) -> TaskProgress {
+        if self.finished_steps > progress.finished_steps {
+            return *self;
+        }
+
+        if self.current_step != progress.step_name {
+            self.current_step = progress.step_name
+        }
+
+        self.total_steps = progress.total_steps;
+
+        if self.finished_steps < progress.finished_steps {
+            self.finished_substeps = None;
+            self.total_substeps = None;
+        }
+        self.finished_steps = progress.finished_steps;
+        if let Some((finished_substeps, total_substeps)) = progress.finished_total_substep {
+            if let Some(task_finished_substeps) = self.finished_substeps {
+                if task_finished_substeps > finished_substeps {
+                    return *self;
+                }
+            }
+            self.finished_substeps = Some(finished_substeps);
+            self.total_substeps = Some(total_substeps);
+        }
+        *self
+    }
+}
+
 impl Task {
     pub fn index_uid(&self) -> Option<&str> {
         use KindWithContent::*;

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/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))

crates/meilisearch/src/option.rs

@@ -654,8 +654,9 @@ impl Opt {
 
 #[derive(Debug, Default, Clone, Parser, Deserialize)]
 pub struct IndexerOpts {
-    /// Sets the maximum amount of RAM Meilisearch can use when indexing. By default, Meilisearch
-    /// uses no more than two thirds of available memory.
+    /// Specifies the maximum resident memory that Meilisearch can use for indexing.
+    /// By default, Meilisearch limits the RAM usage to 5% of the total available memory.
+    /// Note that the underlying store utilizes memory-mapping and makes use of the rest.
     #[clap(long, env = MEILI_MAX_INDEXING_MEMORY, default_value_t)]
     #[serde(default)]
     pub max_indexing_memory: MaxMemory,
@@ -714,7 +715,7 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
     }
 }
 
-/// A type used to detect the max memory available and use 2/3 of it.
+/// A type used to detect the max resident memory available and use 5% of it.
 #[derive(Debug, Clone, Copy, Deserialize, Serialize)]
 pub struct MaxMemory(Option<Byte>);
 
@@ -728,7 +729,7 @@ impl FromStr for MaxMemory {
 
 impl Default for MaxMemory {
     fn default() -> MaxMemory {
-        MaxMemory(total_memory_bytes().map(|bytes| bytes * 2 / 3).map(Byte::from_u64))
+        MaxMemory(total_memory_bytes().map(|bytes| bytes * 5 / 100).map(Byte::from_u64))
     }
 }
 

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/search/mod.rs

@@ -796,8 +796,10 @@ 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)?
                 }
@@ -1405,6 +1407,13 @@ 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.
@@ -1687,7 +1696,7 @@ fn add_non_formatted_ids_to_formatted_options(
 fn make_document(
     displayed_attributes: &BTreeSet<FieldId>,
     field_ids_map: &FieldsIdsMap,
-    obkv: obkv::KvReaderU16,
+    obkv: &obkv::KvReaderU16,
 ) -> Result<Document, MeilisearchHttpError> {
     let mut document = serde_json::Map::new();
 

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;

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

@@ -1344,7 +1344,6 @@ 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 +1360,7 @@ 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 +1368,22 @@ 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 +1681,7 @@ 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": "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 +1719,7 @@ 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": "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 +1757,7 @@ 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": "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 +1795,7 @@ 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": "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 +1833,7 @@ 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": "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 +1871,7 @@ 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": "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 +1909,7 @@ 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": "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 +1947,7 @@ 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": "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 +1985,7 @@ 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": "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 +2023,7 @@ 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": "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 +2061,7 @@ 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": "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 +2099,7 @@ 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": "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 +2138,7 @@ 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": "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 +2175,7 @@ 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": "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 +2212,7 @@ 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": "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 +2232,7 @@ 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 +2262,7 @@ 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###"

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/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;
@@ -65,8 +65,8 @@ 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 +89,8 @@ 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 +113,8 @@ 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 +135,8 @@ 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 +151,8 @@ 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 +170,8 @@ 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 +188,8 @@ 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 +200,129 @@ 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": {
@@ -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/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/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": "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": "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": "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": "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": "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": "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": "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": "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": "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": "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": "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": "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"
@@ -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]
@@ -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;
@@ -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");
 

crates/meilitool/src/main.rs

@@ -264,7 +264,7 @@ fn export_a_dump(
                         format!("While iterating on content file {:?}", content_file_uuid)
                     })? {
                         dump_content_file
-                            .push_document(&obkv_to_object(&doc, &documents_batch_index)?)?;
+                            .push_document(&obkv_to_object(doc, &documents_batch_index)?)?;
                     }
                     dump_content_file.flush()?;
                     count += 1;

crates/milli/Cargo.toml

@@ -12,12 +12,13 @@ readme.workspace = true
 license.workspace = true
 
 [dependencies]
+big_s = "1.0.2"
 bimap = { version = "0.6.3", features = ["serde"] }
 bincode = "1.3.3"
 bstr = "1.9.1"
 bytemuck = { version = "1.18.0", features = ["extern_crate_alloc"] }
 byteorder = "1.5.0"
-charabia = { version = "0.9.1", default-features = false }
+charabia = { version = "0.9.2", default-features = false }
 concat-arrays = "0.1.2"
 crossbeam-channel = "0.5.13"
 deserr = "0.6.2"
@@ -26,10 +27,7 @@ flatten-serde-json = { path = "../flatten-serde-json" }
 fst = "0.4.7"
 fxhash = "0.2.1"
 geoutils = "0.5.1"
-grenad = { version = "0.4.7", default-features = false, features = [
-    "rayon",
-    "tempfile",
-] }
+grenad = { version = "0.5.0", default-features = false, features = ["rayon", "tempfile"] }
 heed = { version = "0.20.3", default-features = false, features = [
     "serde-json",
     "serde-bincode",
@@ -40,14 +38,14 @@ json-depth-checker = { path = "../json-depth-checker" }
 levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
 memchr = "2.5.0"
 memmap2 = "0.9.4"
-obkv = "0.2.2"
+obkv = "0.3.0"
 once_cell = "1.19.0"
 ordered-float = "4.2.1"
 rayon = "1.10.0"
-roaring = { version = "0.10.6", features = ["serde"] }
+roaring = { version = "0.10.7", features = ["serde"] }
 rstar = { version = "0.12.0", features = ["serde"] }
 serde = { version = "1.0.204", features = ["derive"] }
-serde_json = { version = "1.0.120", features = ["preserve_order"] }
+serde_json = { version = "1.0.120", features = ["preserve_order", "raw_value"] }
 slice-group-by = "0.3.1"
 smallstr = { version = "0.3.0", features = ["serde"] }
 smallvec = "1.13.2"
@@ -79,17 +77,32 @@ hf-hub = { git = "https://github.com/dureuill/hf-hub.git", branch = "rust_tls",
 ] }
 tiktoken-rs = "0.5.9"
 liquid = "0.26.6"
-rhai = { git = "https://github.com/rhaiscript/rhai", rev = "ef3df63121d27aacd838f366f2b83fd65f20a1e4", features = ["serde", "no_module", "no_custom_syntax", "no_time", "sync"] }
+rhai = { git = "https://github.com/rhaiscript/rhai", rev = "ef3df63121d27aacd838f366f2b83fd65f20a1e4", features = [
+    "serde",
+    "no_module",
+    "no_custom_syntax",
+    "no_time",
+    "sync",
+] }
 arroy = "0.5.0"
 rand = "0.8.5"
 tracing = "0.1.40"
 ureq = { version = "2.10.0", features = ["json"] }
 url = "2.5.2"
 rayon-par-bridge = "0.1.0"
+hashbrown = "0.15.0"
+raw-collections = { git = "https://github.com/meilisearch/raw-collections.git", version = "0.1.0" }
+bumpalo = "3.16.0"
+thread_local = "1.1.8"
+allocator-api2 = "0.2.18"
+rustc-hash = "2.0.0"
+uell = "0.1.0"
+enum-iterator = "2.1.0"
+bbqueue = { git = "https://github.com/meilisearch/bbqueue" }
+flume = { version = "0.11.1", default-features = false }
 
 [dev-dependencies]
 mimalloc = { version = "0.1.43", default-features = false }
-big_s = "1.0.2"
 insta = "1.39.0"
 maplit = "1.0.2"
 md5 = "0.7.0"

crates/milli/examples/index.rs

@@ -1,114 +0,0 @@
-use std::error::Error;
-use std::fs::File;
-use std::io::{BufRead, BufReader, Cursor, Seek};
-use std::path::Path;
-
-use heed::EnvOpenOptions;
-use milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
-use milli::update::{IndexDocuments, IndexDocumentsConfig, IndexerConfig, Settings};
-use milli::{Index, Object};
-
-fn usage(error: &str, program_name: &str) -> String {
-    format!(
-        "{}. Usage: {} <PATH-TO-INDEX> <PATH-TO-DATASET> [searchable_fields] [filterable_fields]",
-        error, program_name
-    )
-}
-
-fn main() -> Result<(), Box<dyn Error>> {
-    let mut args = std::env::args();
-    let program_name = args.next().expect("No program name");
-    let index_path =
-        args.next().unwrap_or_else(|| panic!("{}", usage("Missing path to index.", &program_name)));
-    let dataset_path = args
-        .next()
-        .unwrap_or_else(|| panic!("{}", usage("Missing path to source dataset.", &program_name)));
-    // let primary_key = args.next().unwrap_or_else(|| "id".into());
-    // "title overview"
-    let searchable_fields: Vec<String> = args
-        .next()
-        .map(|arg| arg.split_whitespace().map(ToString::to_string).collect())
-        .unwrap_or_default();
-
-    println!("{searchable_fields:?}");
-    // "release_date genres"
-    let filterable_fields: Vec<String> = args
-        .next()
-        .map(|arg| arg.split_whitespace().map(ToString::to_string).collect())
-        .unwrap_or_default();
-
-    let mut options = EnvOpenOptions::new();
-    options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
-
-    std::fs::create_dir_all(&index_path).unwrap();
-    let index = Index::new(options, index_path).unwrap();
-    let mut wtxn = index.write_txn().unwrap();
-
-    let config = IndexerConfig::default();
-    let mut builder = Settings::new(&mut wtxn, &index, &config);
-    // builder.set_primary_key(primary_key);
-    let searchable_fields = searchable_fields.iter().map(|s| s.to_string()).collect();
-    builder.set_searchable_fields(searchable_fields);
-    let filterable_fields = filterable_fields.iter().map(|s| s.to_string()).collect();
-    builder.set_filterable_fields(filterable_fields);
-
-    builder.execute(|_| (), || false).unwrap();
-
-    let config = IndexerConfig::default();
-    let indexing_config = IndexDocumentsConfig::default();
-
-    let builder =
-        IndexDocuments::new(&mut wtxn, &index, &config, indexing_config, |_| (), || false).unwrap();
-
-    let documents = documents_from(
-        &dataset_path,
-        Path::new(&dataset_path).extension().unwrap_or_default().to_str().unwrap_or_default(),
-    );
-    let (builder, user_error) = builder.add_documents(documents).unwrap();
-    user_error.unwrap();
-    builder.execute().unwrap();
-    wtxn.commit().unwrap();
-
-    index.prepare_for_closing().wait();
-    Ok(())
-}
-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()
-}
-
-fn documents_from_jsonl(reader: impl BufRead) -> milli::Result<Vec<u8>> {
-    let mut documents = DocumentsBatchBuilder::new(Vec::new());
-
-    for result in serde_json::Deserializer::from_reader(reader).into_iter::<Object>() {
-        let object = result.unwrap();
-        documents.append_json_object(&object)?;
-    }
-
-    documents.into_inner().map_err(Into::into)
-}
-
-fn documents_from_json(reader: impl BufRead) -> milli::Result<Vec<u8>> {
-    let mut documents = DocumentsBatchBuilder::new(Vec::new());
-
-    documents.append_json_array(reader)?;
-
-    documents.into_inner().map_err(Into::into)
-}
-
-fn documents_from_csv(reader: impl BufRead) -> milli::Result<Vec<u8>> {
-    let csv = csv::Reader::from_reader(reader);
-
-    let mut documents = DocumentsBatchBuilder::new(Vec::new());
-    documents.append_csv(csv)?;
-
-    documents.into_inner().map_err(Into::into)
-}

crates/milli/examples/search.rs

@@ -1,124 +0,0 @@
-use std::error::Error;
-use std::io::stdin;
-use std::path::Path;
-use std::time::Instant;
-
-use heed::EnvOpenOptions;
-use milli::{
-    execute_search, filtered_universe, DefaultSearchLogger, GeoSortStrategy, Index, SearchContext,
-    SearchLogger, TermsMatchingStrategy, TimeBudget,
-};
-
-#[global_allocator]
-static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
-
-fn main() -> Result<(), Box<dyn Error>> {
-    let mut args = std::env::args();
-    let program_name = args.next().expect("No program name");
-    let dataset = args.next().unwrap_or_else(|| {
-        panic!(
-            "Missing path to index. Usage: {} <PATH-TO-INDEX> [<logger-dir>] [print-documents]",
-            program_name
-        )
-    });
-    let detailed_logger_dir = args.next();
-    let print_documents: bool =
-        if let Some(arg) = args.next() { arg == "print-documents" } else { false };
-
-    let mut options = EnvOpenOptions::new();
-    options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
-
-    let index = Index::new(options, dataset)?;
-    let txn = index.read_txn()?;
-    let mut query = String::new();
-    while stdin().read_line(&mut query)? > 0 {
-        for _ in 0..2 {
-            let mut default_logger = DefaultSearchLogger;
-            // FIXME: consider resetting the state of the logger between search executions as otherwise panics are possible.
-            // Workaround'd here by recreating the logger on each iteration of the loop
-            let mut detailed_logger = detailed_logger_dir
-                .as_ref()
-                .map(|logger_dir| (milli::VisualSearchLogger::default(), logger_dir));
-            let logger: &mut dyn SearchLogger<_> =
-                if let Some((detailed_logger, _)) = detailed_logger.as_mut() {
-                    detailed_logger
-                } else {
-                    &mut default_logger
-                };
-
-            let start = Instant::now();
-
-            let mut ctx = SearchContext::new(&index, &txn)?;
-            let universe = filtered_universe(ctx.index, ctx.txn, &None)?;
-
-            let docs = execute_search(
-                &mut ctx,
-                (!query.trim().is_empty()).then(|| query.trim()),
-                TermsMatchingStrategy::Last,
-                milli::score_details::ScoringStrategy::Skip,
-                false,
-                universe,
-                &None,
-                &None,
-                GeoSortStrategy::default(),
-                0,
-                20,
-                None,
-                &mut DefaultSearchLogger,
-                logger,
-                TimeBudget::max(),
-                None,
-                None,
-            )?;
-            if let Some((logger, dir)) = detailed_logger {
-                logger.finish(&mut ctx, Path::new(dir))?;
-            }
-            let elapsed = start.elapsed();
-            println!("new: {}us, docids: {:?}", elapsed.as_micros(), docs.documents_ids);
-            if print_documents {
-                let documents = index
-                    .documents(&txn, docs.documents_ids.iter().copied())
-                    .unwrap()
-                    .into_iter()
-                    .map(|(id, obkv)| {
-                        let mut object = serde_json::Map::default();
-                        for (fid, fid_name) in index.fields_ids_map(&txn).unwrap().iter() {
-                            let value = obkv.get(fid).unwrap();
-                            let value: serde_json::Value = serde_json::from_slice(value).unwrap();
-                            object.insert(fid_name.to_owned(), value);
-                        }
-                        (id, serde_json::to_string_pretty(&object).unwrap())
-                    })
-                    .collect::<Vec<_>>();
-
-                for (id, document) in documents {
-                    println!("{id}:");
-                    println!("{document}");
-                }
-
-                let documents = index
-                    .documents(&txn, docs.documents_ids.iter().copied())
-                    .unwrap()
-                    .into_iter()
-                    .map(|(id, obkv)| {
-                        let mut object = serde_json::Map::default();
-                        for (fid, fid_name) in index.fields_ids_map(&txn).unwrap().iter() {
-                            let value = obkv.get(fid).unwrap();
-                            let value: serde_json::Value = serde_json::from_slice(value).unwrap();
-                            object.insert(fid_name.to_owned(), value);
-                        }
-                        (id, serde_json::to_string_pretty(&object).unwrap())
-                    })
-                    .collect::<Vec<_>>();
-                println!("{}us: {:?}", elapsed.as_micros(), docs.documents_ids);
-                for (id, document) in documents {
-                    println!("{id}:");
-                    println!("{document}");
-                }
-            }
-        }
-        query.clear();
-    }
-
-    Ok(())
-}

crates/milli/examples/settings.rs

@@ -1,33 +0,0 @@
-// use big_s::S;
-use heed::EnvOpenOptions;
-// use maplit::hashset;
-use milli::{
-    update::{IndexerConfig, Settings},
-    Criterion, Index,
-};
-
-fn main() {
-    let mut options = EnvOpenOptions::new();
-    options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
-
-    let index = Index::new(options, "data_movies.ms").unwrap();
-    let mut wtxn = index.write_txn().unwrap();
-
-    let config = IndexerConfig::default();
-    let mut builder = Settings::new(&mut wtxn, &index, &config);
-
-    // builder.set_min_word_len_one_typo(5);
-    // builder.set_min_word_len_two_typos(7);
-    // builder.set_sortable_fields(hashset! { S("release_date") });
-    builder.set_criteria(vec![
-        Criterion::Words,
-        Criterion::Typo,
-        Criterion::Proximity,
-        Criterion::Attribute,
-        Criterion::Sort,
-        Criterion::Exactness,
-    ]);
-
-    builder.execute(|_| (), || false).unwrap();
-    wtxn.commit().unwrap();
-}

crates/milli/src/documents/builder.rs

@@ -2,7 +2,7 @@ use std::io::{self, Write};
 
 use grenad::{CompressionType, WriterBuilder};
 use serde::de::Deserializer;
-use serde_json::{to_writer, Value};
+use serde_json::to_writer;
 
 use super::{DocumentsBatchIndex, Error, DOCUMENTS_BATCH_INDEX_KEY};
 use crate::documents::serde_impl::DocumentVisitor;
@@ -87,95 +87,6 @@ impl<W: Write> DocumentsBatchBuilder<W> {
         de.deserialize_any(&mut visitor)?
     }
 
-    /// Appends a new CSV file into the batch and updates the `DocumentsBatchIndex` accordingly.
-    pub fn append_csv<R: io::Read>(&mut self, mut reader: csv::Reader<R>) -> Result<(), Error> {
-        // Make sure that we insert the fields ids in order as the obkv writer has this requirement.
-        let mut typed_fields_ids: Vec<_> = reader
-            .headers()?
-            .into_iter()
-            .map(parse_csv_header)
-            .map(|(k, t)| (self.fields_index.insert(k), t))
-            .enumerate()
-            .collect();
-        // Make sure that we insert the fields ids in order as the obkv writer has this requirement.
-        typed_fields_ids.sort_unstable_by_key(|(_, (fid, _))| *fid);
-
-        let mut record = csv::StringRecord::new();
-        let mut line = 0;
-        while reader.read_record(&mut record)? {
-            // We increment here and not at the end of the while loop to take
-            // the header offset into account.
-            line += 1;
-
-            self.obkv_buffer.clear();
-            let mut writer = obkv::KvWriter::new(&mut self.obkv_buffer);
-
-            for (i, (field_id, type_)) in typed_fields_ids.iter() {
-                self.value_buffer.clear();
-
-                let value = &record[*i];
-                let trimmed_value = value.trim();
-                match type_ {
-                    AllowedType::Number => {
-                        if trimmed_value.is_empty() {
-                            to_writer(&mut self.value_buffer, &Value::Null)?;
-                        } else if let Ok(integer) = trimmed_value.parse::<i64>() {
-                            to_writer(&mut self.value_buffer, &integer)?;
-                        } else {
-                            match trimmed_value.parse::<f64>() {
-                                Ok(float) => {
-                                    to_writer(&mut self.value_buffer, &float)?;
-                                }
-                                Err(error) => {
-                                    return Err(Error::ParseFloat {
-                                        error,
-                                        line,
-                                        value: value.to_string(),
-                                    });
-                                }
-                            }
-                        }
-                    }
-                    AllowedType::Boolean => {
-                        if trimmed_value.is_empty() {
-                            to_writer(&mut self.value_buffer, &Value::Null)?;
-                        } else {
-                            match trimmed_value.parse::<bool>() {
-                                Ok(bool) => {
-                                    to_writer(&mut self.value_buffer, &bool)?;
-                                }
-                                Err(error) => {
-                                    return Err(Error::ParseBool {
-                                        error,
-                                        line,
-                                        value: value.to_string(),
-                                    });
-                                }
-                            }
-                        }
-                    }
-                    AllowedType::String => {
-                        if value.is_empty() {
-                            to_writer(&mut self.value_buffer, &Value::Null)?;
-                        } else {
-                            to_writer(&mut self.value_buffer, value)?;
-                        }
-                    }
-                }
-
-                // We insert into the obkv writer the value buffer that has been filled just above.
-                writer.insert(*field_id, &self.value_buffer)?;
-            }
-
-            let internal_id = self.documents_count.to_be_bytes();
-            let document_bytes = writer.into_inner()?;
-            self.writer.insert(internal_id, &document_bytes)?;
-            self.documents_count += 1;
-        }
-
-        Ok(())
-    }
-
     /// Flushes the content on disk and stores the final version of the `DocumentsBatchIndex`.
     pub fn into_inner(mut self) -> io::Result<W> {
         let DocumentsBatchBuilder { mut writer, fields_index, .. } = self;
@@ -189,35 +100,12 @@ impl<W: Write> DocumentsBatchBuilder<W> {
     }
 }
 
-#[derive(Debug)]
-enum AllowedType {
-    String,
-    Boolean,
-    Number,
-}
-
-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),
-    }
-}
-
 #[cfg(test)]
 mod test {
     use std::io::Cursor;
 
-    use serde_json::json;
-
     use super::*;
-    use crate::documents::{obkv_to_object, DocumentsBatchReader};
+    use crate::documents::DocumentsBatchReader;
 
     #[test]
     fn add_single_documents_json() {
@@ -253,348 +141,4 @@ mod test {
 
         assert!(cursor.next_document().unwrap().is_none());
     }
-
-    #[test]
-    fn add_documents_csv() {
-        let csv_content = "id:number,field:string\n1,hello!\n2,blabla";
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        assert_eq!(builder.documents_count(), 2);
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-        assert_eq!(index.len(), 2);
-
-        let document = cursor.next_document().unwrap().unwrap();
-        assert_eq!(document.iter().count(), 2);
-
-        let document = cursor.next_document().unwrap().unwrap();
-        assert_eq!(document.iter().count(), 2);
-
-        assert!(cursor.next_document().unwrap().is_none());
-    }
-
-    #[test]
-    fn simple_csv_document() {
-        let csv_content = r#"city,country,pop
-"Boston","United States","4628910""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-        let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
-
-        assert_eq!(
-            val,
-            json!({
-                "city": "Boston",
-                "country": "United States",
-                "pop": "4628910",
-            })
-        );
-
-        assert!(cursor.next_document().unwrap().is_none());
-    }
-
-    #[test]
-    fn coma_in_field() {
-        let csv_content = r#"city,country,pop
-"Boston","United, States","4628910""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-
-        let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
-
-        assert_eq!(
-            val,
-            json!({
-                "city": "Boston",
-                "country": "United, States",
-                "pop": "4628910",
-            })
-        );
-    }
-
-    #[test]
-    fn quote_in_field() {
-        let csv_content = r#"city,country,pop
-"Boston","United"" States","4628910""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-
-        let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
-
-        assert_eq!(
-            val,
-            json!({
-                "city": "Boston",
-                "country": "United\" States",
-                "pop": "4628910",
-            })
-        );
-    }
-
-    #[test]
-    fn integer_in_field() {
-        let csv_content = r#"city,country,pop:number
-"Boston","United States","4628910""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-
-        let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
-
-        assert_eq!(
-            val,
-            json!({
-                "city": "Boston",
-                "country": "United States",
-                "pop": 4628910,
-            })
-        );
-    }
-
-    #[test]
-    fn integer_as_id() {
-        let csv_content = r#""id:number","title:string","comment:string"
-"1239","Pride and Prejudice","A great book""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-
-        let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
-
-        assert_eq!(
-            val,
-            json!({
-                "id": 1239,
-                "title": "Pride and Prejudice",
-                "comment": "A great book",
-            })
-        );
-    }
-
-    #[test]
-    fn float_in_field() {
-        let csv_content = r#"city,country,pop:number
-"Boston","United States","4628910.01""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-
-        let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
-
-        assert_eq!(
-            val,
-            json!({
-                "city": "Boston",
-                "country": "United States",
-                "pop": 4628910.01,
-            })
-        );
-    }
-
-    #[test]
-    fn several_colon_in_header() {
-        let csv_content = r#"city:love:string,country:state,pop
-"Boston","United States","4628910""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-
-        let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
-
-        assert_eq!(
-            val,
-            json!({
-                "city:love": "Boston",
-                "country:state": "United States",
-                "pop": "4628910",
-            })
-        );
-    }
-
-    #[test]
-    fn ending_by_colon_in_header() {
-        let csv_content = r#"city:,country,pop
-"Boston","United States","4628910""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-
-        let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
-
-        assert_eq!(
-            val,
-            json!({
-                "city:": "Boston",
-                "country": "United States",
-                "pop": "4628910",
-            })
-        );
-    }
-
-    #[test]
-    fn starting_by_colon_in_header() {
-        let csv_content = r#":city,country,pop
-"Boston","United States","4628910""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-
-        let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
-
-        assert_eq!(
-            val,
-            json!({
-                ":city": "Boston",
-                "country": "United States",
-                "pop": "4628910",
-            })
-        );
-    }
-
-    #[ignore]
-    #[test]
-    fn starting_by_colon_in_header2() {
-        let csv_content = r#":string,country,pop
-"Boston","United States","4628910""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, _) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-
-        assert!(cursor.next_document().is_err());
-    }
-
-    #[test]
-    fn double_colon_in_header() {
-        let csv_content = r#"city::string,country,pop
-"Boston","United States","4628910""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        let (mut cursor, index) = DocumentsBatchReader::from_reader(Cursor::new(vector))
-            .unwrap()
-            .into_cursor_and_fields_index();
-
-        let doc = cursor.next_document().unwrap().unwrap();
-        let val = obkv_to_object(&doc, &index).map(Value::from).unwrap();
-
-        assert_eq!(
-            val,
-            json!({
-                "city:": "Boston",
-                "country": "United States",
-                "pop": "4628910",
-            })
-        );
-    }
-
-    #[test]
-    fn bad_type_in_header() {
-        let csv_content = r#"city,country:number,pop
-"Boston","United States","4628910""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        assert!(builder.append_csv(csv).is_err());
-    }
-
-    #[test]
-    fn bad_column_count1() {
-        let csv_content = r#"city,country,pop
-"Boston","United States","4628910", "too much
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content"#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        assert!(builder.append_csv(csv).is_err());
-    }
-
-    #[test]
-    fn bad_column_count2() {
-        let csv_content = r#"city,country,pop
-"Boston","United States""#;
-        let csv = csv::Reader::from_reader(Cursor::new(csv_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        assert!(builder.append_csv(csv).is_err());
-    }
 }

crates/milli/src/documents/enriched.rs

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

crates/milli/src/documents/mod.rs

@@ -13,8 +13,8 @@ pub use builder::DocumentsBatchBuilder;
 pub use enriched::{EnrichedDocument, EnrichedDocumentsBatchCursor, EnrichedDocumentsBatchReader};
 use obkv::KvReader;
 pub use primary_key::{
-    validate_document_id_value, DocumentIdExtractionError, FieldIdMapper, PrimaryKey,
-    DEFAULT_PRIMARY_KEY,
+    validate_document_id_str, validate_document_id_value, DocumentIdExtractionError, FieldIdMapper,
+    PrimaryKey, DEFAULT_PRIMARY_KEY,
 };
 pub use reader::{DocumentsBatchCursor, DocumentsBatchCursorError, DocumentsBatchReader};
 use serde::{Deserialize, Serialize};
@@ -27,7 +27,7 @@ use crate::{FieldId, Object, Result};
 const DOCUMENTS_BATCH_INDEX_KEY: [u8; 8] = u64::MAX.to_be_bytes();
 
 /// Helper function to convert an obkv reader into a JSON object.
-pub fn obkv_to_object(obkv: &KvReader<'_, FieldId>, index: &DocumentsBatchIndex) -> Result<Object> {
+pub fn obkv_to_object(obkv: &KvReader<FieldId>, index: &DocumentsBatchIndex) -> Result<Object> {
     obkv.iter()
         .map(|(field_id, value)| {
             let field_name = index
@@ -76,7 +76,7 @@ impl DocumentsBatchIndex {
         self.0.get_by_right(name).cloned()
     }
 
-    pub fn recreate_json(&self, document: &obkv::KvReaderU16<'_>) -> Result<Object> {
+    pub fn recreate_json(&self, document: &obkv::KvReaderU16) -> Result<Object> {
         let mut map = Object::new();
 
         for (k, v) in document.iter() {
@@ -96,6 +96,10 @@ impl FieldIdMapper for DocumentsBatchIndex {
     fn id(&self, name: &str) -> Option<FieldId> {
         self.id(name)
     }
+
+    fn name(&self, id: FieldId) -> Option<&str> {
+        self.name(id)
+    }
 }
 
 #[derive(Debug, thiserror::Error)]
@@ -146,11 +150,33 @@ pub fn objects_from_json_value(json: serde_json::Value) -> Vec<crate::Object> {
 macro_rules! documents {
     ($data:tt) => {{
         let documents = serde_json::json!($data);
-        let documents = $crate::documents::objects_from_json_value(documents);
-        $crate::documents::documents_batch_reader_from_objects(documents)
+        let mut file = tempfile::tempfile().unwrap();
+
+        match documents {
+            serde_json::Value::Array(vec) => {
+                for document in vec {
+                    serde_json::to_writer(&mut file, &document).unwrap();
+                }
+            }
+            serde_json::Value::Object(document) => {
+                serde_json::to_writer(&mut file, &document).unwrap();
+            }
+            _ => unimplemented!("The `documents!` macro only support Objects and Array"),
+        }
+        file.sync_all().unwrap();
+        unsafe { memmap2::Mmap::map(&file).unwrap() }
     }};
 }
 
+pub fn mmap_from_objects(objects: impl IntoIterator<Item = Object>) -> memmap2::Mmap {
+    let mut writer = tempfile::tempfile().map(std::io::BufWriter::new).unwrap();
+    for object in objects {
+        serde_json::to_writer(&mut writer, &object).unwrap();
+    }
+    let file = writer.into_inner().unwrap();
+    unsafe { memmap2::Mmap::map(&file).unwrap() }
+}
+
 pub fn documents_batch_reader_from_objects(
     objects: impl IntoIterator<Item = Object>,
 ) -> DocumentsBatchReader<std::io::Cursor<Vec<u8>>> {
@@ -166,7 +192,7 @@ pub fn documents_batch_reader_from_objects(
 mod test {
     use std::io::Cursor;
 
-    use serde_json::{json, Value};
+    use serde_json::json;
 
     use super::*;
 
@@ -220,20 +246,6 @@ mod test {
         assert!(documents.next_document().unwrap().is_none());
     }
 
-    #[test]
-    fn test_nested() {
-        let docs_reader = documents!([{
-            "hello": {
-                "toto": ["hello"]
-            }
-        }]);
-
-        let (mut cursor, _) = docs_reader.into_cursor_and_fields_index();
-        let doc = cursor.next_document().unwrap().unwrap();
-        let nested: Value = serde_json::from_slice(doc.get(0).unwrap()).unwrap();
-        assert_eq!(nested, json!({ "toto": ["hello"] }));
-    }
-
     #[test]
     fn out_of_order_json_fields() {
         let _documents = documents!([
@@ -241,33 +253,4 @@ mod test {
             {"id": 2,"a": 0,"b": 0},
         ]);
     }
-
-    #[test]
-    fn csv_types_dont_panic() {
-        let csv1_content =
-            "id:number,b:boolean,c,d:number\n1,,,\n2,true,doggo,2\n3,false,the best doggo,-2\n4,,\"Hello, World!\",2.5";
-        let csv1 = csv::Reader::from_reader(Cursor::new(csv1_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv1).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        DocumentsBatchReader::from_reader(Cursor::new(vector)).unwrap();
-    }
-
-    #[test]
-    fn out_of_order_csv_fields() {
-        let csv1_content = "id:number,b\n1,0";
-        let csv1 = csv::Reader::from_reader(Cursor::new(csv1_content));
-
-        let csv2_content = "id:number,a,b\n2,0,0";
-        let csv2 = csv::Reader::from_reader(Cursor::new(csv2_content));
-
-        let mut builder = DocumentsBatchBuilder::new(Vec::new());
-        builder.append_csv(csv1).unwrap();
-        builder.append_csv(csv2).unwrap();
-        let vector = builder.into_inner().unwrap();
-
-        DocumentsBatchReader::from_reader(Cursor::new(vector)).unwrap();
-    }
 }

crates/milli/src/documents/primary_key.rs

@@ -1,8 +1,14 @@
 use std::iter;
+use std::ops::ControlFlow;
 use std::result::Result as StdResult;
 
+use bumpalo::Bump;
+use serde_json::value::RawValue;
 use serde_json::Value;
 
+use crate::fields_ids_map::MutFieldIdMapper;
+use crate::update::new::indexer::de::{match_component, DeOrBumpStr};
+use crate::update::new::KvReaderFieldId;
 use crate::{FieldId, InternalError, Object, Result, UserError};
 
 /// The symbol used to define levels in a nested primary key.
@@ -17,6 +23,21 @@ pub trait FieldIdMapper {
     ///
     /// `None` if the field with this name was not found.
     fn id(&self, name: &str) -> Option<FieldId>;
+
+    fn name(&self, id: FieldId) -> Option<&str>;
+}
+
+impl<T> FieldIdMapper for &T
+where
+    T: FieldIdMapper,
+{
+    fn id(&self, name: &str) -> Option<FieldId> {
+        T::id(self, name)
+    }
+
+    fn name(&self, id: FieldId) -> Option<&str> {
+        T::name(self, id)
+    }
 }
 
 /// A type that represent the type of primary key that has been set
@@ -43,7 +64,19 @@ impl<'a> PrimaryKey<'a> {
         })
     }
 
-    pub fn name(&self) -> &str {
+    pub fn new_or_insert(
+        path: &'a str,
+        fields: &mut impl MutFieldIdMapper,
+    ) -> StdResult<Self, UserError> {
+        Ok(if path.contains(PRIMARY_KEY_SPLIT_SYMBOL) {
+            Self::Nested { name: path }
+        } else {
+            let field_id = fields.insert(path).ok_or(UserError::AttributeLimitReached)?;
+            Self::Flat { name: path, field_id }
+        })
+    }
+
+    pub fn name(&self) -> &'a str {
         match self {
             PrimaryKey::Flat { name, .. } => name,
             PrimaryKey::Nested { name } => name,
@@ -52,7 +85,7 @@ impl<'a> PrimaryKey<'a> {
 
     pub fn document_id(
         &self,
-        document: &obkv::KvReader<'_, FieldId>,
+        document: &obkv::KvReader<FieldId>,
         fields: &impl FieldIdMapper,
     ) -> Result<StdResult<String, DocumentIdExtractionError>> {
         match self {
@@ -100,9 +133,105 @@ impl<'a> PrimaryKey<'a> {
         }
     }
 
+    pub fn extract_docid_from_db<'pl, 'bump: 'pl, Mapper: FieldIdMapper>(
+        &self,
+        document: &'pl KvReaderFieldId,
+        db_fields_ids_map: &Mapper,
+        indexer: &'bump Bump,
+    ) -> Result<DeOrBumpStr<'pl, 'bump>> {
+        use serde::Deserializer as _;
+
+        match self {
+            PrimaryKey::Flat { name: _, field_id } => {
+                let Some(document_id) = document.get(*field_id) else {
+                    return Err(InternalError::DocumentsError(
+                        crate::documents::Error::InvalidDocumentFormat,
+                    )
+                    .into());
+                };
+
+                let document_id: &RawValue =
+                    serde_json::from_slice(document_id).map_err(InternalError::SerdeJson)?;
+
+                let document_id = document_id
+                    .deserialize_any(crate::update::new::indexer::de::DocumentIdVisitor(indexer))
+                    .map_err(InternalError::SerdeJson)?;
+
+                let external_document_id = match document_id {
+                    Ok(document_id) => Ok(document_id),
+                    Err(_) => Err(InternalError::DocumentsError(
+                        crate::documents::Error::InvalidDocumentFormat,
+                    )),
+                }?;
+
+                Ok(external_document_id)
+            }
+            nested @ PrimaryKey::Nested { name: _ } => {
+                let mut docid = None;
+                for (first_level, right) in nested.possible_level_names() {
+                    let Some(fid) = db_fields_ids_map.id(first_level) else { continue };
+
+                    let Some(value) = document.get(fid) else { continue };
+                    let value: &RawValue =
+                        serde_json::from_slice(value).map_err(InternalError::SerdeJson)?;
+                    match match_component(first_level, right, value, indexer, &mut docid) {
+                        ControlFlow::Continue(()) => continue,
+                        ControlFlow::Break(Ok(_)) => {
+                            return Err(InternalError::DocumentsError(
+                                crate::documents::Error::InvalidDocumentFormat,
+                            )
+                            .into())
+                        }
+                        ControlFlow::Break(Err(err)) => {
+                            return Err(InternalError::SerdeJson(err).into())
+                        }
+                    }
+                }
+                Ok(docid.ok_or(InternalError::DocumentsError(
+                    crate::documents::Error::InvalidDocumentFormat,
+                ))?)
+            }
+        }
+    }
+
+    pub fn extract_fields_and_docid<'pl, 'bump: 'pl, Mapper: MutFieldIdMapper>(
+        &self,
+        document: &'pl RawValue,
+        new_fields_ids_map: &mut Mapper,
+        indexer: &'bump Bump,
+    ) -> Result<DeOrBumpStr<'pl, 'bump>> {
+        use serde::Deserializer as _;
+        let res = document
+            .deserialize_map(crate::update::new::indexer::de::FieldAndDocidExtractor::new(
+                new_fields_ids_map,
+                self,
+                indexer,
+            ))
+            .map_err(UserError::SerdeJson)??;
+
+        let external_document_id = match res {
+            Ok(document_id) => Ok(document_id),
+            Err(DocumentIdExtractionError::InvalidDocumentId(e)) => Err(e),
+            Err(DocumentIdExtractionError::MissingDocumentId) => {
+                Err(UserError::MissingDocumentId {
+                    primary_key: self.name().to_string(),
+                    document: serde_json::from_str(document.get()).unwrap(),
+                })
+            }
+            Err(DocumentIdExtractionError::TooManyDocumentIds(_)) => {
+                Err(UserError::TooManyDocumentIds {
+                    primary_key: self.name().to_string(),
+                    document: serde_json::from_str(document.get()).unwrap(),
+                })
+            }
+        }?;
+
+        Ok(external_document_id)
+    }
+
     /// Returns an `Iterator` that gives all the possible fields names the primary key
     /// can have depending of the first level name and depth of the objects.
-    pub fn possible_level_names(&self) -> impl Iterator<Item = (&str, &str)> + '_ {
+    pub fn possible_level_names(&self) -> impl Iterator<Item = (&'a str, &'a str)> + '_ {
         let name = self.name();
         name.match_indices(PRIMARY_KEY_SPLIT_SYMBOL)
             .map(move |(i, _)| (&name[..i], &name[i + PRIMARY_KEY_SPLIT_SYMBOL.len_utf8()..]))
@@ -149,7 +278,7 @@ fn starts_with(selector: &str, key: &str) -> bool {
 
 // FIXME: move to a DocumentId struct
 
-fn validate_document_id(document_id: &str) -> Option<&str> {
+pub fn validate_document_id_str(document_id: &str) -> Option<&str> {
     if document_id.is_empty()
         || document_id.len() > 512
         || !document_id.chars().all(|c| c.is_ascii_alphanumeric() || c == '-' || c == '_')
@@ -162,7 +291,7 @@ fn validate_document_id(document_id: &str) -> Option<&str> {
 
 pub fn validate_document_id_value(document_id: Value) -> StdResult<String, UserError> {
     match document_id {
-        Value::String(string) => match validate_document_id(&string) {
+        Value::String(string) => match validate_document_id_str(&string) {
             Some(s) if s.len() == string.len() => Ok(string),
             Some(s) => Ok(s.to_string()),
             None => Err(UserError::InvalidDocumentId { document_id: Value::String(string) }),

crates/milli/src/documents/reader.rs

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

crates/milli/src/error.rs

@@ -3,6 +3,7 @@ use std::convert::Infallible;
 use std::fmt::Write;
 use std::{io, str};
 
+use bstr::BString;
 use heed::{Error as HeedError, MdbError};
 use rayon::ThreadPoolBuildError;
 use rhai::EvalAltResult;
@@ -31,23 +32,23 @@ pub enum Error {
 pub enum InternalError {
     #[error("{}", HeedError::DatabaseClosing)]
     DatabaseClosing,
-    #[error("Missing {} in the {db_name} database.", key.unwrap_or("key"))]
+    #[error("missing {} in the {db_name} database", key.unwrap_or("key"))]
     DatabaseMissingEntry { db_name: &'static str, key: Option<&'static str> },
-    #[error("Missing {key} in the fieldids weights mapping.")]
+    #[error("missing {key} in the fieldids weights mapping")]
     FieldidsWeightsMapMissingEntry { key: FieldId },
     #[error(transparent)]
     FieldIdMapMissingEntry(#[from] FieldIdMapMissingEntry),
-    #[error("Missing {key} in the field id mapping.")]
+    #[error("missing {key} in the field id mapping")]
     FieldIdMappingMissingEntry { key: FieldId },
     #[error(transparent)]
     Fst(#[from] fst::Error),
     #[error(transparent)]
     DocumentsError(#[from] documents::Error),
-    #[error("Invalid compression type have been specified to grenad")]
+    #[error("invalid compression type have been specified to grenad")]
     GrenadInvalidCompressionType,
-    #[error("Invalid grenad file with an invalid version format")]
+    #[error("invalid grenad file with an invalid version format")]
     GrenadInvalidFormatVersion,
-    #[error("Invalid merge while processing {process}")]
+    #[error("invalid merge while processing {process}")]
     IndexingMergingKeys { process: &'static str },
     #[error(transparent)]
     RayonThreadPool(#[from] ThreadPoolBuildError),
@@ -56,9 +57,15 @@ pub enum InternalError {
     #[error(transparent)]
     SerdeJson(#[from] serde_json::Error),
     #[error(transparent)]
+    BincodeError(#[from] bincode::Error),
+    #[error(transparent)]
     Serialization(#[from] SerializationError),
     #[error(transparent)]
     Store(#[from] MdbError),
+    #[error("Cannot delete {key:?} from database {database_name}: {error}")]
+    StoreDeletion { database_name: &'static str, key: BString, error: heed::Error },
+    #[error("Cannot insert {key:?} and value with length {value_length} into database {database_name}: {error}")]
+    StorePut { database_name: &'static str, key: BString, value_length: usize, error: heed::Error },
     #[error(transparent)]
     Utf8(#[from] str::Utf8Error),
     #[error("An indexation process was explicitly aborted")]
@@ -122,7 +129,7 @@ and can not be more than 512 bytes.", .document_id.to_string()
     #[error("The `_vectors` field in the document with id: `{document_id}` is not an object. Was expecting an object with a key for each embedder with manually provided vectors, but instead got `{value}`")]
     InvalidVectorsMapType { document_id: String, value: Value },
     #[error("Bad embedder configuration in the document with id: `{document_id}`. {error}")]
-    InvalidVectorsEmbedderConf { document_id: String, error: deserr::errors::JsonError },
+    InvalidVectorsEmbedderConf { document_id: String, error: String },
     #[error("{0}")]
     InvalidFilter(String),
     #[error("Invalid type for filter subexpression: expected: {}, found: {1}.", .0.join(", "))]

crates/milli/src/fields_ids_map.rs

@@ -4,6 +4,10 @@ use serde::{Deserialize, Serialize};
 
 use crate::FieldId;
 
+mod global;
+pub mod metadata;
+pub use global::GlobalFieldsIdsMap;
+
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct FieldsIdsMap {
     names_ids: BTreeMap<String, FieldId>,
@@ -95,6 +99,20 @@ impl crate::documents::FieldIdMapper for FieldsIdsMap {
     fn id(&self, name: &str) -> Option<FieldId> {
         self.id(name)
     }
+
+    fn name(&self, id: FieldId) -> Option<&str> {
+        self.name(id)
+    }
+}
+
+pub trait MutFieldIdMapper {
+    fn insert(&mut self, name: &str) -> Option<FieldId>;
+}
+
+impl MutFieldIdMapper for FieldsIdsMap {
+    fn insert(&mut self, name: &str) -> Option<FieldId> {
+        self.insert(name)
+    }
 }
 
 #[cfg(test)]

crates/milli/src/fields_ids_map/global.rs

@@ -0,0 +1,114 @@
+use std::collections::BTreeMap;
+use std::sync::RwLock;
+
+use super::metadata::{FieldIdMapWithMetadata, Metadata};
+use super::MutFieldIdMapper;
+use crate::FieldId;
+
+/// A fields ids map that can be globally updated to add fields
+#[derive(Debug, Clone)]
+pub struct GlobalFieldsIdsMap<'indexing> {
+    global: &'indexing RwLock<FieldIdMapWithMetadata>,
+    local: LocalFieldsIdsMap,
+}
+
+#[derive(Debug, Clone)]
+struct LocalFieldsIdsMap {
+    names_ids: BTreeMap<String, FieldId>,
+    ids_names: BTreeMap<FieldId, String>,
+    metadata: BTreeMap<FieldId, Metadata>,
+}
+
+impl LocalFieldsIdsMap {
+    fn new(global: &RwLock<FieldIdMapWithMetadata>) -> Self {
+        let global = global.read().unwrap();
+        Self {
+            names_ids: global.as_fields_ids_map().names_ids.clone(),
+            ids_names: global.as_fields_ids_map().ids_names.clone(),
+            metadata: global.iter_id_metadata().collect(),
+        }
+    }
+
+    fn insert(&mut self, name: &str, field_id: FieldId, metadata: Metadata) {
+        self.names_ids.insert(name.to_owned(), field_id);
+        self.ids_names.insert(field_id, name.to_owned());
+        self.metadata.insert(field_id, metadata);
+    }
+
+    fn name(&self, id: FieldId) -> Option<&str> {
+        self.ids_names.get(&id).map(String::as_str)
+    }
+
+    fn id(&self, name: &str) -> Option<FieldId> {
+        self.names_ids.get(name).copied()
+    }
+
+    fn id_with_metadata(&self, name: &str) -> Option<(FieldId, Metadata)> {
+        let id = self.id(name)?;
+        Some((id, self.metadata(id).unwrap()))
+    }
+
+    fn metadata(&self, id: FieldId) -> Option<Metadata> {
+        self.metadata.get(&id).copied()
+    }
+}
+
+impl<'indexing> GlobalFieldsIdsMap<'indexing> {
+    pub fn new(global: &'indexing RwLock<FieldIdMapWithMetadata>) -> Self {
+        Self { local: LocalFieldsIdsMap::new(global), global }
+    }
+
+    /// Returns the field id related to a field name, it will create a new field id if the
+    /// name is not already known. Returns `None` if the maximum field id as been reached.
+    pub fn id_or_insert(&mut self, name: &str) -> Option<FieldId> {
+        self.id_with_metadata_or_insert(name).map(|(fid, _meta)| fid)
+    }
+
+    pub fn id_with_metadata_or_insert(&mut self, name: &str) -> Option<(FieldId, Metadata)> {
+        if let Some(entry) = self.local.id_with_metadata(name) {
+            return Some(entry);
+        }
+
+        {
+            // optimistically lookup the global map
+            let global = self.global.read().unwrap();
+
+            if let Some((field_id, metadata)) = global.id_with_metadata(name) {
+                self.local.insert(name, field_id, metadata);
+                return Some((field_id, metadata));
+            }
+        }
+
+        {
+            let mut global = self.global.write().unwrap();
+
+            if let Some((field_id, metadata)) = global.id_with_metadata(name) {
+                self.local.insert(name, field_id, metadata);
+                return Some((field_id, metadata));
+            }
+
+            let field_id = global.insert(name)?;
+            let metadata = global.metadata(field_id).unwrap();
+            self.local.insert(name, field_id, metadata);
+            Some((field_id, metadata))
+        }
+    }
+
+    /// Get the name of a field based on its id.
+    pub fn name(&mut self, id: FieldId) -> Option<&str> {
+        if self.local.name(id).is_none() {
+            let global = self.global.read().unwrap();
+
+            let (name, metadata) = global.name_with_metadata(id)?;
+            self.local.insert(name, id, metadata);
+        }
+
+        self.local.name(id)
+    }
+}
+
+impl<'indexing> MutFieldIdMapper for GlobalFieldsIdsMap<'indexing> {
+    fn insert(&mut self, name: &str) -> Option<FieldId> {
+        self.id_or_insert(name)
+    }
+}

crates/milli/src/fields_ids_map/metadata.rs

@@ -0,0 +1,185 @@
+use std::collections::{BTreeMap, HashSet};
+use std::num::NonZeroU16;
+
+use charabia::Language;
+use heed::RoTxn;
+
+use super::FieldsIdsMap;
+use crate::{FieldId, Index, LocalizedAttributesRule, Result};
+
+#[derive(Debug, Clone, Copy)]
+pub struct Metadata {
+    pub searchable: bool,
+    pub filterable: bool,
+    pub sortable: bool,
+    localized_attributes_rule_id: Option<NonZeroU16>,
+}
+
+#[derive(Debug, Clone)]
+pub struct FieldIdMapWithMetadata {
+    fields_ids_map: FieldsIdsMap,
+    builder: MetadataBuilder,
+    metadata: BTreeMap<FieldId, Metadata>,
+}
+
+impl FieldIdMapWithMetadata {
+    pub fn new(existing_fields_ids_map: FieldsIdsMap, builder: MetadataBuilder) -> Self {
+        let metadata = existing_fields_ids_map
+            .iter()
+            .map(|(id, name)| (id, builder.metadata_for_field(name)))
+            .collect();
+        Self { fields_ids_map: existing_fields_ids_map, builder, metadata }
+    }
+
+    pub fn as_fields_ids_map(&self) -> &FieldsIdsMap {
+        &self.fields_ids_map
+    }
+
+    /// Returns the number of fields ids in the map.
+    pub fn len(&self) -> usize {
+        self.fields_ids_map.len()
+    }
+
+    /// Returns `true` if the map is empty.
+    pub fn is_empty(&self) -> bool {
+        self.fields_ids_map.is_empty()
+    }
+
+    /// Returns the field id related to a field name, it will create a new field id if the
+    /// name is not already known. Returns `None` if the maximum field id as been reached.
+    pub fn insert(&mut self, name: &str) -> Option<FieldId> {
+        let id = self.fields_ids_map.insert(name)?;
+        self.metadata.insert(id, self.builder.metadata_for_field(name));
+        Some(id)
+    }
+
+    /// Get the id of a field based on its name.
+    pub fn id(&self, name: &str) -> Option<FieldId> {
+        self.fields_ids_map.id(name)
+    }
+
+    pub fn id_with_metadata(&self, name: &str) -> Option<(FieldId, Metadata)> {
+        let id = self.fields_ids_map.id(name)?;
+        Some((id, self.metadata(id).unwrap()))
+    }
+
+    /// Get the name of a field based on its id.
+    pub fn name(&self, id: FieldId) -> Option<&str> {
+        self.fields_ids_map.name(id)
+    }
+
+    /// Get the name of a field based on its id.
+    pub fn name_with_metadata(&self, id: FieldId) -> Option<(&str, Metadata)> {
+        let name = self.fields_ids_map.name(id)?;
+        Some((name, self.metadata(id).unwrap()))
+    }
+
+    pub fn metadata(&self, id: FieldId) -> Option<Metadata> {
+        self.metadata.get(&id).copied()
+    }
+
+    /// Iterate over the ids and names in the ids order.
+    pub fn iter(&self) -> impl Iterator<Item = (FieldId, &str, Metadata)> {
+        self.fields_ids_map.iter().map(|(id, name)| (id, name, self.metadata(id).unwrap()))
+    }
+
+    pub fn iter_id_metadata(&self) -> impl Iterator<Item = (FieldId, Metadata)> + '_ {
+        self.metadata.iter().map(|(k, v)| (*k, *v))
+    }
+
+    pub fn iter_metadata(&self) -> impl Iterator<Item = Metadata> + '_ {
+        self.metadata.values().copied()
+    }
+
+    pub fn metadata_builder(&self) -> &MetadataBuilder {
+        &self.builder
+    }
+}
+
+impl Metadata {
+    pub fn locales<'rules>(
+        &self,
+        rules: &'rules [LocalizedAttributesRule],
+    ) -> Option<&'rules [Language]> {
+        let localized_attributes_rule_id = self.localized_attributes_rule_id?.get();
+        // - 1: `localized_attributes_rule_id` is NonZero
+        let rule = rules.get((localized_attributes_rule_id - 1) as usize).unwrap();
+        Some(rule.locales())
+    }
+}
+
+#[derive(Debug, Clone)]
+pub struct MetadataBuilder {
+    searchable_attributes: Vec<String>,
+    filterable_attributes: HashSet<String>,
+    sortable_attributes: HashSet<String>,
+    localized_attributes: Option<Vec<LocalizedAttributesRule>>,
+}
+
+impl MetadataBuilder {
+    pub fn from_index(index: &Index, rtxn: &RoTxn) -> Result<Self> {
+        let searchable_attributes =
+            index.searchable_fields(rtxn)?.into_iter().map(|s| s.to_string()).collect();
+        let filterable_attributes = index.filterable_fields(rtxn)?;
+        let sortable_attributes = index.sortable_fields(rtxn)?;
+        let localized_attributes = index.localized_attributes_rules(rtxn)?;
+
+        Ok(Self {
+            searchable_attributes,
+            filterable_attributes,
+            sortable_attributes,
+            localized_attributes,
+        })
+    }
+
+    pub fn new(
+        searchable_attributes: Vec<String>,
+        filterable_attributes: HashSet<String>,
+        sortable_attributes: HashSet<String>,
+        localized_attributes: Option<Vec<LocalizedAttributesRule>>,
+    ) -> Self {
+        Self {
+            searchable_attributes,
+            filterable_attributes,
+            sortable_attributes,
+            localized_attributes,
+        }
+    }
+
+    pub fn metadata_for_field(&self, field: &str) -> Metadata {
+        let searchable = self
+            .searchable_attributes
+            .iter()
+            .any(|attribute| attribute == "*" || attribute == field);
+
+        let filterable = self.filterable_attributes.contains(field);
+
+        let sortable = self.sortable_attributes.contains(field);
+
+        let localized_attributes_rule_id = self
+            .localized_attributes
+            .iter()
+            .flat_map(|v| v.iter())
+            .position(|rule| rule.match_str(field))
+            // saturating_add(1): make `id` `NonZero`
+            .map(|id| NonZeroU16::new(id.saturating_add(1).try_into().unwrap()).unwrap());
+
+        Metadata { searchable, filterable, sortable, localized_attributes_rule_id }
+    }
+
+    pub fn searchable_attributes(&self) -> &[String] {
+        self.searchable_attributes.as_slice()
+    }
+
+    pub fn sortable_attributes(&self) -> &HashSet<String> {
+        &self.sortable_attributes
+    }
+
+    pub fn filterable_attributes(&self) -> &HashSet<String> {
+        &self.filterable_attributes
+    }
+
+    pub fn localized_attributes_rules(&self) -> Option<&[LocalizedAttributesRule]> {
+        self.localized_attributes.as_deref()
+    }
+}

crates/milli/src/heed_codec/facet/mod.rs

@@ -97,7 +97,7 @@ impl<'a> heed::BytesEncode<'a> for FacetGroupValueCodec {
 
     fn bytes_encode(value: &'a Self::EItem) -> Result<Cow<'a, [u8]>, BoxedError> {
         let mut v = vec![value.size];
-        CboRoaringBitmapCodec::serialize_into(&value.bitmap, &mut v);
+        CboRoaringBitmapCodec::serialize_into_vec(&value.bitmap, &mut v);
         Ok(Cow::Owned(v))
     }
 }

crates/milli/src/heed_codec/facet/ordered_f64_codec.rs

@@ -27,17 +27,35 @@ impl heed::BytesEncode<'_> for OrderedF64Codec {
     fn bytes_encode(f: &Self::EItem) -> Result<Cow<'_, [u8]>, BoxedError> {
         let mut buffer = [0u8; 16];
 
-        // write the globally ordered float
-        let bytes = f64_into_bytes(*f).ok_or(InvalidGloballyOrderedFloatError { float: *f })?;
-        buffer[..8].copy_from_slice(&bytes[..]);
-        // Then the f64 value just to be able to read it back
-        let bytes = f.to_be_bytes();
-        buffer[8..16].copy_from_slice(&bytes[..]);
+        encode_f64_into_ordered_bytes(*f, &mut buffer)?;
 
         Ok(Cow::Owned(buffer.to_vec()))
     }
 }
 
+impl OrderedF64Codec {
+    pub fn serialize_into(
+        f: f64,
+        buffer: &mut [u8; 16],
+    ) -> Result<(), InvalidGloballyOrderedFloatError> {
+        encode_f64_into_ordered_bytes(f, buffer)
+    }
+}
+
+fn encode_f64_into_ordered_bytes(
+    f: f64,
+    buffer: &mut [u8; 16],
+) -> Result<(), InvalidGloballyOrderedFloatError> {
+    // write the globally ordered float
+    let bytes = f64_into_bytes(f).ok_or(InvalidGloballyOrderedFloatError { float: f })?;
+    buffer[..8].copy_from_slice(&bytes[..]);
+    // Then the f64 value just to be able to read it back
+    let bytes = f.to_be_bytes();
+    buffer[8..16].copy_from_slice(&bytes[..]);
+
+    Ok(())
+}
+
 #[derive(Error, Debug)]
 #[error("the float {float} cannot be converted to a globally ordered representation")]
 pub struct InvalidGloballyOrderedFloatError {

crates/milli/src/heed_codec/obkv_codec.rs

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

crates/milli/src/heed_codec/roaring_bitmap/cbo_roaring_bitmap_codec.rs

@@ -27,18 +27,27 @@ impl CboRoaringBitmapCodec {
         }
     }
 
-    pub fn serialize_into(roaring: &RoaringBitmap, vec: &mut Vec<u8>) {
+    pub fn serialize_into_vec(roaring: &RoaringBitmap, vec: &mut Vec<u8>) {
+        Self::serialize_into_writer(roaring, vec).unwrap()
+    }
+
+    pub fn serialize_into_writer<W: io::Write>(
+        roaring: &RoaringBitmap,
+        mut writer: W,
+    ) -> io::Result<()> {
         if roaring.len() <= THRESHOLD as u64 {
             // If the number of items (u32s) to encode is less than or equal to the threshold
             // it means that it would weigh the same or less than the RoaringBitmap
             // header, so we directly encode them using ByteOrder instead.
             for integer in roaring {
-                vec.write_u32::<NativeEndian>(integer).unwrap();
+                writer.write_u32::<NativeEndian>(integer)?;
             }
         } else {
             // Otherwise, we use the classic RoaringBitmapCodec that writes a header.
-            roaring.serialize_into(vec).unwrap();
+            roaring.serialize_into(writer)?;
         }
+
+        Ok(())
     }
 
     pub fn deserialize_from(mut bytes: &[u8]) -> io::Result<RoaringBitmap> {
@@ -122,7 +131,7 @@ impl CboRoaringBitmapCodec {
 
     /// Merges a DelAdd delta into a CboRoaringBitmap.
     pub fn merge_deladd_into<'a>(
-        deladd: KvReaderDelAdd<'_>,
+        deladd: &KvReaderDelAdd,
         previous: &[u8],
         buffer: &'a mut Vec<u8>,
     ) -> io::Result<Option<&'a [u8]>> {
@@ -143,7 +152,7 @@ impl CboRoaringBitmapCodec {
             return Ok(None);
         }
 
-        Self::serialize_into(&previous, buffer);
+        Self::serialize_into_vec(&previous, buffer);
         Ok(Some(&buffer[..]))
     }
 }
@@ -169,7 +178,7 @@ impl heed::BytesEncode<'_> for CboRoaringBitmapCodec {
 
     fn bytes_encode(item: &Self::EItem) -> Result<Cow<'_, [u8]>, BoxedError> {
         let mut vec = Vec::with_capacity(Self::serialized_size(item));
-        Self::serialize_into(item, &mut vec);
+        Self::serialize_into_vec(item, &mut vec);
         Ok(Cow::Owned(vec))
     }
 }

crates/milli/src/index.rs

@@ -70,6 +70,8 @@ pub mod main_key {
     pub const EMBEDDING_CONFIGS: &str = "embedding_configs";
     pub const SEARCH_CUTOFF: &str = "search_cutoff";
     pub const LOCALIZED_ATTRIBUTES_RULES: &str = "localized_attributes_rules";
+    pub const FACET_SEARCH: &str = "facet_search";
+    pub const PREFIX_SEARCH: &str = "prefix_search";
 }
 
 pub mod db_name {
@@ -1233,6 +1235,10 @@ impl Index {
         )
     }
 
+    pub(crate) fn delete_words_prefixes_fst(&self, wtxn: &mut RwTxn<'_>) -> heed::Result<bool> {
+        self.main.remap_key_type::<Str>().delete(wtxn, main_key::WORDS_PREFIXES_FST_KEY)
+    }
+
     /// Returns the FST which is the words prefixes dictionary of the engine.
     pub fn words_prefixes_fst<'t>(&self, rtxn: &'t RoTxn<'t>) -> Result<fst::Set<Cow<'t, [u8]>>> {
         match self.main.remap_types::<Str, Bytes>().get(rtxn, main_key::WORDS_PREFIXES_FST_KEY)? {
@@ -1251,12 +1257,20 @@ impl Index {
 
     /* documents */
 
+    /// Returns a document by using the document id.
+    pub fn document<'t>(&self, rtxn: &'t RoTxn, id: DocumentId) -> Result<&'t obkv::KvReaderU16> {
+        self.documents
+            .get(rtxn, &id)?
+            .ok_or(UserError::UnknownInternalDocumentId { document_id: id })
+            .map_err(Into::into)
+    }
+
     /// Returns an iterator over the requested documents. The next item will be an error if a document is missing.
     pub fn iter_documents<'a, 't: 'a>(
         &'a self,
         rtxn: &'t RoTxn<'t>,
         ids: impl IntoIterator<Item = DocumentId> + 'a,
-    ) -> Result<impl Iterator<Item = Result<(DocumentId, obkv::KvReaderU16<'t>)>> + 'a> {
+    ) -> Result<impl Iterator<Item = Result<(DocumentId, &'t obkv::KvReaderU16)>> + 'a> {
         Ok(ids.into_iter().map(move |id| {
             let kv = self
                 .documents
@@ -1271,7 +1285,7 @@ impl Index {
         &self,
         rtxn: &'t RoTxn<'t>,
         ids: impl IntoIterator<Item = DocumentId>,
-    ) -> Result<Vec<(DocumentId, obkv::KvReaderU16<'t>)>> {
+    ) -> Result<Vec<(DocumentId, &'t obkv::KvReaderU16)>> {
         self.iter_documents(rtxn, ids)?.collect()
     }
 
@@ -1279,7 +1293,7 @@ impl Index {
     pub fn all_documents<'a, 't: 'a>(
         &'a self,
         rtxn: &'t RoTxn<'t>,
-    ) -> Result<impl Iterator<Item = Result<(DocumentId, obkv::KvReaderU16<'t>)>> + 'a> {
+    ) -> Result<impl Iterator<Item = Result<(DocumentId, &'t obkv::KvReaderU16)>> + 'a> {
         self.iter_documents(rtxn, self.documents_ids(rtxn)?)
     }
 
@@ -1303,7 +1317,7 @@ impl Index {
         })?;
         Ok(self.iter_documents(rtxn, ids)?.map(move |entry| -> Result<_> {
             let (_docid, obkv) = entry?;
-            match primary_key.document_id(&obkv, &fields)? {
+            match primary_key.document_id(obkv, &fields)? {
                 Ok(document_id) => Ok(document_id),
                 Err(_) => Err(InternalError::DocumentsError(
                     crate::documents::Error::InvalidDocumentFormat,
@@ -1554,6 +1568,41 @@ impl Index {
         self.main.remap_key_type::<Str>().delete(txn, main_key::PROXIMITY_PRECISION)
     }
 
+    pub fn prefix_search(&self, txn: &RoTxn<'_>) -> heed::Result<Option<PrefixSearch>> {
+        self.main.remap_types::<Str, SerdeBincode<PrefixSearch>>().get(txn, main_key::PREFIX_SEARCH)
+    }
+
+    pub(crate) fn put_prefix_search(
+        &self,
+        txn: &mut RwTxn<'_>,
+        val: PrefixSearch,
+    ) -> heed::Result<()> {
+        self.main.remap_types::<Str, SerdeBincode<PrefixSearch>>().put(
+            txn,
+            main_key::PREFIX_SEARCH,
+            &val,
+        )
+    }
+
+    pub(crate) fn delete_prefix_search(&self, txn: &mut RwTxn<'_>) -> heed::Result<bool> {
+        self.main.remap_key_type::<Str>().delete(txn, main_key::PREFIX_SEARCH)
+    }
+
+    pub fn facet_search(&self, txn: &RoTxn<'_>) -> heed::Result<bool> {
+        self.main
+            .remap_types::<Str, SerdeBincode<bool>>()
+            .get(txn, main_key::FACET_SEARCH)
+            .map(|v| v.unwrap_or(true))
+    }
+
+    pub(crate) fn put_facet_search(&self, txn: &mut RwTxn<'_>, val: bool) -> heed::Result<()> {
+        self.main.remap_types::<Str, SerdeBincode<bool>>().put(txn, main_key::FACET_SEARCH, &val)
+    }
+
+    pub(crate) fn delete_facet_search(&self, txn: &mut RwTxn<'_>) -> heed::Result<bool> {
+        self.main.remap_key_type::<Str>().delete(txn, main_key::FACET_SEARCH)
+    }
+
     pub fn localized_attributes_rules(
         &self,
         rtxn: &RoTxn<'_>,
@@ -1638,6 +1687,11 @@ impl Index {
         }
         Ok(res)
     }
+
+    pub fn prefix_settings(&self, rtxn: &RoTxn<'_>) -> Result<PrefixSettings> {
+        let compute_prefixes = self.prefix_search(rtxn)?.unwrap_or_default();
+        Ok(PrefixSettings { compute_prefixes, max_prefix_length: 4, prefix_count_threshold: 100 })
+    }
 }
 
 #[derive(Debug, Deserialize, Serialize)]
@@ -1647,6 +1701,21 @@ pub struct IndexEmbeddingConfig {
     pub user_provided: RoaringBitmap,
 }
 
+#[derive(Debug, Deserialize, Serialize)]
+pub struct PrefixSettings {
+    pub prefix_count_threshold: usize,
+    pub max_prefix_length: usize,
+    pub compute_prefixes: PrefixSearch,
+}
+
+#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, Default)]
+#[serde(rename_all = "camelCase")]
+pub enum PrefixSearch {
+    #[default]
+    IndexingTime,
+    Disabled,
+}
+
 #[derive(Serialize, Deserialize)]
 #[serde(transparent)]
 struct OffsetDateTime(#[serde(with = "time::serde::rfc3339")] time::OffsetDateTime);
@@ -1657,19 +1726,24 @@ pub(crate) mod tests {
     use std::ops::Deref;
 
     use big_s::S;
+    use bumpalo::Bump;
     use heed::{EnvOpenOptions, RwTxn};
     use maplit::{btreemap, hashset};
+    use memmap2::Mmap;
     use tempfile::TempDir;
 
-    use crate::documents::DocumentsBatchReader;
     use crate::error::{Error, InternalError};
     use crate::index::{DEFAULT_MIN_WORD_LEN_ONE_TYPO, DEFAULT_MIN_WORD_LEN_TWO_TYPOS};
+    use crate::update::new::indexer;
+    use crate::update::settings::InnerIndexSettings;
     use crate::update::{
-        self, IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Setting,
-        Settings,
+        self, IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Setting, Settings,
     };
     use crate::vector::settings::{EmbedderSource, EmbeddingSettings};
-    use crate::{db_snap, obkv_to_json, Filter, Index, Search, SearchResult};
+    use crate::vector::EmbeddingConfigs;
+    use crate::{
+        db_snap, obkv_to_json, Filter, Index, Search, SearchResult, ThreadPoolNoAbortBuilder,
+    };
 
     pub(crate) struct TempIndex {
         pub inner: Index,
@@ -1702,35 +1776,68 @@ pub(crate) mod tests {
         pub fn new() -> Self {
             Self::new_with_map_size(4096 * 2000)
         }
-        pub fn add_documents_using_wtxn<'t, R>(
+
+        pub fn add_documents_using_wtxn<'t>(
             &'t self,
             wtxn: &mut RwTxn<'t>,
-            documents: DocumentsBatchReader<R>,
-        ) -> Result<(), crate::error::Error>
-        where
-            R: std::io::Read + std::io::Seek,
-        {
-            let builder = IndexDocuments::new(
-                wtxn,
-                self,
-                &self.indexer_config,
-                self.index_documents_config.clone(),
-                |_| (),
-                || false,
-            )
-            .unwrap();
-            let (builder, user_error) = builder.add_documents(documents).unwrap();
-            user_error?;
-            builder.execute()?;
+            documents: Mmap,
+        ) -> Result<(), crate::error::Error> {
+            let local_pool;
+            let indexer_config = &self.indexer_config;
+            let pool = match &indexer_config.thread_pool {
+                Some(pool) => pool,
+                None => {
+                    local_pool = ThreadPoolNoAbortBuilder::new().build().unwrap();
+                    &local_pool
+                }
+            };
+
+            let rtxn = self.inner.read_txn()?;
+            let db_fields_ids_map = self.inner.fields_ids_map(&rtxn)?;
+            let mut new_fields_ids_map = db_fields_ids_map.clone();
+
+            let embedders =
+                InnerIndexSettings::from_index(&self.inner, &rtxn, None)?.embedding_configs;
+            let mut indexer =
+                indexer::DocumentOperation::new(self.index_documents_config.update_method);
+            indexer.add_documents(&documents).unwrap();
+
+            let indexer_alloc = Bump::new();
+            let (document_changes, operation_stats, primary_key) = indexer.into_changes(
+                &indexer_alloc,
+                &self.inner,
+                &rtxn,
+                None,
+                &mut new_fields_ids_map,
+                &|| false,
+                &|_progress| (),
+            )?;
+
+            if let Some(error) = operation_stats.into_iter().find_map(|stat| stat.error) {
+                return Err(error.into());
+            }
+
+            pool.install(|| {
+                indexer::index(
+                    wtxn,
+                    &self.inner,
+                    &crate::ThreadPoolNoAbortBuilder::new().build().unwrap(),
+                    indexer_config.grenad_parameters(),
+                    &db_fields_ids_map,
+                    new_fields_ids_map,
+                    primary_key,
+                    &document_changes,
+                    embedders,
+                    &|| false,
+                    &|_| (),
+                )
+            })
+            .unwrap()?;
+
             Ok(())
         }
-        pub fn add_documents<R>(
-            &self,
-            documents: DocumentsBatchReader<R>,
-        ) -> Result<(), crate::error::Error>
-        where
-            R: std::io::Read + std::io::Seek,
-        {
+
+        pub fn add_documents(&self, documents: Mmap) -> Result<(), crate::error::Error> {
             let mut wtxn = self.write_txn().unwrap();
             self.add_documents_using_wtxn(&mut wtxn, documents)?;
             wtxn.commit().unwrap();
@@ -1746,6 +1853,7 @@ pub(crate) mod tests {
             wtxn.commit().unwrap();
             Ok(())
         }
+
         pub fn update_settings_using_wtxn<'t>(
             &'t self,
             wtxn: &mut RwTxn<'t>,
@@ -1761,25 +1869,69 @@ pub(crate) mod tests {
             &'t self,
             wtxn: &mut RwTxn<'t>,
             external_document_ids: Vec<String>,
-        ) {
-            let builder = IndexDocuments::new(
-                wtxn,
-                self,
-                &self.indexer_config,
-                self.index_documents_config.clone(),
-                |_| (),
-                || false,
-            )
-            .unwrap();
-            let (builder, user_error) = builder.remove_documents(external_document_ids).unwrap();
-            user_error.unwrap();
-            builder.execute().unwrap();
+        ) -> Result<(), crate::error::Error> {
+            let local_pool;
+            let indexer_config = &self.indexer_config;
+            let pool = match &indexer_config.thread_pool {
+                Some(pool) => pool,
+                None => {
+                    local_pool = ThreadPoolNoAbortBuilder::new().build().unwrap();
+                    &local_pool
+                }
+            };
+
+            let rtxn = self.inner.read_txn()?;
+            let db_fields_ids_map = self.inner.fields_ids_map(&rtxn)?;
+            let mut new_fields_ids_map = db_fields_ids_map.clone();
+
+            let embedders =
+                InnerIndexSettings::from_index(&self.inner, &rtxn, None)?.embedding_configs;
+
+            let mut indexer =
+                indexer::DocumentOperation::new(self.index_documents_config.update_method);
+            let external_document_ids: Vec<_> =
+                external_document_ids.iter().map(AsRef::as_ref).collect();
+            indexer.delete_documents(external_document_ids.as_slice());
+
+            let indexer_alloc = Bump::new();
+            let (document_changes, operation_stats, primary_key) = indexer.into_changes(
+                &indexer_alloc,
+                &self.inner,
+                &rtxn,
+                None,
+                &mut new_fields_ids_map,
+                &|| false,
+                &|_progress| (),
+            )?;
+
+            if let Some(error) = operation_stats.into_iter().find_map(|stat| stat.error) {
+                return Err(error.into());
+            }
+
+            pool.install(|| {
+                indexer::index(
+                    wtxn,
+                    &self.inner,
+                    &crate::ThreadPoolNoAbortBuilder::new().build().unwrap(),
+                    indexer_config.grenad_parameters(),
+                    &db_fields_ids_map,
+                    new_fields_ids_map,
+                    primary_key,
+                    &document_changes,
+                    embedders,
+                    &|| false,
+                    &|_| (),
+                )
+            })
+            .unwrap()?;
+
+            Ok(())
         }
 
         pub fn delete_documents(&self, external_document_ids: Vec<String>) {
             let mut wtxn = self.write_txn().unwrap();
 
-            self.delete_documents_using_wtxn(&mut wtxn, external_document_ids);
+            self.delete_documents_using_wtxn(&mut wtxn, external_document_ids).unwrap();
 
             wtxn.commit().unwrap();
         }
@@ -1796,29 +1948,64 @@ pub(crate) mod tests {
 
         let index = TempIndex::new();
         let mut wtxn = index.inner.write_txn().unwrap();
-
         let should_abort = AtomicBool::new(false);
-        let builder = IndexDocuments::new(
-            &mut wtxn,
-            &index.inner,
-            &index.indexer_config,
-            index.index_documents_config.clone(),
-            |_| (),
-            || should_abort.load(Relaxed),
-        )
-        .unwrap();
 
-        let (builder, user_error) = builder
-            .add_documents(documents!([
-                { "id": 1, "name": "kevin" },
-                { "id": 2, "name": "bob", "age": 20 },
-                { "id": 2, "name": "bob", "age": 20 },
-            ]))
+        let local_pool;
+        let indexer_config = &index.indexer_config;
+        let pool = match &indexer_config.thread_pool {
+            Some(pool) => pool,
+            None => {
+                local_pool = ThreadPoolNoAbortBuilder::new().build().unwrap();
+                &local_pool
+            }
+        };
+
+        let rtxn = index.inner.read_txn().unwrap();
+        let db_fields_ids_map = index.inner.fields_ids_map(&rtxn).unwrap();
+        let mut new_fields_ids_map = db_fields_ids_map.clone();
+
+        let embedders = EmbeddingConfigs::default();
+        let mut indexer = indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
+        let payload = documents!([
+            { "id": 1, "name": "kevin" },
+            { "id": 2, "name": "bob", "age": 20 },
+            { "id": 2, "name": "bob", "age": 20 },
+        ]);
+        indexer.add_documents(&payload).unwrap();
+
+        let indexer_alloc = Bump::new();
+        let (document_changes, _operation_stats, primary_key) = indexer
+            .into_changes(
+                &indexer_alloc,
+                &index.inner,
+                &rtxn,
+                None,
+                &mut new_fields_ids_map,
+                &|| false,
+                &|_progress| (),
+            )
             .unwrap();
-        user_error.unwrap();
 
         should_abort.store(true, Relaxed);
-        let err = builder.execute().unwrap_err();
+
+        let err = pool
+            .install(|| {
+                indexer::index(
+                    &mut wtxn,
+                    &index.inner,
+                    &crate::ThreadPoolNoAbortBuilder::new().build().unwrap(),
+                    indexer_config.grenad_parameters(),
+                    &db_fields_ids_map,
+                    new_fields_ids_map,
+                    primary_key,
+                    &document_changes,
+                    embedders,
+                    &|| should_abort.load(Relaxed),
+                    &|_| (),
+                )
+            })
+            .unwrap()
+            .unwrap_err();
 
         assert!(matches!(err, Error::InternalError(InternalError::AbortedIndexation)));
     }
@@ -2314,7 +2501,16 @@ pub(crate) mod tests {
 
         // And adding lots of documents afterwards instead of just one.
         // These extra subtests don't add much, but it's better than nothing.
-        index.add_documents(documents!([{ "primary_key": 38 }, { "primary_key": 39 }, { "primary_key": 41 }, { "primary_key": 40 }, { "primary_key": 41 }, { "primary_key": 42 }])).unwrap();
+        index
+            .add_documents(documents!([
+                { "primary_key": 38 },
+                { "primary_key": 39 },
+                { "primary_key": 41 },
+                { "primary_key": 40 },
+                { "primary_key": 41 },
+                { "primary_key": 42 },
+            ]))
+            .unwrap();
 
         db_snap!(index, documents_ids, @"[0, 1, 2, 3, 4, 5, ]");
         db_snap!(index, external_documents_ids, 7, @r###"
@@ -2701,7 +2897,7 @@ pub(crate) mod tests {
                 documents!({ "id" : "doggo", "_geo": { "lat": 1, "lng": 2, "doggo": "are the best" }}),
             )
             .unwrap_err();
-        insta::assert_snapshot!(err, @r###"The `_geo` field in the document with the id: `"\"doggo\""` contains the following unexpected fields: `{"doggo":"are the best"}`."###);
+        insta::assert_snapshot!(err, @r###"The `_geo` field in the document with the id: `"doggo"` contains the following unexpected fields: `{"doggo":"are the best"}`."###);
 
         db_snap!(index, geo_faceted_documents_ids); // ensure that no documents were inserted
 
@@ -2711,7 +2907,7 @@ pub(crate) mod tests {
                 documents!({ "id" : "doggo", "_geo": { "lat": 1, "lng": 2, "doggo": "are the best", "and": { "all": ["cats", { "are": "beautiful" } ] } } }),
             )
             .unwrap_err();
-        insta::assert_snapshot!(err, @r###"The `_geo` field in the document with the id: `"\"doggo\""` contains the following unexpected fields: `{"and":{"all":["cats",{"are":"beautiful"}]},"doggo":"are the best"}`."###);
+        insta::assert_snapshot!(err, @r###"The `_geo` field in the document with the id: `"doggo"` contains the following unexpected fields: `{"and":{"all":["cats",{"are":"beautiful"}]},"doggo":"are the best"}`."###);
 
         db_snap!(index, geo_faceted_documents_ids); // ensure that no documents were inserted
     }
@@ -2830,7 +3026,6 @@ pub(crate) mod tests {
         db_snap!(index, fields_ids_map, @r###"
         0   id               |
         1   _vectors         |
-        2   _vectors.doggo   |
         "###);
         db_snap!(index, searchable_fields, @r###"["id"]"###);
         db_snap!(index, fieldids_weights_map, @r###"

crates/milli/src/lib.rs

@@ -1,6 +1,7 @@
 #![cfg_attr(all(test, fuzzing), feature(no_coverage))]
 #![allow(clippy::type_complexity)]
 
+#[cfg(not(windows))]
 #[cfg(test)]
 #[global_allocator]
 pub static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
@@ -55,7 +56,7 @@ pub use self::error::{
 };
 pub use self::external_documents_ids::ExternalDocumentsIds;
 pub use self::fieldids_weights_map::FieldidsWeightsMap;
-pub use self::fields_ids_map::FieldsIdsMap;
+pub use self::fields_ids_map::{FieldsIdsMap, GlobalFieldsIdsMap};
 pub use self::heed_codec::{
     BEU16StrCodec, BEU32StrCodec, BoRoaringBitmapCodec, BoRoaringBitmapLenCodec,
     CboRoaringBitmapCodec, CboRoaringBitmapLenCodec, FieldIdWordCountCodec, ObkvCodec,
@@ -88,6 +89,7 @@ pub type Object = serde_json::Map<String, serde_json::Value>;
 pub type Position = u32;
 pub type RelativePosition = u16;
 pub type SmallString32 = smallstr::SmallString<[u8; 32]>;
+pub type Prefix = smallstr::SmallString<[u8; 16]>;
 pub type SmallVec16<T> = smallvec::SmallVec<[T; 16]>;
 pub type SmallVec32<T> = smallvec::SmallVec<[T; 32]>;
 pub type SmallVec8<T> = smallvec::SmallVec<[T; 8]>;
@@ -214,7 +216,7 @@ pub fn bucketed_position(relative: u16) -> u16 {
 pub fn obkv_to_json(
     displayed_fields: &[FieldId],
     fields_ids_map: &FieldsIdsMap,
-    obkv: obkv::KvReaderU16<'_>,
+    obkv: &obkv::KvReaderU16,
 ) -> Result<Object> {
     displayed_fields
         .iter()
@@ -232,10 +234,7 @@ pub fn obkv_to_json(
 }
 
 /// Transform every field of a raw obkv store into a JSON Object.
-pub fn all_obkv_to_json(
-    obkv: obkv::KvReaderU16<'_>,
-    fields_ids_map: &FieldsIdsMap,
-) -> Result<Object> {
+pub fn all_obkv_to_json(obkv: &obkv::KvReaderU16, fields_ids_map: &FieldsIdsMap) -> Result<Object> {
     let all_keys = obkv.iter().map(|(k, _v)| k).collect::<Vec<_>>();
     obkv_to_json(all_keys.as_slice(), fields_ids_map, obkv)
 }
@@ -434,7 +433,7 @@ mod tests {
         writer.insert(id1, b"1234").unwrap();
         writer.insert(id2, b"4321").unwrap();
         let contents = writer.into_inner().unwrap();
-        let obkv = obkv::KvReaderU16::new(&contents);
+        let obkv = obkv::KvReaderU16::from_slice(&contents);
 
         let expected = json!({
             "field1": 1234,

crates/milli/src/prompt/context.rs

@@ -3,23 +3,19 @@ use liquid::model::{
 };
 use liquid::{ObjectView, ValueView};
 
-use super::document::Document;
-use super::fields::Fields;
-use super::FieldsIdsMapWithMetadata;
-
 #[derive(Debug, Clone)]
-pub struct Context<'a> {
-    document: &'a Document<'a>,
-    fields: Fields<'a>,
+pub struct Context<'a, D: ObjectView, F: ArrayView> {
+    document: &'a D,
+    fields: &'a F,
 }
 
-impl<'a> Context<'a> {
-    pub fn new(document: &'a Document<'a>, field_id_map: &'a FieldsIdsMapWithMetadata<'a>) -> Self {
-        Self { document, fields: Fields::new(document, field_id_map) }
+impl<'a, D: ObjectView, F: ArrayView> Context<'a, D, F> {
+    pub fn new(document: &'a D, fields: &'a F) -> Self {
+        Self { document, fields }
     }
 }
 
-impl<'a> ObjectView for Context<'a> {
+impl<'a, D: ObjectView, F: ArrayView> ObjectView for Context<'a, D, F> {
     fn as_value(&self) -> &dyn ValueView {
         self
     }
@@ -56,7 +52,7 @@ impl<'a> ObjectView for Context<'a> {
     }
 }
 
-impl<'a> ValueView for Context<'a> {
+impl<'a, D: ObjectView, F: ArrayView> ValueView for Context<'a, D, F> {
     fn as_debug(&self) -> &dyn std::fmt::Debug {
         self
     }

crates/milli/src/prompt/document.rs

@@ -1,10 +1,15 @@
 use std::cell::OnceCell;
 use std::collections::BTreeMap;
+use std::fmt::{self, Debug};
 
+use bumpalo::Bump;
 use liquid::model::{
-    DisplayCow, KString, KStringCow, ObjectRender, ObjectSource, State, Value as LiquidValue,
+    ArrayView, DisplayCow, KString, KStringCow, ObjectRender, ObjectSource, ScalarCow, State,
+    Value as LiquidValue,
 };
 use liquid::{ObjectView, ValueView};
+use raw_collections::{RawMap, RawVec};
+use serde_json::value::RawValue;
 
 use crate::update::del_add::{DelAdd, KvReaderDelAdd};
 use crate::FieldsIdsMap;
@@ -30,13 +35,13 @@ impl ParsedValue {
 
 impl<'a> Document<'a> {
     pub fn new(
-        data: obkv::KvReaderU16<'a>,
+        data: &'a obkv::KvReaderU16,
         side: DelAdd,
         inverted_field_map: &'a FieldsIdsMap,
     ) -> Self {
         let mut out_data = BTreeMap::new();
         for (fid, raw) in data {
-            let obkv = KvReaderDelAdd::new(raw);
+            let obkv = KvReaderDelAdd::from_slice(raw);
             let Some(raw) = obkv.get(side) else {
                 continue;
             };
@@ -93,7 +98,7 @@ impl<'a> ObjectView for Document<'a> {
 }
 
 impl<'a> ValueView for Document<'a> {
-    fn as_debug(&self) -> &dyn std::fmt::Debug {
+    fn as_debug(&self) -> &dyn Debug {
         self
     }
 
@@ -128,4 +133,515 @@ impl<'a> ValueView for Document<'a> {
     fn as_object(&self) -> Option<&dyn ObjectView> {
         Some(self)
     }
+
+    fn is_object(&self) -> bool {
+        true
+    }
+}
+
+/// Implementation for any type that implements the Document trait
+use crate::update::new::document::Document as DocumentTrait;
+
+#[derive(Debug)]
+pub struct ParseableDocument<'doc, D> {
+    document: D,
+    doc_alloc: &'doc Bump,
+}
+
+impl<'doc, D> ParseableDocument<'doc, D> {
+    pub fn new(document: D, doc_alloc: &'doc Bump) -> Self {
+        Self { document, doc_alloc }
+    }
+}
+
+impl<'doc, D: DocumentTrait<'doc> + Debug> ObjectView for ParseableDocument<'doc, D> {
+    fn as_value(&self) -> &dyn ValueView {
+        self
+    }
+
+    fn size(&self) -> i64 {
+        self.document.top_level_fields_count() as i64
+    }
+
+    fn keys<'k>(&'k self) -> Box<dyn Iterator<Item = KStringCow<'k>> + 'k> {
+        Box::new(self.document.iter_top_level_fields().map(|res| {
+            let (field, _) = res.unwrap();
+            KStringCow::from_ref(field)
+        }))
+    }
+
+    fn values<'k>(&'k self) -> Box<dyn Iterator<Item = &'k dyn ValueView> + 'k> {
+        Box::new(self.document.iter_top_level_fields().map(|res| {
+            let (_, value) = res.unwrap();
+            ParseableValue::new_bump(value, self.doc_alloc) as _
+        }))
+    }
+
+    fn iter<'k>(&'k self) -> Box<dyn Iterator<Item = (KStringCow<'k>, &'k dyn ValueView)> + 'k> {
+        Box::new(self.document.iter_top_level_fields().map(|res| {
+            let (field, value) = res.unwrap();
+            (KStringCow::from_ref(field), ParseableValue::new_bump(value, self.doc_alloc) as _)
+        }))
+    }
+
+    fn contains_key(&self, index: &str) -> bool {
+        self.document.top_level_field(index).unwrap().is_some()
+    }
+
+    fn get<'s>(&'s self, index: &str) -> Option<&'s dyn ValueView> {
+        let s = self.document.top_level_field(index).unwrap()?;
+        Some(ParseableValue::new_bump(s, self.doc_alloc))
+    }
+}
+
+impl<'doc, D: DocumentTrait<'doc> + Debug> ValueView for ParseableDocument<'doc, D> {
+    fn as_debug(&self) -> &dyn fmt::Debug {
+        self
+    }
+    fn render(&self) -> liquid::model::DisplayCow<'_> {
+        DisplayCow::Owned(Box::new(ObjectRender::new(self)))
+    }
+
+    fn source(&self) -> liquid::model::DisplayCow<'_> {
+        DisplayCow::Owned(Box::new(ObjectSource::new(self)))
+    }
+
+    fn type_name(&self) -> &'static str {
+        "object"
+    }
+
+    fn query_state(&self, state: liquid::model::State) -> bool {
+        match state {
+            State::Truthy => true,
+            State::DefaultValue | State::Empty | State::Blank => false,
+        }
+    }
+
+    fn to_kstr(&self) -> liquid::model::KStringCow<'_> {
+        let s = ObjectRender::new(self).to_string();
+        KStringCow::from_string(s)
+    }
+
+    fn to_value(&self) -> LiquidValue {
+        LiquidValue::Object(
+            self.document
+                .iter_top_level_fields()
+                .map(|res| {
+                    let (k, v) = res.unwrap();
+                    (k.to_string().into(), ParseableValue::new(v, self.doc_alloc).to_value())
+                })
+                .collect(),
+        )
+    }
+
+    fn as_object(&self) -> Option<&dyn ObjectView> {
+        Some(self)
+    }
+
+    fn is_object(&self) -> bool {
+        true
+    }
+}
+
+#[derive(Debug)]
+struct ParseableValue<'doc> {
+    value: raw_collections::Value<'doc>,
+}
+
+impl<'doc> ParseableValue<'doc> {
+    pub fn new(value: &'doc RawValue, doc_alloc: &'doc Bump) -> Self {
+        let value = raw_collections::Value::from_raw_value(value, doc_alloc).unwrap();
+        Self { value }
+    }
+
+    pub fn new_bump(value: &'doc RawValue, doc_alloc: &'doc Bump) -> &'doc Self {
+        doc_alloc.alloc(Self::new(value, doc_alloc))
+    }
+}
+
+// transparent newtype for implementing ValueView
+#[repr(transparent)]
+#[derive(Debug)]
+struct ParseableMap<'doc>(RawMap<'doc>);
+
+// transparent newtype for implementing ValueView
+#[repr(transparent)]
+#[derive(Debug)]
+struct ParseableArray<'doc>(RawVec<'doc>);
+
+impl<'doc> ParseableMap<'doc> {
+    pub fn as_parseable<'a>(map: &'a RawMap<'doc>) -> &'a ParseableMap<'doc> {
+        // SAFETY: repr(transparent)
+        unsafe { &*(map as *const RawMap as *const Self) }
+    }
+}
+
+impl<'doc> ParseableArray<'doc> {
+    pub fn as_parseable<'a>(array: &'a RawVec<'doc>) -> &'a ParseableArray<'doc> {
+        // SAFETY: repr(transparent)
+        unsafe { &*(array as *const RawVec as *const Self) }
+    }
+}
+
+impl<'doc> ArrayView for ParseableArray<'doc> {
+    fn as_value(&self) -> &dyn ValueView {
+        self
+    }
+
+    fn size(&self) -> i64 {
+        self.0.len() as _
+    }
+
+    fn values<'k>(&'k self) -> Box<dyn Iterator<Item = &'k dyn ValueView> + 'k> {
+        Box::new(self.0.iter().map(|v| ParseableValue::new_bump(v, self.0.bump()) as _))
+    }
+
+    fn contains_key(&self, index: i64) -> bool {
+        let index = convert_index(index, self.size());
+        index < self.size() && index >= 0
+    }
+
+    fn get(&self, index: i64) -> Option<&dyn ValueView> {
+        let index = convert_index(index, self.size());
+        if index <= 0 {
+            return None;
+        }
+        let v = self.0.get(index as usize)?;
+        Some(ParseableValue::new_bump(v, self.0.bump()))
+    }
+}
+
+impl<'doc> ValueView for ParseableArray<'doc> {
+    fn as_debug(&self) -> &dyn std::fmt::Debug {
+        self
+    }
+
+    fn render(&self) -> DisplayCow<'_> {
+        DisplayCow::Owned(Box::new(ArrayRender { s: &self.0 }))
+    }
+
+    fn source(&self) -> DisplayCow<'_> {
+        DisplayCow::Owned(Box::new(ArraySource { s: &self.0 }))
+    }
+
+    fn type_name(&self) -> &'static str {
+        "array"
+    }
+
+    fn query_state(&self, state: State) -> bool {
+        match state {
+            State::Truthy => true,
+            State::DefaultValue | State::Empty | State::Blank => self.0.is_empty(),
+        }
+    }
+
+    fn to_kstr(&self) -> KStringCow<'_> {
+        let s = ArrayRender { s: &self.0 }.to_string();
+        KStringCow::from_string(s)
+    }
+
+    fn to_value(&self) -> LiquidValue {
+        LiquidValue::Array(self.values().map(|v| v.to_value()).collect())
+    }
+
+    fn is_array(&self) -> bool {
+        true
+    }
+
+    fn as_array(&self) -> Option<&dyn ArrayView> {
+        Some(self as _)
+    }
+}
+
+impl<'doc> ObjectView for ParseableMap<'doc> {
+    fn as_value(&self) -> &dyn ValueView {
+        self
+    }
+
+    fn size(&self) -> i64 {
+        self.0.len() as i64
+    }
+
+    fn keys<'k>(&'k self) -> Box<dyn Iterator<Item = KStringCow<'k>> + 'k> {
+        Box::new(self.0.keys().map(Into::into))
+    }
+
+    fn values<'k>(&'k self) -> Box<dyn Iterator<Item = &'k dyn ValueView> + 'k> {
+        Box::new(self.0.values().map(|value| {
+            let doc_alloc = self.0.bump();
+            ParseableValue::new_bump(value, doc_alloc) as _
+        }))
+    }
+
+    fn iter<'k>(&'k self) -> Box<dyn Iterator<Item = (KStringCow<'k>, &'k dyn ValueView)> + 'k> {
+        Box::new(self.0.iter().map(|(k, v)| {
+            let doc_alloc = self.0.bump();
+            (k.into(), ParseableValue::new_bump(v, doc_alloc) as _)
+        }))
+    }
+
+    fn contains_key(&self, index: &str) -> bool {
+        self.0.get(index).is_some()
+    }
+
+    fn get<'s>(&'s self, index: &str) -> Option<&'s dyn ValueView> {
+        let v = self.0.get(index)?;
+        let doc_alloc = self.0.bump();
+        let value = ParseableValue::new(v, doc_alloc);
+        Some(doc_alloc.alloc(value) as _)
+    }
+}
+
+impl<'doc> ValueView for ParseableMap<'doc> {
+    fn as_debug(&self) -> &dyn std::fmt::Debug {
+        self
+    }
+
+    fn render(&self) -> liquid::model::DisplayCow<'_> {
+        DisplayCow::Owned(Box::new(ObjectRender::new(self)))
+    }
+
+    fn source(&self) -> liquid::model::DisplayCow<'_> {
+        DisplayCow::Owned(Box::new(ObjectSource::new(self)))
+    }
+
+    fn type_name(&self) -> &'static str {
+        "object"
+    }
+
+    fn query_state(&self, state: liquid::model::State) -> bool {
+        match state {
+            State::Truthy => true,
+            State::DefaultValue | State::Empty | State::Blank => self.0.is_empty(),
+        }
+    }
+
+    fn to_kstr(&self) -> liquid::model::KStringCow<'_> {
+        let s = ObjectRender::new(self).to_string();
+        KStringCow::from_string(s)
+    }
+
+    fn to_value(&self) -> LiquidValue {
+        LiquidValue::Object(
+            self.0
+                .iter()
+                .map(|(k, v)| {
+                    (k.to_string().into(), ParseableValue::new(v, self.0.bump()).to_value())
+                })
+                .collect(),
+        )
+    }
+
+    fn as_object(&self) -> Option<&dyn ObjectView> {
+        Some(self)
+    }
+
+    fn is_object(&self) -> bool {
+        true
+    }
+}
+
+impl<'doc> ValueView for ParseableValue<'doc> {
+    fn as_debug(&self) -> &dyn Debug {
+        self
+    }
+
+    fn render(&self) -> DisplayCow<'_> {
+        use raw_collections::value::Number;
+        use raw_collections::Value;
+        match &self.value {
+            Value::Null => LiquidValue::Nil.render(),
+            Value::Bool(v) => v.render(),
+            Value::Number(number) => match number {
+                Number::PosInt(x) => DisplayCow::Borrowed(x),
+                Number::NegInt(x) => x.render(),
+                Number::Finite(x) => x.render(),
+            },
+            Value::String(s) => s.render(),
+            Value::Array(raw_vec) => ParseableArray::as_parseable(raw_vec).render(),
+            Value::Object(raw_map) => ParseableMap::as_parseable(raw_map).render(),
+        }
+    }
+
+    fn source(&self) -> DisplayCow<'_> {
+        use raw_collections::value::Number;
+        use raw_collections::Value;
+        match &self.value {
+            Value::Null => LiquidValue::Nil.source(),
+            Value::Bool(v) => ValueView::source(v),
+            Value::Number(number) => match number {
+                Number::PosInt(x) => DisplayCow::Borrowed(x),
+                Number::NegInt(x) => x.source(),
+                Number::Finite(x) => x.source(),
+            },
+            Value::String(s) => s.source(),
+            Value::Array(raw_vec) => ParseableArray::as_parseable(raw_vec).source(),
+            Value::Object(raw_map) => ParseableMap::as_parseable(raw_map).source(),
+        }
+    }
+
+    fn type_name(&self) -> &'static str {
+        use raw_collections::value::Number;
+        use raw_collections::Value;
+        match &self.value {
+            Value::Null => LiquidValue::Nil.type_name(),
+            Value::Bool(v) => v.type_name(),
+            Value::Number(number) => match number {
+                Number::PosInt(_x) => "whole positive number",
+                Number::NegInt(x) => x.type_name(),
+                Number::Finite(x) => x.type_name(),
+            },
+            Value::String(s) => s.type_name(),
+            Value::Array(_raw_vec) => "array",
+            Value::Object(_raw_map) => "object",
+        }
+    }
+
+    fn query_state(&self, state: State) -> bool {
+        use raw_collections::Value;
+        match &self.value {
+            Value::Null => ValueView::query_state(&LiquidValue::Nil, state),
+            Value::Bool(v) => ValueView::query_state(v, state),
+            Value::Number(_number) => match state {
+                State::Truthy => true,
+                State::DefaultValue => false,
+                State::Empty => false,
+                State::Blank => false,
+            },
+            Value::String(s) => ValueView::query_state(s, state),
+            Value::Array(raw_vec) => ParseableArray::as_parseable(raw_vec).query_state(state),
+            Value::Object(raw_map) => ParseableMap::as_parseable(raw_map).query_state(state),
+        }
+    }
+
+    fn to_kstr(&self) -> KStringCow<'_> {
+        use raw_collections::Value;
+        match &self.value {
+            Value::Null => ValueView::to_kstr(&LiquidValue::Nil),
+            Value::Bool(v) => ValueView::to_kstr(v),
+            Value::Number(_number) => self.render().to_string().into(),
+            Value::String(s) => KStringCow::from_ref(s),
+            Value::Array(raw_vec) => ParseableArray::as_parseable(raw_vec).to_kstr(),
+            Value::Object(raw_map) => ParseableMap::as_parseable(raw_map).to_kstr(),
+        }
+    }
+
+    fn to_value(&self) -> LiquidValue {
+        use raw_collections::Value;
+        match &self.value {
+            Value::Null => LiquidValue::Nil,
+            Value::Bool(v) => LiquidValue::Scalar(liquid::model::ScalarCow::new(*v)),
+            Value::Number(number) => match number {
+                raw_collections::value::Number::PosInt(number) => {
+                    let number: i64 = match (*number).try_into() {
+                        Ok(number) => number,
+                        Err(_) => {
+                            return LiquidValue::Scalar(ScalarCow::new(self.render().to_string()))
+                        }
+                    };
+                    LiquidValue::Scalar(ScalarCow::new(number))
+                }
+                raw_collections::value::Number::NegInt(number) => {
+                    LiquidValue::Scalar(ScalarCow::new(*number))
+                }
+                raw_collections::value::Number::Finite(number) => {
+                    LiquidValue::Scalar(ScalarCow::new(*number))
+                }
+            },
+            Value::String(s) => LiquidValue::Scalar(liquid::model::ScalarCow::new(s.to_string())),
+            Value::Array(raw_vec) => ParseableArray::as_parseable(raw_vec).to_value(),
+            Value::Object(raw_map) => ParseableMap::as_parseable(raw_map).to_value(),
+        }
+    }
+
+    fn as_scalar(&self) -> Option<liquid::model::ScalarCow<'_>> {
+        use raw_collections::value::Number;
+        use raw_collections::Value;
+        match &self.value {
+            Value::Bool(v) => Some(liquid::model::ScalarCow::new(*v)),
+            Value::Number(number) => match number {
+                Number::PosInt(number) => {
+                    let number: i64 = match (*number).try_into() {
+                        Ok(number) => number,
+                        Err(_) => return Some(ScalarCow::new(self.render().to_string())),
+                    };
+                    Some(ScalarCow::new(number))
+                }
+                Number::NegInt(number) => Some(ScalarCow::new(*number)),
+                Number::Finite(number) => Some(ScalarCow::new(*number)),
+            },
+            Value::String(s) => Some(ScalarCow::new(*s)),
+            _ => None,
+        }
+    }
+
+    fn is_scalar(&self) -> bool {
+        use raw_collections::Value;
+        matches!(&self.value, Value::Bool(_) | Value::Number(_) | Value::String(_))
+    }
+
+    fn as_array(&self) -> Option<&dyn liquid::model::ArrayView> {
+        if let raw_collections::Value::Array(array) = &self.value {
+            return Some(ParseableArray::as_parseable(array) as _);
+        }
+        None
+    }
+
+    fn is_array(&self) -> bool {
+        matches!(&self.value, raw_collections::Value::Array(_))
+    }
+
+    fn as_object(&self) -> Option<&dyn ObjectView> {
+        if let raw_collections::Value::Object(object) = &self.value {
+            return Some(ParseableMap::as_parseable(object) as _);
+        }
+        None
+    }
+
+    fn is_object(&self) -> bool {
+        matches!(&self.value, raw_collections::Value::Object(_))
+    }
+
+    fn is_nil(&self) -> bool {
+        matches!(&self.value, raw_collections::Value::Null)
+    }
+}
+
+struct ArraySource<'s, 'doc> {
+    s: &'s RawVec<'doc>,
+}
+
+impl<'s, 'doc> fmt::Display for ArraySource<'s, 'doc> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(f, "[")?;
+        for item in self.s {
+            let v = ParseableValue::new(item, self.s.bump());
+            write!(f, "{}, ", v.render())?;
+        }
+        write!(f, "]")?;
+        Ok(())
+    }
+}
+
+struct ArrayRender<'s, 'doc> {
+    s: &'s RawVec<'doc>,
+}
+
+impl<'s, 'doc> fmt::Display for ArrayRender<'s, 'doc> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        for item in self.s {
+            let v = ParseableValue::new(item, self.s.bump());
+
+            write!(f, "{}", v.render())?;
+        }
+        Ok(())
+    }
+}
+
+fn convert_index(index: i64, max_size: i64) -> i64 {
+    if 0 <= index {
+        index
+    } else {
+        max_size + index
+    }
 }

crates/milli/src/prompt/fields.rs

@@ -1,36 +1,23 @@
+use std::cell::RefCell;
+use std::fmt;
+
+use bumpalo::Bump;
 use liquid::model::{
     ArrayView, DisplayCow, KStringCow, ObjectRender, ObjectSource, State, Value as LiquidValue,
 };
 use liquid::{ObjectView, ValueView};
 
-use super::document::Document;
 use super::{FieldMetadata, FieldsIdsMapWithMetadata};
-#[derive(Debug, Clone)]
-pub struct Fields<'a>(Vec<FieldValue<'a>>);
-
-impl<'a> Fields<'a> {
-    pub fn new(document: &'a Document<'a>, field_id_map: &'a FieldsIdsMapWithMetadata<'a>) -> Self {
-        Self(
-            std::iter::repeat(document)
-                .zip(field_id_map.iter())
-                .map(|(document, (fid, name))| FieldValue {
-                    document,
-                    name,
-                    metadata: field_id_map.metadata(fid).unwrap_or_default(),
-                })
-                .collect(),
-        )
-    }
-}
+use crate::GlobalFieldsIdsMap;
 
 #[derive(Debug, Clone, Copy)]
-pub struct FieldValue<'a> {
+pub struct FieldValue<'a, D: ObjectView> {
     name: &'a str,
-    document: &'a Document<'a>,
+    document: &'a D,
     metadata: FieldMetadata,
 }
 
-impl<'a> ValueView for FieldValue<'a> {
+impl<'a, D: ObjectView> ValueView for FieldValue<'a, D> {
     fn as_debug(&self) -> &dyn std::fmt::Debug {
         self
     }
@@ -70,7 +57,7 @@ impl<'a> ValueView for FieldValue<'a> {
     }
 }
 
-impl<'a> FieldValue<'a> {
+impl<'a, D: ObjectView> FieldValue<'a, D> {
     pub fn name(&self) -> &&'a str {
         &self.name
     }
@@ -88,7 +75,7 @@ impl<'a> FieldValue<'a> {
     }
 }
 
-impl<'a> ObjectView for FieldValue<'a> {
+impl<'a, D: ObjectView> ObjectView for FieldValue<'a, D> {
     fn as_value(&self) -> &dyn ValueView {
         self
     }
@@ -127,7 +114,42 @@ impl<'a> ObjectView for FieldValue<'a> {
     }
 }
 
-impl<'a> ArrayView for Fields<'a> {
+#[derive(Debug, Clone)]
+pub struct OwnedFields<'a, D: ObjectView>(Vec<FieldValue<'a, D>>);
+
+#[derive(Debug)]
+pub struct BorrowedFields<'a, 'map, D: ObjectView> {
+    document: &'a D,
+    field_id_map: &'a RefCell<GlobalFieldsIdsMap<'map>>,
+    doc_alloc: &'a Bump,
+}
+
+impl<'a, D: ObjectView> OwnedFields<'a, D> {
+    pub fn new(document: &'a D, field_id_map: &'a FieldsIdsMapWithMetadata<'a>) -> Self {
+        Self(
+            std::iter::repeat(document)
+                .zip(field_id_map.iter())
+                .map(|(document, (fid, name))| FieldValue {
+                    document,
+                    name,
+                    metadata: field_id_map.metadata(fid).unwrap_or_default(),
+                })
+                .collect(),
+        )
+    }
+}
+
+impl<'a, 'map, D: ObjectView> BorrowedFields<'a, 'map, D> {
+    pub fn new(
+        document: &'a D,
+        field_id_map: &'a RefCell<GlobalFieldsIdsMap<'map>>,
+        doc_alloc: &'a Bump,
+    ) -> Self {
+        Self { document, field_id_map, doc_alloc }
+    }
+}
+
+impl<'a, D: ObjectView> ArrayView for OwnedFields<'a, D> {
     fn as_value(&self) -> &dyn ValueView {
         self.0.as_value()
     }
@@ -149,7 +171,91 @@ impl<'a> ArrayView for Fields<'a> {
     }
 }
 
-impl<'a> ValueView for Fields<'a> {
+impl<'a, 'map, D: ObjectView> ArrayView for BorrowedFields<'a, 'map, D> {
+    fn as_value(&self) -> &dyn ValueView {
+        self
+    }
+
+    fn size(&self) -> i64 {
+        self.document.size()
+    }
+
+    fn values<'k>(&'k self) -> Box<dyn Iterator<Item = &'k dyn ValueView> + 'k> {
+        Box::new(self.document.keys().map(|k| {
+            let mut field_id_map = self.field_id_map.borrow_mut();
+            let (_, metadata) = field_id_map.id_with_metadata_or_insert(&k).unwrap();
+            let fv = self.doc_alloc.alloc(FieldValue {
+                name: self.doc_alloc.alloc_str(&k),
+                document: self.document,
+                metadata: FieldMetadata { searchable: metadata.searchable },
+            });
+            fv as _
+        }))
+    }
+
+    fn contains_key(&self, index: i64) -> bool {
+        let index = if index >= 0 { index } else { self.size() + index };
+        index >= 0 && index < self.size()
+    }
+
+    fn get(&self, index: i64) -> Option<&dyn ValueView> {
+        let index = if index >= 0 { index } else { self.size() + index };
+        let index: usize = index.try_into().ok()?;
+        let key = self.document.keys().nth(index)?;
+        let mut field_id_map = self.field_id_map.borrow_mut();
+        let (_, metadata) = field_id_map.id_with_metadata_or_insert(&key)?;
+        let fv = self.doc_alloc.alloc(FieldValue {
+            name: self.doc_alloc.alloc_str(&key),
+            document: self.document,
+            metadata: FieldMetadata { searchable: metadata.searchable },
+        });
+        Some(fv as _)
+    }
+}
+
+impl<'a, 'map, D: ObjectView> ValueView for BorrowedFields<'a, 'map, D> {
+    fn as_debug(&self) -> &dyn std::fmt::Debug {
+        self
+    }
+
+    fn render(&self) -> liquid::model::DisplayCow<'_> {
+        DisplayCow::Owned(Box::new(ArrayRender { s: self }))
+    }
+
+    fn source(&self) -> liquid::model::DisplayCow<'_> {
+        DisplayCow::Owned(Box::new(ArraySource { s: self }))
+    }
+
+    fn type_name(&self) -> &'static str {
+        "array"
+    }
+
+    fn query_state(&self, state: liquid::model::State) -> bool {
+        match state {
+            State::Truthy => true,
+            State::DefaultValue | State::Empty | State::Blank => self.document.size() == 0,
+        }
+    }
+
+    fn to_kstr(&self) -> liquid::model::KStringCow<'_> {
+        let s = ArrayRender { s: self }.to_string();
+        KStringCow::from_string(s)
+    }
+
+    fn to_value(&self) -> LiquidValue {
+        LiquidValue::Array(self.values().map(|v| v.to_value()).collect())
+    }
+
+    fn as_array(&self) -> Option<&dyn ArrayView> {
+        Some(self)
+    }
+
+    fn is_array(&self) -> bool {
+        true
+    }
+}
+
+impl<'a, D: ObjectView> ValueView for OwnedFields<'a, D> {
     fn as_debug(&self) -> &dyn std::fmt::Debug {
         self
     }
@@ -182,3 +288,31 @@ impl<'a> ValueView for Fields<'a> {
         Some(self)
     }
 }
+
+struct ArraySource<'a, 'map, D: ObjectView> {
+    s: &'a BorrowedFields<'a, 'map, D>,
+}
+
+impl<'a, 'map, D: ObjectView> fmt::Display for ArraySource<'a, 'map, D> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(f, "[")?;
+        for item in self.s.values() {
+            write!(f, "{}, ", item.render())?;
+        }
+        write!(f, "]")?;
+        Ok(())
+    }
+}
+
+struct ArrayRender<'a, 'map, D: ObjectView> {
+    s: &'a BorrowedFields<'a, 'map, D>,
+}
+
+impl<'a, 'map, D: ObjectView> fmt::Display for ArrayRender<'a, 'map, D> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        for item in self.s.values() {
+            write!(f, "{}", item.render())?;
+        }
+        Ok(())
+    }
+}