dnrops
/
meilisearch
mirror of https://github.com/meilisearch/meilisearch.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'main' into indexer-edition-2024

This commit is contained in:
ManyTheFish 2024-09-25 07:37:32 +02:00
parent 7ad037841f 7f20c13f3f
commit 974272f2e9
94 changed files with 8510 additions and 4616 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
Cargo.lock generated
View File

@ -387,14 +387,14 @@ checksum = "96d30a06541fbafbc7f82ed10c06164cfbd2c401138f6addd8404629c4b16711"
[[package]]
name = "arroy"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2ece9e5347e7fdaaea3181dec7f916677ad5f3fcbac183648ce1924eb4aeef9a"
source = "git+https://github.com/meilisearch/arroy/?rev=2386594dfb009ce08821a925ccc89fb8e30bf73d#2386594dfb009ce08821a925ccc89fb8e30bf73d"
dependencies = [
"bytemuck",
"byteorder",
"heed",
"log",
"memmap2",
"nohash",
"ordered-float",
"rand",
"rayon",
@ -471,7 +471,7 @@ checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
[[package]]
name = "benchmarks"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"anyhow",
"bytes",
@ -652,7 +652,7 @@ dependencies = [
[[package]]
name = "build-info"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"anyhow",
"time",
@ -1621,7 +1621,7 @@ dependencies = [
[[package]]
name = "dump"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"anyhow",
"big_s",
@ -1833,7 +1833,7 @@ checksum = "9fc0510504f03c51ada170672ac806f1f105a88aa97a5281117e1ddc3368e51a"
[[package]]
name = "file-store"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"tempfile",
"thiserror",
@ -1855,7 +1855,7 @@ dependencies = [
[[package]]
name = "filter-parser"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"insta",
"nom",
@ -1875,7 +1875,7 @@ dependencies = [
[[package]]
name = "flatten-serde-json"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"criterion",
"serde_json",
@ -1999,7 +1999,7 @@ dependencies = [
[[package]]
name = "fuzzers"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"arbitrary",
"clap",
@ -2551,7 +2551,7 @@ checksum = "206ca75c9c03ba3d4ace2460e57b189f39f43de612c2f85836e65c929701bb2d"
[[package]]
name = "index-scheduler"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"anyhow",
"arroy",
@ -2745,7 +2745,7 @@ dependencies = [
[[package]]
name = "json-depth-checker"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"criterion",
"serde_json",
@ -3373,7 +3373,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
[[package]]
name = "meili-snap"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"insta",
"md5",
@ -3382,7 +3382,7 @@ dependencies = [
[[package]]
name = "meilisearch"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"actix-cors",
"actix-http",
@ -3471,7 +3471,7 @@ dependencies = [
[[package]]
name = "meilisearch-auth"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"base64 0.22.1",
"enum-iterator",
@ -3490,7 +3490,7 @@ dependencies = [
[[package]]
name = "meilisearch-types"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"actix-web",
"anyhow",
@ -3520,7 +3520,7 @@ dependencies = [
[[package]]
name = "meilitool"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"anyhow",
"clap",
@ -3528,6 +3528,7 @@ dependencies = [
"file-store",
"meilisearch-auth",
"meilisearch-types",
"serde",
"time",
"uuid",
]
@ -3550,7 +3551,7 @@ dependencies = [
[[package]]
name = "milli"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"arroy",
"big_s",
@ -3694,6 +3695,12 @@ version = "0.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6d02c0b00610773bb7fc61d85e13d86c7858cbdf00e1a120bfc41bc055dbaa0e"
[[package]]
name = "nohash"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a0f889fb66f7acdf83442c35775764b51fed3c606ab9cee51500dbde2cf528ca"
[[package]]
name = "nom"
version = "7.1.3"
@ -3984,7 +3991,7 @@ checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
[[package]]
name = "permissive-json-pointer"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"big_s",
"serde_json",
@ -4841,9 +4848,9 @@ checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
[[package]]
name = "serde"
version = "1.0.204"
version = "1.0.210"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bc76f558e0cbb2a839d37354c575f1dc3fdc6546b5be373ba43d95f231bf7c12"
checksum = "c8e3592472072e6e22e0a54d5904d9febf8508f65fb8552499a1abc7d1078c3a"
dependencies = [
"serde_derive",
]
@ -4859,9 +4866,9 @@ dependencies = [
[[package]]
name = "serde_derive"
version = "1.0.204"
version = "1.0.210"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e0cd7e117be63d3c3678776753929474f3b04a43a080c744d6b0ae2a8c28e222"
checksum = "243902eda00fad750862fc144cea25caca5e20d615af0a81bee94ca738f1df1f"
dependencies = [
"proc-macro2",
"quote",
@ -6368,7 +6375,7 @@ dependencies = [
[[package]]
name = "xtask"
version = "1.10.0"
version = "1.11.0"
dependencies = [
"anyhow",
"build-info",

2
Cargo.toml
View File

@ -22,7 +22,7 @@ members = [
]
[workspace.package]
version = "1.10.0"
version = "1.11.0"
authors = [
"Quentin de Quelen <quentin@dequelen.me>",
"Clément Renault <clement@meilisearch.com>",

6
README.md
View File

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

2
dump/src/reader/mod.rs
View File

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

829
dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-5.snap
View File

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

1553
dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-6.snap
View File

File diff suppressed because it is too large Load Diff

1541
dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-7.snap
View File

File diff suppressed because it is too large Load Diff

1549
dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-8.snap
View File

File diff suppressed because it is too large Load Diff

780
dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-9.snap Normal file
View File

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

29
filter-parser/src/condition.rs
View File

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

2
filter-parser/src/error.rs
View File

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

41
filter-parser/src/lib.rs
View File

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

2
filter-parser/src/value.rs
View File

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

2
index-scheduler/Cargo.toml
View File

@ -41,7 +41,7 @@ ureq = "2.10.0"
uuid = { version = "1.10.0", features = ["serde", "v4"] }
[dev-dependencies]
arroy = "0.4.0"
arroy = { git = "https://github.com/meilisearch/arroy/", rev = "2386594dfb009ce08821a925ccc89fb8e30bf73d" }
big_s = "1.0.2"
crossbeam = "0.8.4"
insta = { version = "1.39.0", features = ["json", "redactions"] }

146
index-scheduler/src/autobatcher.rs
View File

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

228
index-scheduler/src/batch.rs
View File

@ -113,9 +113,9 @@ pub(crate) enum IndexOperation {
index_uid: String,
task: Task,
},
IndexDocumentDeletionByFilter {
DocumentDeletion {
index_uid: String,
task: Task,
tasks: Vec<Task>,
},
DocumentClear {
index_uid: String,
@ -168,11 +168,11 @@ impl Batch {
Batch::IndexOperation { op, .. } => match op {
IndexOperation::DocumentOperation { tasks, .. }
| IndexOperation::Settings { tasks, .. }
| IndexOperation::DocumentDeletion { tasks, .. }
| IndexOperation::DocumentClear { tasks, .. } => {
RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
}
IndexOperation::DocumentEdition { task, .. }
| IndexOperation::IndexDocumentDeletionByFilter { task, .. } => {
IndexOperation::DocumentEdition { task, .. } => {
RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
}
IndexOperation::SettingsAndDocumentOperation {
@ -237,7 +237,7 @@ impl IndexOperation {
match self {
IndexOperation::DocumentOperation { index_uid, .. }
| IndexOperation::DocumentEdition { index_uid, .. }
| IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
| IndexOperation::DocumentDeletion { index_uid, .. }
| IndexOperation::DocumentClear { index_uid, .. }
| IndexOperation::Settings { index_uid, .. }
| IndexOperation::DocumentClearAndSetting { index_uid, .. }
@ -255,8 +255,8 @@ impl fmt::Display for IndexOperation {
IndexOperation::DocumentEdition { .. } => {
f.write_str("IndexOperation::DocumentEdition")
}
IndexOperation::IndexDocumentDeletionByFilter { .. } => {
f.write_str("IndexOperation::IndexDocumentDeletionByFilter")
IndexOperation::DocumentDeletion { .. } => {
f.write_str("IndexOperation::DocumentDeletion")
}
IndexOperation::DocumentClear { .. } => f.write_str("IndexOperation::DocumentClear"),
IndexOperation::Settings { .. } => f.write_str("IndexOperation::Settings"),
@ -292,21 +292,6 @@ impl IndexScheduler {
},
must_create_index,
})),
BatchKind::DocumentDeletionByFilter { id } => {
let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
match &task.kind {
KindWithContent::DocumentDeletionByFilter { index_uid, .. } => {
Ok(Some(Batch::IndexOperation {
op: IndexOperation::IndexDocumentDeletionByFilter {
index_uid: index_uid.clone(),
task,
},
must_create_index: false,
}))
}
_ => unreachable!(),
}
}
BatchKind::DocumentEdition { id } => {
let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
match &task.kind {
@ -369,30 +354,11 @@ impl IndexScheduler {
must_create_index,
}))
}
BatchKind::DocumentDeletion { deletion_ids } => {
BatchKind::DocumentDeletion { deletion_ids, includes_by_filter: _ } => {
let tasks = self.get_existing_tasks(rtxn, deletion_ids)?;
let mut operations = Vec::with_capacity(tasks.len());
let mut documents_counts = Vec::with_capacity(tasks.len());
for task in &tasks {
match task.kind {
KindWithContent::DocumentDeletion { ref documents_ids, .. } => {
operations.push(DocumentOperation::Delete(documents_ids.clone()));
documents_counts.push(documents_ids.len() as u64);
}
_ => unreachable!(),
}
}
Ok(Some(Batch::IndexOperation {
op: IndexOperation::DocumentOperation {
index_uid,
primary_key: None,
method: IndexDocumentsMethod::ReplaceDocuments,
documents_counts,
operations,
tasks,
},
op: IndexOperation::DocumentDeletion { index_uid, tasks },
must_create_index,
}))
}
@ -1430,7 +1396,7 @@ impl IndexScheduler {
{
(original_filter, context, function)
} else {
// In the case of a `documentDeleteByFilter` the details MUST be set
// In the case of a `documentEdition` the details MUST be set
unreachable!();
};
@ -1460,52 +1426,102 @@ impl IndexScheduler {
Ok(vec![task])
}
IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
let filter =
if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
&task.kind
{
filter_expr
} else {
unreachable!()
};
let deleted_documents = delete_document_by_filter(
index_wtxn,
filter,
self.index_mapper.indexer_config(),
self.must_stop_processing.clone(),
index,
);
let original_filter = if let Some(Details::DocumentDeletionByFilter {
original_filter,
deleted_documents: _,
}) = task.details
{
original_filter
} else {
// In the case of a `documentDeleteByFilter` the details MUST be set
unreachable!();
};
IndexOperation::DocumentDeletion { mut tasks, index_uid: _ } => {
let mut to_delete = RoaringBitmap::new();
let external_documents_ids = index.external_documents_ids();
match deleted_documents {
Ok(deleted_documents) => {
task.status = Status::Succeeded;
task.details = Some(Details::DocumentDeletionByFilter {
original_filter,
deleted_documents: Some(deleted_documents),
});
}
Err(e) => {
task.status = Status::Failed;
task.details = Some(Details::DocumentDeletionByFilter {
original_filter,
deleted_documents: Some(0),
});
task.error = Some(e.into());
for task in tasks.iter_mut() {
let before = to_delete.len();
task.status = Status::Succeeded;
match &task.kind {
KindWithContent::DocumentDeletion { index_uid: _, documents_ids } => {
for id in documents_ids {
if let Some(id) = external_documents_ids.get(index_wtxn, id)? {
to_delete.insert(id);
}
}
let will_be_removed = to_delete.len() - before;
task.details = Some(Details::DocumentDeletion {
provided_ids: documents_ids.len(),
deleted_documents: Some(will_be_removed),
});
}
KindWithContent::DocumentDeletionByFilter { index_uid: _, filter_expr } => {
let before = to_delete.len();
let filter = match Filter::from_json(filter_expr) {
Ok(filter) => filter,
Err(err) => {
// theorically, this should be catched by deserr before reaching the index-scheduler and cannot happens
task.status = Status::Failed;
task.error = match err {
milli::Error::UserError(
milli::UserError::InvalidFilterExpression { .. },
) => Some(
Error::from(err)
.with_custom_error_code(Code::InvalidDocumentFilter)
.into(),
),
e => Some(e.into()),
};
None
}
};
if let Some(filter) = filter {
let candidates =
filter.evaluate(index_wtxn, index).map_err(|err| match err {
milli::Error::UserError(
milli::UserError::InvalidFilter(_),
) => Error::from(err)
.with_custom_error_code(Code::InvalidDocumentFilter),
e => e.into(),
});
match candidates {
Ok(candidates) => to_delete |= candidates,
Err(err) => {
task.status = Status::Failed;
task.error = Some(err.into());
}
};
}
let will_be_removed = to_delete.len() - before;
if let Some(Details::DocumentDeletionByFilter {
original_filter: _,
deleted_documents,
}) = &mut task.details
{
*deleted_documents = Some(will_be_removed);
} else {
// In the case of a `documentDeleteByFilter` the details MUST be set
unreachable!()
}
}
_ => unreachable!(),
}
}
Ok(vec![task])
let config = IndexDocumentsConfig {
update_method: IndexDocumentsMethod::ReplaceDocuments,
..Default::default()
};
let must_stop_processing = self.must_stop_processing.clone();
let mut builder = milli::update::IndexDocuments::new(
index_wtxn,
index,
self.index_mapper.indexer_config(),
config,
|indexing_step| tracing::debug!(update = ?indexing_step),
|| must_stop_processing.get(),
)?;
let (new_builder, _count) =
builder.remove_documents_from_db_no_batch(&to_delete)?;
builder = new_builder;
let _ = builder.execute()?;
Ok(tasks)
}
IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
let indexer_config = self.index_mapper.indexer_config();
@ -1709,46 +1725,6 @@ impl IndexScheduler {
}
}
fn delete_document_by_filter<'a>(
wtxn: &mut RwTxn<'a>,
filter: &serde_json::Value,
indexer_config: &IndexerConfig,
must_stop_processing: MustStopProcessing,
index: &'a Index,
) -> Result<u64> {
let filter = Filter::from_json(filter)?;
Ok(if let Some(filter) = filter {
let candidates = filter.evaluate(wtxn, index).map_err(|err| match err {
milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
}
e => e.into(),
})?;
let config = IndexDocumentsConfig {
update_method: IndexDocumentsMethod::ReplaceDocuments,
..Default::default()
};
let mut builder = milli::update::IndexDocuments::new(
wtxn,
index,
indexer_config,
config,
|indexing_step| tracing::debug!(update = ?indexing_step),
|| must_stop_processing.get(),
)?;
let (new_builder, count) = builder.remove_documents_from_db_no_batch(&candidates)?;
builder = new_builder;
let _ = builder.execute()?;
count
} else {
0
})
}
fn edit_documents_by_function<'a>(
wtxn: &mut RwTxn<'a>,
filter: &Option<serde_json::Value>,

2
index-scheduler/src/features.rs
View File

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

163
index-scheduler/src/lib.rs
View File

@ -1477,7 +1477,7 @@ impl IndexScheduler {
.map(
|IndexEmbeddingConfig {
name,
config: milli::vector::EmbeddingConfig { embedder_options, prompt },
config: milli::vector::EmbeddingConfig { embedder_options, prompt, quantized },
..
}| {
let prompt =
@ -1486,7 +1486,10 @@ impl IndexScheduler {
{
let embedders = self.embedders.read().unwrap();
if let Some(embedder) = embedders.get(&embedder_options) {
return Ok((name, (embedder.clone(), prompt)));
return Ok((
name,
(embedder.clone(), prompt, quantized.unwrap_or_default()),
));
}
}
@ -1500,7 +1503,7 @@ impl IndexScheduler {
let mut embedders = self.embedders.write().unwrap();
embedders.insert(embedder_options, embedder.clone());
}
Ok((name, (embedder, prompt)))
Ok((name, (embedder, prompt, quantized.unwrap_or_default())))
},
)
.collect();
@ -1764,6 +1767,7 @@ mod tests {
use crossbeam::channel::RecvTimeoutError;
use file_store::File;
use insta::assert_json_snapshot;
use maplit::btreeset;
use meili_snap::{json_string, snapshot};
use meilisearch_auth::AuthFilter;
use meilisearch_types::document_formats::DocumentFormatError;
@ -2553,6 +2557,117 @@ mod tests {
snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents");
}
#[test]
fn fail_in_process_batch_for_document_deletion() {
let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
use meilisearch_types::settings::{Settings, Unchecked};
let mut new_settings: Box<Settings<Unchecked>> = Box::default();
new_settings.filterable_attributes = Setting::Set(btreeset!(S("catto")));
index_scheduler
.register(
KindWithContent::SettingsUpdate {
index_uid: S("doggos"),
new_settings,
is_deletion: false,
allow_index_creation: true,
},
None,
false,
)
.unwrap();
let content = r#"[
{ "id": 1, "doggo": "jean bob" },
{ "id": 2, "catto": "jorts" },
{ "id": 3, "doggo": "bork" }
]"#;
let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap();
let documents_count = read_json(content.as_bytes(), &mut file).unwrap();
file.persist().unwrap();
index_scheduler
.register(
KindWithContent::DocumentAdditionOrUpdate {
index_uid: S("doggos"),
primary_key: Some(S("id")),
method: ReplaceDocuments,
content_file: uuid,
documents_count,
allow_index_creation: true,
},
None,
false,
)
.unwrap();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_setting_and_document_addition");
handle.advance_one_successful_batch();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_adding_the_settings");
handle.advance_one_successful_batch();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_adding_the_documents");
index_scheduler
.register(
KindWithContent::DocumentDeletion {
index_uid: S("doggos"),
documents_ids: vec![S("1")],
},
None,
false,
)
.unwrap();
// This one should not be catched by Meilisearch but it's still nice to handle it because if one day we break the filters it could happens
index_scheduler
.register(
KindWithContent::DocumentDeletionByFilter {
index_uid: S("doggos"),
filter_expr: serde_json::json!(true),
},
None,
false,
)
.unwrap();
// Should fail because the ids are not filterable
index_scheduler
.register(
KindWithContent::DocumentDeletionByFilter {
index_uid: S("doggos"),
filter_expr: serde_json::json!("id = 2"),
},
None,
false,
)
.unwrap();
index_scheduler
.register(
KindWithContent::DocumentDeletionByFilter {
index_uid: S("doggos"),
filter_expr: serde_json::json!("catto EXISTS"),
},
None,
false,
)
.unwrap();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_document_deletions");
// Everything should be batched together
handle.advance_one_successful_batch();
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_removing_the_documents");
let index = index_scheduler.index("doggos").unwrap();
let rtxn = index.read_txn().unwrap();
let field_ids_map = index.fields_ids_map(&rtxn).unwrap();
let field_ids = field_ids_map.ids().collect::<Vec<_>>();
let documents = index
.all_documents(&rtxn)
.unwrap()
.map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap())
.collect::<Vec<_>>();
snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents_remaining_should_only_be_bork");
}
#[test]
fn do_not_batch_task_of_different_indexes() {
let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
@ -5085,7 +5200,7 @@ mod tests {
let simple_hf_name = name.clone();
let configs = index_scheduler.embedders(configs).unwrap();
let (hf_embedder, _) = configs.get(&simple_hf_name).unwrap();
let (hf_embedder, _, _) = configs.get(&simple_hf_name).unwrap();
let beagle_embed = hf_embedder.embed_one(S("Intel the beagle best doggo")).unwrap();
let lab_embed = hf_embedder.embed_one(S("Max the lab best doggo")).unwrap();
let patou_embed = hf_embedder.embed_one(S("kefir the patou best doggo")).unwrap();
@ -5403,7 +5518,11 @@ mod tests {
),
prompt: PromptData {
template: "{{doc.doggo}}",
max_bytes: Some(
400,
),
},
quantized: None,
},
user_provided: RoaringBitmap<[1, 2]>,
},
@ -5416,28 +5535,8 @@ mod tests {
// the document with the id 3 should keep its original embedding
let docid = index.external_documents_ids.get(&rtxn, "3").unwrap().unwrap();
let mut embeddings = Vec::new();
'vectors: for i in 0..=u8::MAX {
let reader = arroy::Reader::open(&rtxn, i as u16, index.vector_arroy)
.map(Some)
.or_else(|e| match e {
arroy::Error::MissingMetadata(_) => Ok(None),
e => Err(e),
})
.transpose();
let Some(reader) = reader else {
break 'vectors;
};
let embedding = reader.unwrap().item_vector(&rtxn, docid).unwrap();
if let Some(embedding) = embedding {
embeddings.push(embedding)
} else {
break 'vectors;
}
}
let embeddings = index.embeddings(&rtxn, docid).unwrap();
let embeddings = &embeddings["my_doggo_embedder"];
snapshot!(embeddings.len(), @"1");
assert!(embeddings[0].iter().all(|i| *i == 3.0), "{:?}", embeddings[0]);
@ -5617,8 +5716,12 @@ mod tests {
},
),
prompt: PromptData {
template: "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}",
template: "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
max_bytes: Some(
400,
),
},
quantized: None,
},
user_provided: RoaringBitmap<[0]>,
},
@ -5657,8 +5760,12 @@ mod tests {
},
),
prompt: PromptData {
template: "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}",
template: "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
max_bytes: Some(
400,
),
},
quantized: None,
},
user_provided: RoaringBitmap<[]>,
},

44
index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_adding_the_documents.snap Normal file
View File

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

43
index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_adding_the_settings.snap Normal file
View File

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

43
index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_adding_the_settings_and_documents.snap Normal file
View File

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

56
index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_removing_the_documents.snap Normal file
View File

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

9
index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/documents_remaining_should_only_be_bork.snap Normal file
View File

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

53
index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/registered_the_document_deletions.snap Normal file
View File

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

39
index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/registered_the_setting_and_document_addition.snap Normal file
View File

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

2
index-scheduler/src/snapshots/lib.rs/import_vectors/Intel to kefir succeeds.snap
View File

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

2
index-scheduler/src/snapshots/lib.rs/import_vectors/Intel to kefir.snap
View File

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

2
index-scheduler/src/snapshots/lib.rs/import_vectors/adding Intel succeeds.snap
View File

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

2
index-scheduler/src/snapshots/lib.rs/import_vectors/after adding Intel.snap
View File

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

2
index-scheduler/src/snapshots/lib.rs/import_vectors/after_registering_settings_task_vectors.snap
View File

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

2
index-scheduler/src/snapshots/lib.rs/import_vectors/settings_update_processed_vectors.snap
View File

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

2
index-scheduler/src/snapshots/lib.rs/test_settings_update/after_registering_settings_task.snap
View File

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

2
index-scheduler/src/snapshots/lib.rs/test_settings_update/settings_update_processed.snap
View File

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

2
meilisearch-types/Cargo.toml
View File

@ -66,3 +66,5 @@ khmer = ["milli/khmer"]
vietnamese = ["milli/vietnamese"]
# force swedish character recomposition
swedish-recomposition = ["milli/swedish-recomposition"]
# force german character recomposition
german = ["milli/german"]

12
meilisearch-types/src/error.rs
View File

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

9
meilisearch-types/src/index_uid.rs
View File

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

266
meilisearch-types/src/locales.rs
View File

@ -1,135 +1,6 @@
use deserr::Deserr;
use milli::LocalizedAttributesRule;
use serde::{Deserialize, Serialize};
use serde_json::json;
/// Generate a Locale enum and its From and Into implementations for milli::tokenizer::Language.
///
/// this enum implements `Deserr` in order to be used in the API.
macro_rules! make_locale {
($($language:tt), +) => {
#[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize, Ord, PartialOrd)]
#[deserr(rename_all = camelCase)]
#[serde(rename_all = "camelCase")]
pub enum Locale {
$($language),+,
}
impl From<milli::tokenizer::Language> for Locale {
fn from(other: milli::tokenizer::Language) -> Locale {
match other {
$(milli::tokenizer::Language::$language => Locale::$language), +
}
}
}
impl From<Locale> for milli::tokenizer::Language {
fn from(other: Locale) -> milli::tokenizer::Language {
match other {
$(Locale::$language => milli::tokenizer::Language::$language), +,
}
}
}
#[derive(Debug)]
pub struct LocaleFormatError {
pub invalid_locale: String,
}
impl std::fmt::Display for LocaleFormatError {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
let valid_locales = [$(Locale::$language),+].iter().map(|l| format!("`{}`", json!(l).as_str().unwrap())).collect::<Vec<_>>().join(", ");
write!(f, "Unsupported locale `{}`, expected one of {}", self.invalid_locale, valid_locales)
}
}
};
}
make_locale! {
Epo,
Eng,
Rus,
Cmn,
Spa,
Por,
Ita,
Ben,
Fra,
Deu,
Ukr,
Kat,
Ara,
Hin,
Jpn,
Heb,
Yid,
Pol,
Amh,
Jav,
Kor,
Nob,
Dan,
Swe,
Fin,
Tur,
Nld,
Hun,
Ces,
Ell,
Bul,
Bel,
Mar,
Kan,
Ron,
Slv,
Hrv,
Srp,
Mkd,
Lit,
Lav,
Est,
Tam,
Vie,
Urd,
Tha,
Guj,
Uzb,
Pan,
Aze,
Ind,
Tel,
Pes,
Mal,
Ori,
Mya,
Nep,
Sin,
Khm,
Tuk,
Aka,
Zul,
Sna,
Afr,
Lat,
Slk,
Cat,
Tgl,
Hye,
Zho
}
impl std::error::Error for LocaleFormatError {}
impl std::str::FromStr for Locale {
type Err = LocaleFormatError;
fn from_str(s: &str) -> Result<Self, Self::Err> {
milli::tokenizer::Language::from_code(s)
.map(Self::from)
.ok_or(LocaleFormatError { invalid_locale: s.to_string() })
}
}
#[derive(Debug, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize)]
#[deserr(rename_all = camelCase)]
@ -156,3 +27,140 @@ impl From<LocalizedAttributesRuleView> for LocalizedAttributesRule {
}
}
}
/// Generate a Locale enum and its From and Into implementations for milli::tokenizer::Language.
///
/// this enum implements `Deserr` in order to be used in the API.
macro_rules! make_locale {
($(($iso_639_1:ident, $iso_639_1_str:expr) => ($iso_639_3:ident, $iso_639_3_str:expr),)+) => {
#[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize, Ord, PartialOrd)]
#[deserr(rename_all = camelCase)]
#[serde(rename_all = "camelCase")]
pub enum Locale {
$($iso_639_1,)+
$($iso_639_3,)+
Cmn,
}
impl From<milli::tokenizer::Language> for Locale {
fn from(other: milli::tokenizer::Language) -> Locale {
match other {
$(milli::tokenizer::Language::$iso_639_3 => Locale::$iso_639_3,)+
milli::tokenizer::Language::Cmn => Locale::Cmn,
}
}
}
impl From<Locale> for milli::tokenizer::Language {
fn from(other: Locale) -> milli::tokenizer::Language {
match other {
$(Locale::$iso_639_1 => milli::tokenizer::Language::$iso_639_3,)+
$(Locale::$iso_639_3 => milli::tokenizer::Language::$iso_639_3,)+
Locale::Cmn => milli::tokenizer::Language::Cmn,
}
}
}
impl std::str::FromStr for Locale {
type Err = LocaleFormatError;
fn from_str(s: &str) -> Result<Self, Self::Err> {
let locale = match s {
$($iso_639_1_str => Locale::$iso_639_1,)+
$($iso_639_3_str => Locale::$iso_639_3,)+
"cmn" => Locale::Cmn,
_ => return Err(LocaleFormatError { invalid_locale: s.to_string() }),
};
Ok(locale)
}
}
#[derive(Debug)]
pub struct LocaleFormatError {
pub invalid_locale: String,
}
impl std::fmt::Display for LocaleFormatError {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
let mut valid_locales = [$($iso_639_1_str),+,$($iso_639_3_str),+,"cmn"];
valid_locales.sort_by(|left, right| left.len().cmp(&right.len()).then(left.cmp(right)));
write!(f, "Unsupported locale `{}`, expected one of {}", self.invalid_locale, valid_locales.join(", "))
}
}
impl std::error::Error for LocaleFormatError {}
};
}
make_locale!(
(Af, "af") => (Afr, "afr"),
(Ak, "ak") => (Aka, "aka"),
(Am, "am") => (Amh, "amh"),
(Ar, "ar") => (Ara, "ara"),
(Az, "az") => (Aze, "aze"),
(Be, "be") => (Bel, "bel"),
(Bn, "bn") => (Ben, "ben"),
(Bg, "bg") => (Bul, "bul"),
(Ca, "ca") => (Cat, "cat"),
(Cs, "cs") => (Ces, "ces"),
(Da, "da") => (Dan, "dan"),
(De, "de") => (Deu, "deu"),
(El, "el") => (Ell, "ell"),
(En, "en") => (Eng, "eng"),
(Eo, "eo") => (Epo, "epo"),
(Et, "et") => (Est, "est"),
(Fi, "fi") => (Fin, "fin"),
(Fr, "fr") => (Fra, "fra"),
(Gu, "gu") => (Guj, "guj"),
(He, "he") => (Heb, "heb"),
(Hi, "hi") => (Hin, "hin"),
(Hr, "hr") => (Hrv, "hrv"),
(Hu, "hu") => (Hun, "hun"),
(Hy, "hy") => (Hye, "hye"),
(Id, "id") => (Ind, "ind"),
(It, "it") => (Ita, "ita"),
(Jv, "jv") => (Jav, "jav"),
(Ja, "ja") => (Jpn, "jpn"),
(Kn, "kn") => (Kan, "kan"),
(Ka, "ka") => (Kat, "kat"),
(Km, "km") => (Khm, "khm"),
(Ko, "ko") => (Kor, "kor"),
(La, "la") => (Lat, "lat"),
(Lv, "lv") => (Lav, "lav"),
(Lt, "lt") => (Lit, "lit"),
(Ml, "ml") => (Mal, "mal"),
(Mr, "mr") => (Mar, "mar"),
(Mk, "mk") => (Mkd, "mkd"),
(My, "my") => (Mya, "mya"),
(Ne, "ne") => (Nep, "nep"),
(Nl, "nl") => (Nld, "nld"),
(Nb, "nb") => (Nob, "nob"),
(Or, "or") => (Ori, "ori"),
(Pa, "pa") => (Pan, "pan"),
(Fa, "fa") => (Pes, "pes"),
(Pl, "pl") => (Pol, "pol"),
(Pt, "pt") => (Por, "por"),
(Ro, "ro") => (Ron, "ron"),
(Ru, "ru") => (Rus, "rus"),
(Si, "si") => (Sin, "sin"),
(Sk, "sk") => (Slk, "slk"),
(Sl, "sl") => (Slv, "slv"),
(Sn, "sn") => (Sna, "sna"),
(Es, "es") => (Spa, "spa"),
(Sr, "sr") => (Srp, "srp"),
(Sv, "sv") => (Swe, "swe"),
(Ta, "ta") => (Tam, "tam"),
(Te, "te") => (Tel, "tel"),
(Tl, "tl") => (Tgl, "tgl"),
(Th, "th") => (Tha, "tha"),
(Tk, "tk") => (Tuk, "tuk"),
(Tr, "tr") => (Tur, "tur"),
(Uk, "uk") => (Ukr, "ukr"),
(Ur, "ur") => (Urd, "urd"),
(Uz, "uz") => (Uzb, "uzb"),
(Vi, "vi") => (Vie, "vie"),
(Yi, "yi") => (Yid, "yid"),
(Zh, "zh") => (Zho, "zho"),
(Zu, "zu") => (Zul, "zul"),
);

59
meilisearch-types/src/versioning.rs
View File

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

1
meilisearch/Cargo.toml
View File

@ -153,6 +153,7 @@ greek = ["meilisearch-types/greek"]
khmer = ["meilisearch-types/khmer"]
vietnamese = ["meilisearch-types/vietnamese"]
swedish-recomposition = ["meilisearch-types/swedish-recomposition"]
german = ["meilisearch-types/german"]
[package.metadata.mini-dashboard]
assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.14/build.zip"

17
meilisearch/src/analytics/segment_analytics.rs
View File

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

21
meilisearch/src/error.rs
View File

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

16
meilisearch/src/lib.rs
View File

@ -13,11 +13,10 @@ pub mod search_queue;
use std::fs::File;
use std::io::{BufReader, BufWriter};
use std::num::NonZeroUsize;
use std::path::Path;
use std::str::FromStr;
use std::sync::Arc;
use std::thread::{self, available_parallelism};
use std::thread;
use std::time::Duration;
use actix_cors::Cors;
@ -37,7 +36,7 @@ use meilisearch_types::milli::documents::{DocumentsBatchBuilder, DocumentsBatchR
use meilisearch_types::milli::update::{IndexDocumentsConfig, IndexDocumentsMethod};
use meilisearch_types::settings::apply_settings_to_builder;
use meilisearch_types::tasks::KindWithContent;
use meilisearch_types::versioning::{check_version_file, create_version_file};
use meilisearch_types::versioning::{check_version_file, create_current_version_file};
use meilisearch_types::{compression, milli, VERSION_FILE_NAME};
pub use option::Opt;
use option::ScheduleSnapshot;
@ -118,6 +117,7 @@ pub type LogStderrType = tracing_subscriber::filter::Filtered<
pub fn create_app(
index_scheduler: Data<IndexScheduler>,
auth_controller: Data<AuthController>,
search_queue: Data<SearchQueue>,
opt: Opt,
logs: (LogRouteHandle, LogStderrHandle),
analytics: Arc<dyn Analytics>,
@ -137,6 +137,7 @@ pub fn create_app(
s,
index_scheduler.clone(),
auth_controller.clone(),
search_queue.clone(),
&opt,
logs,
analytics.clone(),
@ -318,7 +319,7 @@ fn open_or_create_database_unchecked(
match (
index_scheduler_builder(),
auth_controller.map_err(anyhow::Error::from),
create_version_file(&opt.db_path).map_err(anyhow::Error::from),
create_current_version_file(&opt.db_path).map_err(anyhow::Error::from),
) {
(Ok(i), Ok(a), Ok(())) => Ok((i, a)),
(Err(e), _, _) | (_, Err(e), _) | (_, _, Err(e)) => {
@ -469,19 +470,16 @@ pub fn configure_data(
config: &mut web::ServiceConfig,
index_scheduler: Data<IndexScheduler>,
auth: Data<AuthController>,
search_queue: Data<SearchQueue>,
opt: &Opt,
(logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle),
analytics: Arc<dyn Analytics>,
) {
let search_queue = SearchQueue::new(
opt.experimental_search_queue_size,
available_parallelism().unwrap_or(NonZeroUsize::new(2).unwrap()),
);
let http_payload_size_limit = opt.http_payload_size_limit.as_u64() as usize;
config
.app_data(index_scheduler)
.app_data(auth)
.app_data(web::Data::new(search_queue))
.app_data(search_queue)
.app_data(web::Data::from(analytics))
.app_data(web::Data::new(logs_route))
.app_data(web::Data::new(logs_stderr))

9
meilisearch/src/main.rs
View File

@ -1,8 +1,10 @@
use std::env;
use std::io::{stderr, LineWriter, Write};
use std::num::NonZeroUsize;
use std::path::PathBuf;
use std::str::FromStr;
use std::sync::Arc;
use std::thread::available_parallelism;
use actix_web::http::KeepAlive;
use actix_web::web::Data;
@ -11,6 +13,7 @@ use index_scheduler::IndexScheduler;
use is_terminal::IsTerminal;
use meilisearch::analytics::Analytics;
use meilisearch::option::LogMode;
use meilisearch::search_queue::SearchQueue;
use meilisearch::{
analytics, create_app, setup_meilisearch, LogRouteHandle, LogRouteType, LogStderrHandle,
LogStderrType, Opt, SubscriberForSecondLayer,
@ -148,11 +151,17 @@ async fn run_http(
let opt_clone = opt.clone();
let index_scheduler = Data::from(index_scheduler);
let auth_controller = Data::from(auth_controller);
let search_queue = SearchQueue::new(
opt.experimental_search_queue_size,
available_parallelism().unwrap_or(NonZeroUsize::new(2).unwrap()),
);
let search_queue = Data::new(search_queue);
let http_server = HttpServer::new(move || {
create_app(
index_scheduler.clone(),
auth_controller.clone(),
search_queue.clone(),
opt.clone(),
logs.clone(),
analytics.clone(),

6
meilisearch/src/routes/indexes/facet_search.rs
View File

@ -81,7 +81,7 @@ pub async fn search(
let index = index_scheduler.index(&index_uid)?;
let features = index_scheduler.features();
let search_kind = search_kind(&search_query, &index_scheduler, &index, features)?;
let _permit = search_queue.try_get_search_permit().await?;
let permit = search_queue.try_get_search_permit().await?;
let search_result = tokio::task::spawn_blocking(move || {
perform_facet_search(
&index,
@ -93,7 +93,9 @@ pub async fn search(
locales,
)
})
.await?;
.await;
permit.drop().await;
let search_result = search_result?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);

103
meilisearch/src/routes/indexes/search.rs
View File

@ -128,8 +128,10 @@ impl std::ops::Deref for SemanticRatioGet {
}
}
impl From<SearchQueryGet> for SearchQuery {
fn from(other: SearchQueryGet) -> Self {
impl TryFrom<SearchQueryGet> for SearchQuery {
type Error = ResponseError;
fn try_from(other: SearchQueryGet) -> Result<Self, Self::Error> {
let filter = match other.filter {
Some(f) => match serde_json::from_str(&f) {
Ok(v) => Some(v),
@ -140,19 +142,28 @@ impl From<SearchQueryGet> for SearchQuery {
let hybrid = match (other.hybrid_embedder, other.hybrid_semantic_ratio) {
(None, None) => None,
(None, Some(semantic_ratio)) => {
Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder: None })
(None, Some(_)) => {
return Err(ResponseError::from_msg(
"`hybridEmbedder` is mandatory when `hybridSemanticRatio` is present".into(),
meilisearch_types::error::Code::InvalidHybridQuery,
));
}
(Some(embedder), None) => {
Some(HybridQuery { semantic_ratio: DEFAULT_SEMANTIC_RATIO(), embedder })
}
(Some(embedder), None) => Some(HybridQuery {
semantic_ratio: DEFAULT_SEMANTIC_RATIO(),
embedder: Some(embedder),
}),
(Some(embedder), Some(semantic_ratio)) => {
Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder: Some(embedder) })
Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder })
}
};
Self {
if other.vector.is_some() && hybrid.is_none() {
return Err(ResponseError::from_msg(
"`hybridEmbedder` is mandatory when `vector` is present".into(),
meilisearch_types::error::Code::MissingSearchHybrid,
));
}
Ok(Self {
q: other.q,
vector: other.vector.map(CS::into_inner),
offset: other.offset.0,
@ -179,7 +190,7 @@ impl From<SearchQueryGet> for SearchQuery {
hybrid,
ranking_score_threshold: other.ranking_score_threshold.map(|o| o.0),
locales: other.locales.map(|o| o.into_iter().collect()),
}
})
}
}
@ -219,7 +230,7 @@ pub async fn search_with_url_query(
debug!(parameters = ?params, "Search get");
let index_uid = IndexUid::try_from(index_uid.into_inner())?;
let mut query: SearchQuery = params.into_inner().into();
let mut query: SearchQuery = params.into_inner().try_into()?;
// Tenant token search_rules.
if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
@ -233,11 +244,13 @@ pub async fn search_with_url_query(
let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)?;
let _permit = search_queue.try_get_search_permit().await?;
let permit = search_queue.try_get_search_permit().await?;
let search_result = tokio::task::spawn_blocking(move || {
perform_search(&index, query, search_kind, retrieve_vector, index_scheduler.features())
})
.await?;
.await;
permit.drop().await;
let search_result = search_result?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
}
@ -276,11 +289,13 @@ pub async fn search_with_post(
let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
let _permit = search_queue.try_get_search_permit().await?;
let permit = search_queue.try_get_search_permit().await?;
let search_result = tokio::task::spawn_blocking(move || {
perform_search(&index, query, search_kind, retrieve_vectors, index_scheduler.features())
})
.await?;
.await;
permit.drop().await;
let search_result = search_result?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
if search_result.degraded {
@ -308,44 +323,36 @@ pub fn search_kind(
features.check_vector("Passing `hybrid` as a parameter")?;
}
// regardless of anything, always do a keyword search when we don't have a vector and the query is whitespace or missing
if query.vector.is_none() {
match &query.q {
Some(q) if q.trim().is_empty() => return Ok(SearchKind::KeywordOnly),
None => return Ok(SearchKind::KeywordOnly),
_ => {}
// handle with care, the order of cases matters, the semantics is subtle
match (query.q.as_deref(), &query.hybrid, query.vector.as_deref()) {
// empty query, no vector => placeholder search
(Some(q), _, None) if q.trim().is_empty() => Ok(SearchKind::KeywordOnly),
// no query, no vector => placeholder search
(None, _, None) => Ok(SearchKind::KeywordOnly),
// hybrid.semantic_ratio == 1.0 => vector
(_, Some(HybridQuery { semantic_ratio, embedder }), v) if **semantic_ratio == 1.0 => {
SearchKind::semantic(index_scheduler, index, embedder, v.map(|v| v.len()))
}
}
match &query.hybrid {
Some(HybridQuery { semantic_ratio, embedder }) if **semantic_ratio == 1.0 => {
Ok(SearchKind::semantic(
index_scheduler,
index,
embedder.as_deref(),
query.vector.as_ref().map(Vec::len),
)?)
}
Some(HybridQuery { semantic_ratio, embedder: _ }) if **semantic_ratio == 0.0 => {
// hybrid.semantic_ratio == 0.0 => keyword
(_, Some(HybridQuery { semantic_ratio, embedder: _ }), _) if **semantic_ratio == 0.0 => {
Ok(SearchKind::KeywordOnly)
}
Some(HybridQuery { semantic_ratio, embedder }) => Ok(SearchKind::hybrid(
// no query, hybrid, vector => semantic
(None, Some(HybridQuery { semantic_ratio: _, embedder }), Some(v)) => {
SearchKind::semantic(index_scheduler, index, embedder, Some(v.len()))
}
// query, no hybrid, no vector => keyword
(Some(_), None, None) => Ok(SearchKind::KeywordOnly),
// query, hybrid, maybe vector => hybrid
(Some(_), Some(HybridQuery { semantic_ratio, embedder }), v) => SearchKind::hybrid(
index_scheduler,
index,
embedder.as_deref(),
embedder,
**semantic_ratio,
query.vector.as_ref().map(Vec::len),
)?),
None => match (query.q.as_deref(), query.vector.as_deref()) {
(_query, None) => Ok(SearchKind::KeywordOnly),
(None, Some(_vector)) => Ok(SearchKind::semantic(
index_scheduler,
index,
None,
query.vector.as_ref().map(Vec::len),
)?),
(Some(_), Some(_)) => Err(MeilisearchHttpError::MissingSearchHybrid.into()),
},
v.map(|v| v.len()),
),
(_, None, Some(_)) => Err(MeilisearchHttpError::MissingSearchHybrid.into()),
}
}

15
meilisearch/src/routes/indexes/settings.rs
View File

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

9
meilisearch/src/routes/indexes/similar.rs
View File

@ -102,8 +102,8 @@ async fn similar(
let index = index_scheduler.index(&index_uid)?;
let (embedder_name, embedder) =
SearchKind::embedder(&index_scheduler, &index, query.embedder.as_deref(), None)?;
let (embedder_name, embedder, quantized) =
SearchKind::embedder(&index_scheduler, &index, &query.embedder, None)?;
tokio::task::spawn_blocking(move || {
perform_similar(
@ -111,6 +111,7 @@ async fn similar(
query,
embedder_name,
embedder,
quantized,
retrieve_vectors,
index_scheduler.features(),
)
@ -139,8 +140,8 @@ pub struct SimilarQueryGet {
show_ranking_score_details: Param<bool>,
#[deserr(default, error = DeserrQueryParamError<InvalidSimilarRankingScoreThreshold>, default)]
pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
#[deserr(default, error = DeserrQueryParamError<InvalidEmbedder>)]
pub embedder: Option<String>,
#[deserr(error = DeserrQueryParamError<InvalidEmbedder>)]
pub embedder: String,
}
#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]

4
meilisearch/src/routes/multi_search.rs
View File

@ -39,7 +39,7 @@ pub async fn multi_search_with_post(
) -> Result<HttpResponse, ResponseError> {
// Since we don't want to process half of the search requests and then get a permit refused
// we're going to get one permit for the whole duration of the multi-search request.
let _permit = search_queue.try_get_search_permit().await?;
let permit = search_queue.try_get_search_permit().await?;
let federated_search = params.into_inner();
@ -81,6 +81,7 @@ pub async fn multi_search_with_post(
perform_federated_search(&index_scheduler, queries, federation, features)
})
.await;
permit.drop().await;
if let Ok(Ok(_)) = search_result {
multi_aggregate.succeed();
@ -143,6 +144,7 @@ pub async fn multi_search_with_post(
Ok(search_results)
}
.await;
permit.drop().await;
if search_results.is_ok() {
multi_aggregate.succeed();

319
meilisearch/src/search/federated.rs
View File

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

168
meilisearch/src/search/mod.rs
View File

@ -267,58 +267,54 @@ impl fmt::Debug for SearchQuery {
pub struct HybridQuery {
#[deserr(default, error = DeserrJsonError<InvalidSearchSemanticRatio>, default)]
pub semantic_ratio: SemanticRatio,
#[deserr(default, error = DeserrJsonError<InvalidEmbedder>, default)]
pub embedder: Option<String>,
#[deserr(error = DeserrJsonError<InvalidEmbedder>)]
pub embedder: String,
}
#[derive(Clone)]
pub enum SearchKind {
KeywordOnly,
SemanticOnly { embedder_name: String, embedder: Arc<Embedder> },
Hybrid { embedder_name: String, embedder: Arc<Embedder>, semantic_ratio: f32 },
SemanticOnly { embedder_name: String, embedder: Arc<Embedder>, quantized: bool },
Hybrid { embedder_name: String, embedder: Arc<Embedder>, quantized: bool, semantic_ratio: f32 },
}
impl SearchKind {
pub(crate) fn semantic(
index_scheduler: &index_scheduler::IndexScheduler,
index: &Index,
embedder_name: Option<&str>,
embedder_name: &str,
vector_len: Option<usize>,
) -> Result<Self, ResponseError> {
let (embedder_name, embedder) =
let (embedder_name, embedder, quantized) =
Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
Ok(Self::SemanticOnly { embedder_name, embedder })
Ok(Self::SemanticOnly { embedder_name, embedder, quantized })
}
pub(crate) fn hybrid(
index_scheduler: &index_scheduler::IndexScheduler,
index: &Index,
embedder_name: Option<&str>,
embedder_name: &str,
semantic_ratio: f32,
vector_len: Option<usize>,
) -> Result<Self, ResponseError> {
let (embedder_name, embedder) =
let (embedder_name, embedder, quantized) =
Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
Ok(Self::Hybrid { embedder_name, embedder, semantic_ratio })
Ok(Self::Hybrid { embedder_name, embedder, quantized, semantic_ratio })
}
pub(crate) fn embedder(
index_scheduler: &index_scheduler::IndexScheduler,
index: &Index,
embedder_name: Option<&str>,
embedder_name: &str,
vector_len: Option<usize>,
) -> Result<(String, Arc<Embedder>), ResponseError> {
) -> Result<(String, Arc<Embedder>, bool), ResponseError> {
let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
let embedders = index_scheduler.embedders(embedder_configs)?;
let embedder_name = embedder_name.unwrap_or_else(|| embedders.get_default_embedder_name());
let embedder = embedders.get(embedder_name);
let embedder = embedder
let (embedder, _, quantized) = embedders
.get(embedder_name)
.ok_or(milli::UserError::InvalidEmbedder(embedder_name.to_owned()))
.map_err(milli::Error::from)?
.0;
.map_err(milli::Error::from)?;
if let Some(vector_len) = vector_len {
if vector_len != embedder.dimensions() {
@ -332,7 +328,7 @@ impl SearchKind {
}
}
Ok((embedder_name.to_owned(), embedder))
Ok((embedder_name.to_owned(), embedder, quantized))
}
}
@ -441,9 +437,6 @@ pub struct SearchQueryWithIndex {
}
impl SearchQueryWithIndex {
pub fn has_federation_options(&self) -> bool {
self.federation_options.is_some()
}
pub fn has_pagination(&self) -> Option<&'static str> {
if self.offset.is_some() {
Some("offset")
@ -458,6 +451,10 @@ impl SearchQueryWithIndex {
}
}
pub fn has_facets(&self) -> Option<&[String]> {
self.facets.as_deref().filter(|v| !v.is_empty())
}
pub fn into_index_query_federation(self) -> (IndexUid, SearchQuery, Option<FederationOptions>) {
let SearchQueryWithIndex {
index_uid,
@ -537,8 +534,8 @@ pub struct SimilarQuery {
pub limit: usize,
#[deserr(default, error = DeserrJsonError<InvalidSimilarFilter>)]
pub filter: Option<Value>,
#[deserr(default, error = DeserrJsonError<InvalidEmbedder>, default)]
pub embedder: Option<String>,
#[deserr(error = DeserrJsonError<InvalidEmbedder>)]
pub embedder: String,
#[deserr(default, error = DeserrJsonError<InvalidSimilarAttributesToRetrieve>)]
pub attributes_to_retrieve: Option<BTreeSet<String>>,
#[deserr(default, error = DeserrJsonError<InvalidSimilarRetrieveVectors>)]
@ -792,7 +789,7 @@ fn prepare_search<'t>(
search.query(q);
}
}
SearchKind::SemanticOnly { embedder_name, embedder } => {
SearchKind::SemanticOnly { embedder_name, embedder, quantized } => {
let vector = match query.vector.clone() {
Some(vector) => vector,
None => {
@ -806,14 +803,19 @@ fn prepare_search<'t>(
}
};
search.semantic(embedder_name.clone(), embedder.clone(), Some(vector));
search.semantic(embedder_name.clone(), embedder.clone(), *quantized, Some(vector));
}
SearchKind::Hybrid { embedder_name, embedder, semantic_ratio: _ } => {
SearchKind::Hybrid { embedder_name, embedder, quantized, semantic_ratio: _ } => {
if let Some(q) = &query.q {
search.query(q);
}
// will be embedded in hybrid search if necessary
search.semantic(embedder_name.clone(), embedder.clone(), query.vector.clone());
search.semantic(
embedder_name.clone(),
embedder.clone(),
*quantized,
query.vector.clone(),
);
}
}
@ -987,39 +989,13 @@ pub fn perform_search(
HitsInfo::OffsetLimit { limit, offset, estimated_total_hits: number_of_hits }
};
let (facet_distribution, facet_stats) = match facets {
Some(ref fields) => {
let mut facet_distribution = index.facets_distribution(&rtxn);
let max_values_by_facet = index
.max_values_per_facet(&rtxn)
.map_err(milli::Error::from)?
.map(|x| x as usize)
.unwrap_or(DEFAULT_VALUES_PER_FACET);
facet_distribution.max_values_per_facet(max_values_by_facet);
let sort_facet_values_by =
index.sort_facet_values_by(&rtxn).map_err(milli::Error::from)?;
if fields.iter().all(|f| f != "*") {
let fields: Vec<_> =
fields.iter().map(|n| (n, sort_facet_values_by.get(n))).collect();
facet_distribution.facets(fields);
}
let distribution = facet_distribution
.candidates(candidates)
.default_order_by(sort_facet_values_by.get("*"))
.execute()?;
let stats = facet_distribution.compute_stats()?;
(Some(distribution), Some(stats))
}
None => (None, None),
};
let facet_stats = facet_stats.map(|stats| {
stats.into_iter().map(|(k, (min, max))| (k, FacetStats { min, max })).collect()
});
let (facet_distribution, facet_stats) = facets
.map(move |facets| {
compute_facet_distribution_stats(&facets, index, &rtxn, candidates, Route::Search)
})
.transpose()?
.map(|ComputedFacets { distribution, stats }| (distribution, stats))
.unzip();
let result = SearchResult {
hits: documents,
@ -1035,6 +1011,61 @@ pub fn perform_search(
Ok(result)
}
#[derive(Debug, Clone, Default, Serialize)]
pub struct ComputedFacets {
pub distribution: BTreeMap<String, IndexMap<String, u64>>,
pub stats: BTreeMap<String, FacetStats>,
}
enum Route {
Search,
MultiSearch,
}
fn compute_facet_distribution_stats<S: AsRef<str>>(
facets: &[S],
index: &Index,
rtxn: &RoTxn,
candidates: roaring::RoaringBitmap,
route: Route,
) -> Result<ComputedFacets, ResponseError> {
let mut facet_distribution = index.facets_distribution(rtxn);
let max_values_by_facet = index
.max_values_per_facet(rtxn)
.map_err(milli::Error::from)?
.map(|x| x as usize)
.unwrap_or(DEFAULT_VALUES_PER_FACET);
facet_distribution.max_values_per_facet(max_values_by_facet);
let sort_facet_values_by = index.sort_facet_values_by(rtxn).map_err(milli::Error::from)?;
// add specific facet if there is no placeholder
if facets.iter().all(|f| f.as_ref() != "*") {
let fields: Vec<_> =
facets.iter().map(|n| (n, sort_facet_values_by.get(n.as_ref()))).collect();
facet_distribution.facets(fields);
}
let distribution = facet_distribution
.candidates(candidates)
.default_order_by(sort_facet_values_by.get("*"))
.execute()
.map_err(|error| match (error, route) {
(
error @ milli::Error::UserError(milli::UserError::InvalidFacetsDistribution {
..
}),
Route::MultiSearch,
) => ResponseError::from_msg(error.to_string(), Code::InvalidMultiSearchFacets),
(error, _) => error.into(),
})?;
let stats = facet_distribution.compute_stats()?;
let stats = stats.into_iter().map(|(k, (min, max))| (k, FacetStats { min, max })).collect();
Ok(ComputedFacets { distribution, stats })
}
pub fn search_from_kind(
search_kind: SearchKind,
search: milli::Search<'_>,
@ -1413,6 +1444,7 @@ pub fn perform_similar(
query: SimilarQuery,
embedder_name: String,
embedder: Arc<Embedder>,
quantized: bool,
retrieve_vectors: RetrieveVectors,
features: RoFeatures,
) -> Result<SimilarResult, ResponseError> {
@ -1441,8 +1473,16 @@ pub fn perform_similar(
));
};
let mut similar =
milli::Similar::new(internal_id, offset, limit, index, &rtxn, embedder_name, embedder);
let mut similar = milli::Similar::new(
internal_id,
offset,
limit,
index,
&rtxn,
embedder_name,
embedder,
quantized,
);
if let Some(ref filter) = query.filter {
if let Some(facets) = parse_filter(filter, Code::InvalidSimilarFilter, features)? {

38
meilisearch/src/search_queue.rs
View File

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

29
meilisearch/tests/common/server.rs
View File

@ -11,13 +11,11 @@ use actix_web::http::StatusCode;
use byte_unit::{Byte, Unit};
use clap::Parser;
use meilisearch::option::{IndexerOpts, MaxMemory, MaxThreads, Opt};
use meilisearch::{analytics, create_app, setup_meilisearch, SubscriberForSecondLayer};
use meilisearch::setup_meilisearch;
use once_cell::sync::Lazy;
use tempfile::TempDir;
use tokio::sync::OnceCell;
use tokio::time::sleep;
use tracing::level_filters::LevelFilter;
use tracing_subscriber::Layer;
use uuid::Uuid;
use super::index::Index;
@ -183,7 +181,7 @@ impl Server<Shared> {
let options = default_settings(dir.path());
let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
let service = Service { index_scheduler, auth, options, api_key: None };
let service = Service { index_scheduler, auth, api_key: None, options };
Server { service, _dir: Some(dir), _marker: PhantomData }
}
@ -263,28 +261,7 @@ impl<State> Server<State> {
Response = ServiceResponse<impl MessageBody>,
Error = actix_web::Error,
> {
let (_route_layer, route_layer_handle) =
tracing_subscriber::reload::Layer::new(None.with_filter(
tracing_subscriber::filter::Targets::new().with_target("", LevelFilter::OFF),
));
let (_stderr_layer, stderr_layer_handle) = tracing_subscriber::reload::Layer::new(
(Box::new(
tracing_subscriber::fmt::layer()
.with_span_events(tracing_subscriber::fmt::format::FmtSpan::CLOSE),
)
as Box<dyn tracing_subscriber::Layer<SubscriberForSecondLayer> + Send + Sync>)
.with_filter(tracing_subscriber::filter::Targets::new()),
);
actix_web::test::init_service(create_app(
self.service.index_scheduler.clone().into(),
self.service.auth.clone().into(),
self.service.options.clone(),
(route_layer_handle, stderr_layer_handle),
analytics::MockAnalytics::new(&self.service.options),
true,
))
.await
self.service.init_web_app().await
}
pub async fn list_api_keys(&self, params: &str) -> (Value, StatusCode) {

26
meilisearch/tests/common/service.rs
View File

@ -1,10 +1,15 @@
use std::num::NonZeroUsize;
use std::sync::Arc;
use actix_web::body::MessageBody;
use actix_web::dev::ServiceResponse;
use actix_web::http::header::ContentType;
use actix_web::http::StatusCode;
use actix_web::test;
use actix_web::test::TestRequest;
use actix_web::web::Data;
use index_scheduler::IndexScheduler;
use meilisearch::search_queue::SearchQueue;
use meilisearch::{analytics, create_app, Opt, SubscriberForSecondLayer};
use meilisearch_auth::AuthController;
use tracing::level_filters::LevelFilter;
@ -106,7 +111,13 @@ impl Service {
self.request(req).await
}
pub async fn request(&self, mut req: test::TestRequest) -> (Value, StatusCode) {
pub async fn init_web_app(
&self,
) -> impl actix_web::dev::Service<
actix_http::Request,
Response = ServiceResponse<impl MessageBody>,
Error = actix_web::Error,
> {
let (_route_layer, route_layer_handle) =
tracing_subscriber::reload::Layer::new(None.with_filter(
tracing_subscriber::filter::Targets::new().with_target("", LevelFilter::OFF),
@ -119,16 +130,25 @@ impl Service {
as Box<dyn tracing_subscriber::Layer<SubscriberForSecondLayer> + Send + Sync>)
.with_filter(tracing_subscriber::filter::Targets::new()),
);
let search_queue = SearchQueue::new(
self.options.experimental_search_queue_size,
NonZeroUsize::new(1).unwrap(),
);
let app = test::init_service(create_app(
actix_web::test::init_service(create_app(
self.index_scheduler.clone().into(),
self.auth.clone().into(),
Data::new(search_queue),
self.options.clone(),
(route_layer_handle, stderr_layer_handle),
analytics::MockAnalytics::new(&self.options),
true,
))
.await;
.await
}
pub async fn request(&self, mut req: test::TestRequest) -> (Value, StatusCode) {
let app = self.init_web_app().await;
if let Some(api_key) = &self.api_key {
req = req.insert_header(("Authorization", ["Bearer ", api_key].concat()));

3
meilisearch/tests/content_type.rs
View File

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

6
meilisearch/tests/documents/errors.rs
View File

@ -136,7 +136,7 @@ async fn get_all_documents_bad_filter() {
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `doggo`.\n1:6 doggo",
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `doggo`.\n1:6 doggo",
"code": "invalid_document_filter",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@ -525,7 +525,7 @@ async fn delete_document_by_filter() {
snapshot!(code, @"400 Bad Request");
snapshot!(response, @r###"
{
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `hello`.\n1:6 hello",
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `hello`.\n1:6 hello",
"code": "invalid_document_filter",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@ -723,7 +723,7 @@ async fn fetch_document_by_filter() {
snapshot!(code, @"400 Bad Request");
snapshot!(response, @r###"
{
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `cool doggo`.\n1:11 cool doggo",
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `cool doggo`.\n1:11 cool doggo",
"code": "invalid_document_filter",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_document_filter"

3
meilisearch/tests/dumps/mod.rs
View File

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

8
meilisearch/tests/logs/mod.rs
View File

@ -1,10 +1,13 @@
mod error;
use std::num::NonZeroUsize;
use std::rc::Rc;
use std::str::FromStr;
use actix_web::http::header::ContentType;
use actix_web::web::Data;
use meili_snap::snapshot;
use meilisearch::search_queue::SearchQueue;
use meilisearch::{analytics, create_app, Opt, SubscriberForSecondLayer};
use tracing::level_filters::LevelFilter;
use tracing_subscriber::layer::SubscriberExt;
@ -40,10 +43,15 @@ async fn basic_test_log_stream_route() {
.with_span_events(tracing_subscriber::fmt::format::FmtSpan::ACTIVE)
.with_filter(tracing_subscriber::filter::LevelFilter::from_str("OFF").unwrap()),
);
let search_queue = SearchQueue::new(
server.service.options.experimental_search_queue_size,
NonZeroUsize::new(1).unwrap(),
);
let app = actix_web::test::init_service(create_app(
server.service.index_scheduler.clone().into(),
server.service.auth.clone().into(),
Data::new(search_queue),
server.service.options.clone(),
(route_layer_handle, stderr_layer_handle),
analytics::MockAnalytics::new(&server.service.options),

12
meilisearch/tests/search/errors.rs
View File

@ -646,7 +646,7 @@ async fn filter_invalid_syntax_object() {
.search(json!({"filter": "title & Glass"}), |response, code| {
snapshot!(response, @r###"
{
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
"code": "invalid_search_filter",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@ -669,7 +669,7 @@ async fn filter_invalid_syntax_array() {
.search(json!({"filter": ["title & Glass"]}), |response, code| {
snapshot!(response, @r###"
{
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
"code": "invalid_search_filter",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@ -1163,7 +1163,7 @@ async fn search_with_contains_without_enabling_the_feature() {
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
"message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
"code": "feature_not_enabled",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#feature_not_enabled"
@ -1176,7 +1176,7 @@ async fn search_with_contains_without_enabling_the_feature() {
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n25:33 doggo != echo AND doggo CONTAINS kefir",
"message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n25:33 doggo != echo AND doggo CONTAINS kefir",
"code": "feature_not_enabled",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#feature_not_enabled"
@ -1192,7 +1192,7 @@ async fn search_with_contains_without_enabling_the_feature() {
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
"message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
"code": "feature_not_enabled",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#feature_not_enabled"
@ -1204,7 +1204,7 @@ async fn search_with_contains_without_enabling_the_feature() {
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
"message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
"code": "feature_not_enabled",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#feature_not_enabled"

65
meilisearch/tests/search/hybrid.rs
View File

@ -128,7 +128,7 @@ async fn simple_search() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2}, "retrieveVectors": true}),
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2, "embedder": "default"}, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
@ -137,7 +137,7 @@ async fn simple_search() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.5}, "showRankingScore": true, "retrieveVectors": true}),
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.5, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
@ -146,7 +146,7 @@ async fn simple_search() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.8}, "showRankingScore": true, "retrieveVectors": true}),
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.8, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
@ -161,7 +161,7 @@ async fn limit_offset() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2}, "retrieveVectors": true, "offset": 1, "limit": 1}),
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2, "embedder": "default"}, "retrieveVectors": true, "offset": 1, "limit": 1}),
)
.await;
snapshot!(code, @"200 OK");
@ -174,7 +174,7 @@ async fn limit_offset() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.9}, "retrieveVectors": true, "offset": 1, "limit": 1}),
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.9, "embedder": "default"}, "retrieveVectors": true, "offset": 1, "limit": 1}),
)
.await;
snapshot!(code, @"200 OK");
@ -188,8 +188,11 @@ async fn simple_search_hf() {
let server = Server::new().await;
let index = index_with_documents_hf(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
let (response, code) =
index.search_post(json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2}})).await;
let (response, code) = index
.search_post(
json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2, "embedder": "default"}}),
)
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"}]"###);
snapshot!(response["semanticHitCount"], @"0");
@ -197,7 +200,7 @@ async fn simple_search_hf() {
let (response, code) = index
.search_post(
// disable ranking score as the vectors between architectures are not equal
json!({"q": "Captain", "hybrid": {"semanticRatio": 0.55}, "showRankingScore": false}),
json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.55}, "showRankingScore": false}),
)
.await;
snapshot!(code, @"200 OK");
@ -206,7 +209,7 @@ async fn simple_search_hf() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "hybrid": {"semanticRatio": 0.8}, "showRankingScore": false}),
json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.8}, "showRankingScore": false}),
)
.await;
snapshot!(code, @"200 OK");
@ -215,7 +218,7 @@ async fn simple_search_hf() {
let (response, code) = index
.search_post(
json!({"q": "Movie World", "hybrid": {"semanticRatio": 0.2}, "showRankingScore": false}),
json!({"q": "Movie World", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "showRankingScore": false}),
)
.await;
snapshot!(code, @"200 OK");
@ -224,7 +227,7 @@ async fn simple_search_hf() {
let (response, code) = index
.search_post(
json!({"q": "Wonder replacement", "hybrid": {"semanticRatio": 0.2}, "showRankingScore": false}),
json!({"q": "Wonder replacement", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "showRankingScore": false}),
)
.await;
snapshot!(code, @"200 OK");
@ -237,7 +240,7 @@ async fn distribution_shift() {
let server = Server::new().await;
let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
let search = json!({"q": "Captain", "vector": [1.0, 1.0], "showRankingScore": true, "hybrid": {"semanticRatio": 1.0}, "retrieveVectors": true});
let search = json!({"q": "Captain", "vector": [1.0, 1.0], "showRankingScore": true, "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "retrieveVectors": true});
let (response, code) = index.search_post(search.clone()).await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.9472135901451112}]"###);
@ -271,7 +274,7 @@ async fn highlighter() {
let (response, code) = index
.search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
"hybrid": {"semanticRatio": 0.2},
"hybrid": {"embedder": "default", "semanticRatio": 0.2},
"retrieveVectors": true,
"attributesToHighlight": [
"desc",
@ -287,7 +290,7 @@ async fn highlighter() {
let (response, code) = index
.search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
"hybrid": {"semanticRatio": 0.8},
"hybrid": {"embedder": "default", "semanticRatio": 0.8},
"retrieveVectors": true,
"showRankingScore": true,
"attributesToHighlight": [
@ -304,7 +307,7 @@ async fn highlighter() {
// no highlighting on full semantic
let (response, code) = index
.search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
"hybrid": {"semanticRatio": 1.0},
"hybrid": {"embedder": "default", "semanticRatio": 1.0},
"retrieveVectors": true,
"showRankingScore": true,
"attributesToHighlight": [
@ -326,7 +329,7 @@ async fn invalid_semantic_ratio() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 1.2}}),
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"embedder": "default", "semanticRatio": 1.2}}),
)
.await;
snapshot!(code, @"400 Bad Request");
@ -341,7 +344,7 @@ async fn invalid_semantic_ratio() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": -0.8}}),
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"embedder": "default", "semanticRatio": -0.8}}),
)
.await;
snapshot!(code, @"400 Bad Request");
@ -357,7 +360,7 @@ async fn invalid_semantic_ratio() {
let (response, code) = index
.search_get(
&yaup::to_string(
&json!({"q": "Captain", "vector": [1.0, 1.0], "hybridSemanticRatio": 1.2}),
&json!({"q": "Captain", "vector": [1.0, 1.0], "hybridEmbedder": "default", "hybridSemanticRatio": 1.2}),
)
.unwrap(),
)
@ -375,7 +378,7 @@ async fn invalid_semantic_ratio() {
let (response, code) = index
.search_get(
&yaup::to_string(
&json!({"q": "Captain", "vector": [1.0, 1.0], "hybridSemanticRatio": -0.2}),
&json!({"q": "Captain", "vector": [1.0, 1.0], "hybridEmbedder": "default", "hybridSemanticRatio": -0.2}),
)
.unwrap(),
)
@ -398,7 +401,7 @@ async fn single_document() {
let (response, code) = index
.search_post(
json!({"vector": [1.0, 3.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}),
json!({"vector": [1.0, 3.0], "hybrid": {"semanticRatio": 1.0, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
)
.await;
@ -414,7 +417,7 @@ async fn query_combination() {
// search without query and vector, but with hybrid => still placeholder
let (response, code) = index
.search_post(json!({"hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
.search_post(json!({"hybrid": {"embedder": "default", "semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"200 OK");
@ -423,7 +426,7 @@ async fn query_combination() {
// same with a different semantic ratio
let (response, code) = index
.search_post(json!({"hybrid": {"semanticRatio": 0.76}, "showRankingScore": true, "retrieveVectors": true}))
.search_post(json!({"hybrid": {"embedder": "default", "semanticRatio": 0.76}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"200 OK");
@ -432,7 +435,7 @@ async fn query_combination() {
// wrong vector dimensions
let (response, code) = index
.search_post(json!({"vector": [1.0, 0.0, 1.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
.search_post(json!({"vector": [1.0, 0.0, 1.0], "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"400 Bad Request");
@ -447,7 +450,7 @@ async fn query_combination() {
// full vector
let (response, code) = index
.search_post(json!({"vector": [1.0, 0.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
.search_post(json!({"vector": [1.0, 0.0], "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"200 OK");
@ -456,7 +459,7 @@ async fn query_combination() {
// full keyword, without a query
let (response, code) = index
.search_post(json!({"vector": [1.0, 0.0], "hybrid": {"semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
.search_post(json!({"vector": [1.0, 0.0], "hybrid": {"embedder": "default", "semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"200 OK");
@ -465,7 +468,7 @@ async fn query_combination() {
// query + vector, full keyword => keyword
let (response, code) = index
.search_post(json!({"q": "Captain", "vector": [1.0, 0.0], "hybrid": {"semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
.search_post(json!({"q": "Captain", "vector": [1.0, 0.0], "hybrid": {"embedder": "default", "semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"200 OK");
@ -480,7 +483,7 @@ async fn query_combination() {
snapshot!(code, @"400 Bad Request");
snapshot!(response, @r###"
{
"message": "Invalid request: missing `hybrid` parameter when both `q` and `vector` are present.",
"message": "Invalid request: missing `hybrid` parameter when `vector` is present.",
"code": "missing_search_hybrid",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#missing_search_hybrid"
@ -490,7 +493,7 @@ async fn query_combination() {
// full vector, without a vector => error
let (response, code) = index
.search_post(
json!({"q": "Captain", "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}),
json!({"q": "Captain", "hybrid": {"semanticRatio": 1.0, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
)
.await;
@ -507,7 +510,7 @@ async fn query_combination() {
// hybrid without a vector => full keyword
let (response, code) = index
.search_post(
json!({"q": "Planet", "hybrid": {"semanticRatio": 0.99}, "showRankingScore": true, "retrieveVectors": true}),
json!({"q": "Planet", "hybrid": {"semanticRatio": 0.99, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
)
.await;
@ -523,7 +526,7 @@ async fn retrieve_vectors() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2}, "retrieveVectors": true}),
json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
@ -573,7 +576,7 @@ async fn retrieve_vectors() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2}, "retrieveVectors": true}),
json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");

773
meilisearch/tests/search/locales.rs
View File

File diff suppressed because it is too large Load Diff

35
meilisearch/tests/search/mod.rs
View File

@ -1099,22 +1099,28 @@ async fn experimental_feature_vector_store() {
index.add_documents(json!(documents), None).await;
index.wait_task(0).await;
index
.search(json!({
let (response, code) = index
.search_post(json!({
"vector": [1.0, 2.0, 3.0],
"hybrid": {
"embedder": "manual",
},
"showRankingScore": true
}), |response, code|{
meili_snap::snapshot!(code, @"400 Bad Request");
meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
{
"message": "Passing `vector` as a parameter requires enabling the `vector store` experimental feature. See https://github.com/meilisearch/product/discussions/677",
"code": "feature_not_enabled",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#feature_not_enabled"
}
"###);
})
}))
.await;
{
meili_snap::snapshot!(code, @"400 Bad Request");
meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
{
"message": "Passing `vector` as a parameter requires enabling the `vector store` experimental feature. See https://github.com/meilisearch/product/discussions/677",
"code": "feature_not_enabled",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#feature_not_enabled"
}
"###);
}
index
.search(json!({
"retrieveVectors": true,
@ -1162,6 +1168,9 @@ async fn experimental_feature_vector_store() {
let (response, code) = index
.search_post(json!({
"vector": [1.0, 2.0, 3.0],
"hybrid": {
"embedder": "manual",
},
"showRankingScore": true,
"retrieveVectors": true,
}))

1543
meilisearch/tests/search/multi.rs
View File

File diff suppressed because it is too large Load Diff

37
meilisearch/tests/search/search_queue.rs
View File

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

3
meilisearch/tests/settings/get_settings.rs
View File

@ -190,7 +190,8 @@ async fn secrets_are_hidden_in_settings() {
"source": "rest",
"apiKey": "My suXXXXXX...",
"dimensions": 4,
"documentTemplate": "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}",
"documentTemplate": "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
"documentTemplateMaxBytes": 400,
"url": "https://localhost:7777",
"request": "{{text}}",
"response": "{{embedding}}",

124
meilisearch/tests/similar/errors.rs
View File

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

49
meilisearch/tests/similar/mod.rs
View File

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

380
meilisearch/tests/vector/binary_quantized.rs Normal file
View File

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

10
meilisearch/tests/vector/mod.rs
View File

@ -1,3 +1,4 @@
mod binary_quantized;
mod openai;
mod rest;
mod settings;
@ -624,7 +625,8 @@ async fn clear_documents() {
"###);
// Make sure the arroy DB has been cleared
let (documents, _code) = index.search_post(json!({ "vector": [1, 1, 1] })).await;
let (documents, _code) =
index.search_post(json!({ "vector": [1, 1, 1], "hybrid": {"embedder": "manual"} })).await;
snapshot!(documents, @r###"
{
"hits": [],
@ -685,7 +687,11 @@ async fn add_remove_one_vector_4588() {
let task = index.wait_task(value.uid()).await;
snapshot!(task, name: "document-deleted");
let (documents, _code) = index.search_post(json!({"vector": [1, 1, 1] })).await;
let (documents, _code) = index
.search_post(
json!({"vector": [1, 1, 1], "hybrid": {"semanticRatio": 1.0, "embedder": "manual"} }),
)
.await;
snapshot!(documents, @r###"
{
"hits": [

37
meilisearch/tests/vector/openai.rs
View File

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

154
meilisearch/tests/vector/rest.rs
View File

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

3
meilisearch/tests/vector/settings.rs
View File

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

1
meilitool/Cargo.toml
View File

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

444
meilitool/src/main.rs
View File

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

7
milli/Cargo.toml
View File

@ -83,7 +83,7 @@ hf-hub = { git = "https://github.com/dureuill/hf-hub.git", branch = "rust_tls",
tiktoken-rs = "0.5.9"
liquid = "0.26.6"
rhai = { version = "1.19.0", features = ["serde", "no_module", "no_custom_syntax", "no_time", "sync"] }
arroy = "0.4.0"
arroy = { git = "https://github.com/meilisearch/arroy/", rev = "2386594dfb009ce08821a925ccc89fb8e30bf73d" }
rand = "0.8.5"
tracing = "0.1.40"
ureq = { version = "2.10.0", features = ["json"] }
@ -108,6 +108,8 @@ all-tokenizations = [
"charabia/greek",
"charabia/khmer",
"charabia/vietnamese",
"charabia/swedish-recomposition",
"charabia/german-segmentation",
]
# Use POSIX semaphores instead of SysV semaphores in LMDB
@ -140,6 +142,9 @@ khmer = ["charabia/khmer"]
# allow vietnamese specialized tokenization
vietnamese = ["charabia/vietnamese"]
# allow german specialized tokenization
german = ["charabia/german-segmentation"]
# force swedish character recomposition
swedish-recomposition = ["charabia/swedish-recomposition"]

6
milli/src/error.rs
View File

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

60
milli/src/index.rs
View File

@ -21,7 +21,7 @@ use crate::heed_codec::{BEU16StrCodec, FstSetCodec, StrBEU16Codec, StrRefCodec};
use crate::order_by_map::OrderByMap;
use crate::proximity::ProximityPrecision;
use crate::vector::parsed_vectors::RESERVED_VECTORS_FIELD_NAME;
use crate::vector::{Embedding, EmbeddingConfig};
use crate::vector::{ArroyWrapper, Embedding, EmbeddingConfig};
use crate::{
default_criteria, CboRoaringBitmapCodec, Criterion, DocumentId, ExternalDocumentsIds,
FacetDistribution, FieldDistribution, FieldId, FieldIdMapMissingEntry, FieldIdWordCountCodec,
@ -162,7 +162,7 @@ pub struct Index {
/// Maps an embedder name to its id in the arroy store.
pub embedder_category_id: Database<Str, U8>,
/// Vector store based on arroy™.
pub vector_arroy: arroy::Database<arroy::distances::Angular>,
pub vector_arroy: arroy::Database<Unspecified>,
/// Maps the document id to the document as an obkv store.
pub(crate) documents: Database<BEU32, ObkvCodec>,
@ -1622,15 +1622,17 @@ impl Index {
&'a self,
rtxn: &'a RoTxn<'a>,
embedder_id: u8,
) -> impl Iterator<Item = Result<arroy::Reader<'a, arroy::distances::Angular>>> + 'a {
quantized: bool,
) -> impl Iterator<Item = Result<ArroyWrapper>> + 'a {
crate::vector::arroy_db_range_for_embedder(embedder_id).map_while(move |k| {
arroy::Reader::open(rtxn, k, self.vector_arroy)
.map(Some)
.or_else(|e| match e {
arroy::Error::MissingMetadata(_) => Ok(None),
e => Err(e.into()),
})
.transpose()
let reader = ArroyWrapper::new(self.vector_arroy, k, quantized);
// Here we don't care about the dimensions, but we want to know if we can read
// in the database or if its metadata are missing because there is no document with that many vectors.
match reader.dimensions(rtxn) {
Ok(_) => Some(Ok(reader)),
Err(arroy::Error::MissingMetadata(_)) => None,
Err(e) => Some(Err(e.into())),
}
})
}
@ -1652,32 +1654,18 @@ impl Index {
docid: DocumentId,
) -> Result<BTreeMap<String, Vec<Embedding>>> {
let mut res = BTreeMap::new();
for row in self.embedder_category_id.iter(rtxn)? {
let (embedder_name, embedder_id) = row?;
let embedder_id = (embedder_id as u16) << 8;
let mut embeddings = Vec::new();
'vectors: for i in 0..=u8::MAX {
let reader = arroy::Reader::open(rtxn, embedder_id | (i as u16), self.vector_arroy)
.map(Some)
.or_else(|e| match e {
arroy::Error::MissingMetadata(_) => Ok(None),
e => Err(e),
})
.transpose();
let Some(reader) = reader else {
break 'vectors;
};
let embedding = reader?.item_vector(rtxn, docid)?;
if let Some(embedding) = embedding {
embeddings.push(embedding)
} else {
break 'vectors;
}
}
res.insert(embedder_name.to_owned(), embeddings);
let embedding_configs = self.embedding_configs(rtxn)?;
for config in embedding_configs {
let embedder_id = self.embedder_category_id.get(rtxn, &config.name)?.unwrap();
let embeddings = self
.arroy_readers(rtxn, embedder_id, config.config.quantized())
.map_while(|reader| {
reader
.and_then(|r| r.item_vector(rtxn, docid).map_err(|e| e.into()))
.transpose()
})
.collect::<Result<Vec<_>>>()?;
res.insert(config.name.to_owned(), embeddings);
}
Ok(res)
}

4
milli/src/prompt/context.rs
View File

@ -5,7 +5,7 @@ use liquid::{ObjectView, ValueView};
use super::document::Document;
use super::fields::Fields;
use crate::FieldsIdsMap;
use super::FieldsIdsMapWithMetadata;
#[derive(Debug, Clone)]
pub struct Context<'a> {
@ -14,7 +14,7 @@ pub struct Context<'a> {
}
impl<'a> Context<'a> {
pub fn new(document: &'a Document<'a>, field_id_map: &'a FieldsIdsMap) -> Self {
pub fn new(document: &'a Document<'a>, field_id_map: &'a FieldsIdsMapWithMetadata<'a>) -> Self {
Self { document, fields: Fields::new(document, field_id_map) }
}
}

24
milli/src/prompt/fields.rs
View File

@ -4,16 +4,20 @@ use liquid::model::{
use liquid::{ObjectView, ValueView};
use super::document::Document;
use crate::FieldsIdsMap;
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 FieldsIdsMap) -> Self {
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 })
.map(|(document, (fid, name))| FieldValue {
document,
name,
metadata: field_id_map.metadata(fid).unwrap_or_default(),
})
.collect(),
)
}
@ -23,6 +27,7 @@ impl<'a> Fields<'a> {
pub struct FieldValue<'a> {
name: &'a str,
document: &'a Document<'a>,
metadata: FieldMetadata,
}
impl<'a> ValueView for FieldValue<'a> {
@ -74,6 +79,10 @@ impl<'a> FieldValue<'a> {
self.document.get(self.name).unwrap_or(&LiquidValue::Nil)
}
pub fn is_searchable(&self) -> &bool {
&self.metadata.searchable
}
pub fn is_empty(&self) -> bool {
self.size() == 0
}
@ -89,12 +98,14 @@ impl<'a> ObjectView for FieldValue<'a> {
}
fn keys<'k>(&'k self) -> Box<dyn Iterator<Item = KStringCow<'k>> + 'k> {
Box::new(["name", "value"].iter().map(|&x| KStringCow::from_static(x)))
Box::new(["name", "value", "is_searchable"].iter().map(|&x| KStringCow::from_static(x)))
}
fn values<'k>(&'k self) -> Box<dyn Iterator<Item = &'k dyn ValueView> + 'k> {
Box::new(
std::iter::once(self.name() as &dyn ValueView).chain(std::iter::once(self.value())),
std::iter::once(self.name() as &dyn ValueView)
.chain(std::iter::once(self.value()))
.chain(std::iter::once(self.is_searchable() as &dyn ValueView)),
)
}
@ -103,13 +114,14 @@ impl<'a> ObjectView for FieldValue<'a> {
}
fn contains_key(&self, index: &str) -> bool {
index == "name" || index == "value"
index == "name" || index == "value" || index == "is_searchable"
}
fn get<'s>(&'s self, index: &str) -> Option<&'s dyn ValueView> {
match index {
"name" => Some(self.name()),
"value" => Some(self.value()),
"is_searchable" => Some(self.is_searchable()),
_ => None,
}
}

143
milli/src/prompt/mod.rs
View File

@ -4,28 +4,33 @@ pub(crate) mod error;
mod fields;
mod template_checker;
use std::collections::BTreeMap;
use std::convert::TryFrom;
use std::num::NonZeroUsize;
use std::ops::Deref;
use error::{NewPromptError, RenderPromptError};
use self::context::Context;
use self::document::Document;
use crate::update::del_add::DelAdd;
use crate::FieldsIdsMap;
use crate::{FieldId, FieldsIdsMap};
pub struct Prompt {
template: liquid::Template,
template_text: String,
max_bytes: Option<NonZeroUsize>,
}
#[derive(Debug, Clone, serde::Serialize, serde::Deserialize)]
pub struct PromptData {
pub template: String,
pub max_bytes: Option<NonZeroUsize>,
}
impl From<Prompt> for PromptData {
fn from(value: Prompt) -> Self {
Self { template: value.template_text }
Self { template: value.template_text, max_bytes: value.max_bytes }
}
}
@ -33,14 +38,18 @@ impl TryFrom<PromptData> for Prompt {
type Error = NewPromptError;
fn try_from(value: PromptData) -> Result<Self, Self::Error> {
Prompt::new(value.template)
Prompt::new(value.template, value.max_bytes)
}
}
impl Clone for Prompt {
fn clone(&self) -> Self {
let template_text = self.template_text.clone();
Self { template: new_template(&template_text).unwrap(), template_text }
Self {
template: new_template(&template_text).unwrap(),
template_text,
max_bytes: self.max_bytes,
}
}
}
@ -53,25 +62,35 @@ fn default_template() -> liquid::Template {
}
fn default_template_text() -> &'static str {
"{% for field in fields %} \
"{% for field in fields %}\
{% if field.is_searchable and field.value != nil %}\
{{ field.name }}: {{ field.value }}\n\
{% endif %}\
{% endfor %}"
}
pub fn default_max_bytes() -> NonZeroUsize {
NonZeroUsize::new(400).unwrap()
}
impl Default for Prompt {
fn default() -> Self {
Self { template: default_template(), template_text: default_template_text().into() }
Self {
template: default_template(),
template_text: default_template_text().into(),
max_bytes: Some(default_max_bytes()),
}
}
}
impl Default for PromptData {
fn default() -> Self {
Self { template: default_template_text().into() }
Self { template: default_template_text().into(), max_bytes: Some(default_max_bytes()) }
}
}
impl Prompt {
pub fn new(template: String) -> Result<Self, NewPromptError> {
pub fn new(template: String, max_bytes: Option<NonZeroUsize>) -> Result<Self, NewPromptError> {
let this = Self {
template: liquid::ParserBuilder::with_stdlib()
.build()
@ -79,6 +98,7 @@ impl Prompt {
.parse(&template)
.map_err(NewPromptError::cannot_parse_template)?,
template_text: template,
max_bytes,
};
// render template with special object that's OK with `doc.*` and `fields.*`
@ -93,20 +113,72 @@ impl Prompt {
&self,
document: &obkv::KvReaderU16,
side: DelAdd,
field_id_map: &FieldsIdsMap,
field_id_map: &FieldsIdsMapWithMetadata,
) -> Result<String, RenderPromptError> {
let document = Document::new(document, side, field_id_map);
let context = Context::new(&document, field_id_map);
self.template.render(&context).map_err(RenderPromptError::missing_context)
let mut rendered =
self.template.render(&context).map_err(RenderPromptError::missing_context)?;
if let Some(max_bytes) = self.max_bytes {
truncate(&mut rendered, max_bytes.get());
}
Ok(rendered)
}
}
fn truncate(s: &mut String, max_bytes: usize) {
if max_bytes >= s.len() {
return;
}
for i in (0..=max_bytes).rev() {
if s.is_char_boundary(i) {
s.truncate(i);
break;
}
}
}
pub struct FieldsIdsMapWithMetadata<'a> {
fields_ids_map: &'a FieldsIdsMap,
metadata: BTreeMap<FieldId, FieldMetadata>,
}
impl<'a> FieldsIdsMapWithMetadata<'a> {
pub fn new(fields_ids_map: &'a FieldsIdsMap, searchable_fields_ids: &'_ [FieldId]) -> Self {
let mut metadata: BTreeMap<FieldId, FieldMetadata> =
fields_ids_map.ids().map(|id| (id, Default::default())).collect();
for searchable_field_id in searchable_fields_ids {
let Some(metadata) = metadata.get_mut(searchable_field_id) else { continue };
metadata.searchable = true;
}
Self { fields_ids_map, metadata }
}
pub fn metadata(&self, field_id: FieldId) -> Option<FieldMetadata> {
self.metadata.get(&field_id).copied()
}
}
impl<'a> Deref for FieldsIdsMapWithMetadata<'a> {
type Target = FieldsIdsMap;
fn deref(&self) -> &Self::Target {
self.fields_ids_map
}
}
#[derive(Debug, Default, Clone, Copy)]
pub struct FieldMetadata {
pub searchable: bool,
}
#[cfg(test)]
mod test {
use super::Prompt;
use crate::error::FaultSource;
use crate::prompt::error::{NewPromptError, NewPromptErrorKind};
use crate::prompt::truncate;
#[test]
fn default_template() {
@ -116,18 +188,18 @@ mod test {
#[test]
fn empty_template() {
Prompt::new("".into()).unwrap();
Prompt::new("".into(), None).unwrap();
}
#[test]
fn template_ok() {
Prompt::new("{{doc.title}}: {{doc.overview}}".into()).unwrap();
Prompt::new("{{doc.title}}: {{doc.overview}}".into(), None).unwrap();
}
#[test]
fn template_syntax() {
assert!(matches!(
Prompt::new("{{doc.title: {{doc.overview}}".into()),
Prompt::new("{{doc.title: {{doc.overview}}".into(), None),
Err(NewPromptError {
kind: NewPromptErrorKind::CannotParseTemplate(_),
fault: FaultSource::User
@ -138,7 +210,7 @@ mod test {
#[test]
fn template_missing_doc() {
assert!(matches!(
Prompt::new("{{title}}: {{overview}}".into()),
Prompt::new("{{title}}: {{overview}}".into(), None),
Err(NewPromptError {
kind: NewPromptErrorKind::InvalidFieldsInTemplate(_),
fault: FaultSource::User
@ -148,29 +220,62 @@ mod test {
#[test]
fn template_nested_doc() {
Prompt::new("{{doc.actor.firstName}}: {{doc.actor.lastName}}".into()).unwrap();
Prompt::new("{{doc.actor.firstName}}: {{doc.actor.lastName}}".into(), None).unwrap();
}
#[test]
fn template_fields() {
Prompt::new("{% for field in fields %}{{field}}{% endfor %}".into()).unwrap();
Prompt::new("{% for field in fields %}{{field}}{% endfor %}".into(), None).unwrap();
}
#[test]
fn template_fields_ok() {
Prompt::new("{% for field in fields %}{{field.name}}: {{field.value}}{% endfor %}".into())
.unwrap();
Prompt::new(
"{% for field in fields %}{{field.name}}: {{field.value}}{% endfor %}".into(),
None,
)
.unwrap();
}
#[test]
fn template_fields_invalid() {
assert!(matches!(
// intentionally garbled field
Prompt::new("{% for field in fields %}{{field.vaelu}} {% endfor %}".into()),
Prompt::new("{% for field in fields %}{{field.vaelu}} {% endfor %}".into(), None),
Err(NewPromptError {
kind: NewPromptErrorKind::InvalidFieldsInTemplate(_),
fault: FaultSource::User
})
));
}
// todo: test truncation
#[test]
fn template_truncation() {
let mut s = "インテル ザー ビーグル".to_string();
truncate(&mut s, 42);
assert_eq!(s, "インテル ザー ビーグル");
assert_eq!(s.len(), 32);
truncate(&mut s, 32);
assert_eq!(s, "インテル ザー ビーグル");
truncate(&mut s, 31);
assert_eq!(s, "インテル ザー ビーグ");
truncate(&mut s, 30);
assert_eq!(s, "インテル ザー ビーグ");
truncate(&mut s, 28);
assert_eq!(s, "インテル ザー ビー");
truncate(&mut s, 26);
assert_eq!(s, "インテル ザー ビー");
truncate(&mut s, 25);
assert_eq!(s, "インテル ザー ビ");
assert_eq!("イ".len(), 3);
truncate(&mut s, 3);
assert_eq!(s, "イ");
truncate(&mut s, 2);
assert_eq!(s, "");
}
}

33
milli/src/search/facet/facet_distribution.rs
View File

@ -1,4 +1,5 @@
use std::collections::{BTreeMap, HashMap, HashSet};
use std::fmt::Display;
use std::ops::ControlFlow;
use std::{fmt, mem};
@ -37,6 +38,15 @@ pub enum OrderBy {
Count,
}
impl Display for OrderBy {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self {
OrderBy::Lexicographic => f.write_str("alphabetically"),
OrderBy::Count => f.write_str("by count"),
}
}
}
pub struct FacetDistribution<'a> {
facets: Option<HashMap<String, OrderBy>>,
candidates: Option<RoaringBitmap>,
@ -100,7 +110,6 @@ impl<'a> FacetDistribution<'a> {
let mut lexicographic_distribution = BTreeMap::new();
let mut key_buffer: Vec<_> = field_id.to_be_bytes().to_vec();
let distribution_prelength = distribution.len();
let db = self.index.field_id_docid_facet_f64s;
for docid in candidates {
key_buffer.truncate(mem::size_of::<FieldId>());
@ -113,23 +122,21 @@ impl<'a> FacetDistribution<'a> {
for result in iter {
let ((_, _, value), ()) = result?;
*lexicographic_distribution.entry(value.to_string()).or_insert(0) += 1;
if lexicographic_distribution.len() - distribution_prelength
== self.max_values_per_facet
{
break;
}
}
}
distribution.extend(lexicographic_distribution);
distribution.extend(
lexicographic_distribution
.into_iter()
.take(self.max_values_per_facet.saturating_sub(distribution.len())),
);
}
FacetType::String => {
let mut normalized_distribution = BTreeMap::new();
let mut key_buffer: Vec<_> = field_id.to_be_bytes().to_vec();
let db = self.index.field_id_docid_facet_strings;
'outer: for docid in candidates {
for docid in candidates {
key_buffer.truncate(mem::size_of::<FieldId>());
key_buffer.extend_from_slice(&docid.to_be_bytes());
let iter = db
@ -144,14 +151,14 @@ impl<'a> FacetDistribution<'a> {
.or_insert_with(|| (original_value, 0));
*count += 1;
if normalized_distribution.len() == self.max_values_per_facet {
break 'outer;
}
// we'd like to break here if we have enough facet values, but we are collecting them by increasing docid,
// so higher ranked facets could be in later docids
}
}
let iter = normalized_distribution
.into_iter()
.take(self.max_values_per_facet.saturating_sub(distribution.len()))
.map(|(_normalized, (original, count))| (original.to_string(), count));
distribution.extend(iter);
}
@ -467,7 +474,7 @@ mod tests {
.execute()
.unwrap();
milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 1}}"###);
milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2}}"###);
let map = FacetDistribution::new(&txn, &index)
.facets(iter::once(("colour", OrderBy::Count)))

20
milli/src/search/facet/filter.rs
View File

@ -12,7 +12,7 @@ use serde_json::Value;
use super::facet_range_search;
use crate::error::{Error, UserError};
use crate::heed_codec::facet::{
FacetGroupKey, FacetGroupKeyCodec, FacetGroupValueCodec, OrderedF64Codec,
FacetGroupKey, FacetGroupKeyCodec, FacetGroupValue, FacetGroupValueCodec, OrderedF64Codec,
};
use crate::index::db_name::FACET_ID_STRING_DOCIDS;
use crate::{
@ -336,6 +336,24 @@ impl<'a> Filter<'a> {
return Ok(docids);
}
Condition::StartsWith { keyword: _, word } => {
let value = crate::normalize_facet(word.value());
let base = FacetGroupKey { field_id, level: 0, left_bound: value.as_str() };
let docids = strings_db
.prefix_iter(rtxn, &base)?
.map(|result| -> Result<RoaringBitmap> {
match result {
Ok((_facet_group_key, FacetGroupValue { bitmap, .. })) => Ok(bitmap),
Err(_e) => Err(InternalError::from(SerializationError::Decoding {
db_name: Some(FACET_ID_STRING_DOCIDS),
})
.into()),
}
})
.union()?;
return Ok(docids);
}
};
let mut output = RoaringBitmap::new();

4
milli/src/search/hybrid.rs
View File

@ -190,7 +190,7 @@ impl<'a> Search<'a> {
return Ok(return_keyword_results(self.limit, self.offset, keyword_results));
};
// no embedder, no semantic search
let Some(SemanticSearch { vector, embedder_name, embedder }) = semantic else {
let Some(SemanticSearch { vector, embedder_name, embedder, quantized }) = semantic else {
return Ok(return_keyword_results(self.limit, self.offset, keyword_results));
};
@ -212,7 +212,7 @@ impl<'a> Search<'a> {
};
search.semantic =
Some(SemanticSearch { vector: Some(vector_query), embedder_name, embedder });
Some(SemanticSearch { vector: Some(vector_query), embedder_name, embedder, quantized });
// TODO: would be better to have two distinct functions at this point
let vector_results = search.execute()?;

7
milli/src/search/mod.rs
View File

@ -32,6 +32,7 @@ pub struct SemanticSearch {
vector: Option<Vec<f32>>,
embedder_name: String,
embedder: Arc<Embedder>,
quantized: bool,
}
pub struct Search<'a> {
@ -89,9 +90,10 @@ impl<'a> Search<'a> {
&mut self,
embedder_name: String,
embedder: Arc<Embedder>,
quantized: bool,
vector: Option<Vec<f32>>,
) -> &mut Search<'a> {
self.semantic = Some(SemanticSearch { embedder_name, embedder, vector });
self.semantic = Some(SemanticSearch { embedder_name, embedder, quantized, vector });
self
}
@ -206,7 +208,7 @@ impl<'a> Search<'a> {
degraded,
used_negative_operator,
} = match self.semantic.as_ref() {
Some(SemanticSearch { vector: Some(vector), embedder_name, embedder }) => {
Some(SemanticSearch { vector: Some(vector), embedder_name, embedder, quantized }) => {
execute_vector_search(
&mut ctx,
vector,
@ -219,6 +221,7 @@ impl<'a> Search<'a> {
self.limit,
embedder_name,
embedder,
*quantized,
self.time_budget.clone(),
self.ranking_score_threshold,
)?

5
milli/src/search/new/mod.rs
View File

@ -312,6 +312,7 @@ fn get_ranking_rules_for_placeholder_search<'ctx>(
Ok(ranking_rules)
}
#[allow(clippy::too_many_arguments)]
fn get_ranking_rules_for_vector<'ctx>(
ctx: &SearchContext<'ctx>,
sort_criteria: &Option<Vec<AscDesc>>,
@ -320,6 +321,7 @@ fn get_ranking_rules_for_vector<'ctx>(
target: &[f32],
embedder_name: &str,
embedder: &Embedder,
quantized: bool,
) -> Result<Vec<BoxRankingRule<'ctx, PlaceholderQuery>>> {
// query graph search
@ -347,6 +349,7 @@ fn get_ranking_rules_for_vector<'ctx>(
limit_plus_offset,
embedder_name,
embedder,
quantized,
)?;
ranking_rules.push(Box::new(vector_sort));
vector = true;
@ -576,6 +579,7 @@ pub fn execute_vector_search(
length: usize,
embedder_name: &str,
embedder: &Embedder,
quantized: bool,
time_budget: TimeBudget,
ranking_score_threshold: Option<f64>,
) -> Result<PartialSearchResult> {
@ -591,6 +595,7 @@ pub fn execute_vector_search(
vector,
embedder_name,
embedder,
quantized,
)?;
let mut placeholder_search_logger = logger::DefaultSearchLogger;

11
milli/src/search/new/vector_sort.rs
View File

@ -16,6 +16,7 @@ pub struct VectorSort<Q: RankingRuleQueryTrait> {
limit: usize,
distribution_shift: Option<DistributionShift>,
embedder_index: u8,
quantized: bool,
}
impl<Q: RankingRuleQueryTrait> VectorSort<Q> {
@ -26,6 +27,7 @@ impl<Q: RankingRuleQueryTrait> VectorSort<Q> {
limit: usize,
embedder_name: &str,
embedder: &Embedder,
quantized: bool,
) -> Result<Self> {
let embedder_index = ctx
.index
@ -41,6 +43,7 @@ impl<Q: RankingRuleQueryTrait> VectorSort<Q> {
limit,
distribution_shift: embedder.distribution(),
embedder_index,
quantized,
})
}
@ -49,16 +52,12 @@ impl<Q: RankingRuleQueryTrait> VectorSort<Q> {
ctx: &mut SearchContext<'_>,
vector_candidates: &RoaringBitmap,
) -> Result<()> {
let readers: std::result::Result<Vec<_>, _> =
ctx.index.arroy_readers(ctx.txn, self.embedder_index).collect();
let readers = readers?;
let target = &self.target;
let mut results = Vec::new();
for reader in readers.iter() {
for reader in ctx.index.arroy_readers(ctx.txn, self.embedder_index, self.quantized) {
let nns_by_vector =
reader.nns_by_vector(ctx.txn, target, self.limit, None, Some(vector_candidates))?;
reader?.nns_by_vector(ctx.txn, target, self.limit, Some(vector_candidates))?;
results.extend(nns_by_vector.into_iter());
}
results.sort_unstable_by_key(|(_, distance)| OrderedFloat(*distance));

14
milli/src/search/similar.rs
View File

@ -18,9 +18,11 @@ pub struct Similar<'a> {
embedder_name: String,
embedder: Arc<Embedder>,
ranking_score_threshold: Option<f64>,
quantized: bool,
}
impl<'a> Similar<'a> {
#[allow(clippy::too_many_arguments)]
pub fn new(
id: DocumentId,
offset: usize,
@ -29,6 +31,7 @@ impl<'a> Similar<'a> {
rtxn: &'a heed::RoTxn<'a>,
embedder_name: String,
embedder: Arc<Embedder>,
quantized: bool,
) -> Self {
Self {
id,
@ -40,6 +43,7 @@ impl<'a> Similar<'a> {
embedder_name,
embedder,
ranking_score_threshold: None,
quantized,
}
}
@ -67,19 +71,13 @@ impl<'a> Similar<'a> {
.get(self.rtxn, &self.embedder_name)?
.ok_or_else(|| crate::UserError::InvalidEmbedder(self.embedder_name.to_owned()))?;
let readers: std::result::Result<Vec<_>, _> =
self.index.arroy_readers(self.rtxn, embedder_index).collect();
let readers = readers?;
let mut results = Vec::new();
for reader in readers.iter() {
let nns_by_item = reader.nns_by_item(
for reader in self.index.arroy_readers(self.rtxn, embedder_index, self.quantized) {
let nns_by_item = reader?.nns_by_item(
self.rtxn,
self.id,
self.limit + self.offset + 1,
None,
Some(&universe),
)?;
if let Some(mut nns_by_item) = nns_by_item {

126
milli/src/update/index_documents/extract/extract_vector_points.rs
View File

@ -15,14 +15,14 @@ use serde_json::Value;
use super::helpers::{create_writer, writer_into_reader, GrenadParameters};
use crate::error::FaultSource;
use crate::index::IndexEmbeddingConfig;
use crate::prompt::Prompt;
use crate::prompt::{FieldsIdsMapWithMetadata, Prompt};
use crate::update::del_add::{DelAdd, KvReaderDelAdd, KvWriterDelAdd};
use crate::update::settings::InnerIndexSettingsDiff;
use crate::vector::error::{EmbedErrorKind, PossibleEmbeddingMistakes, UnusedVectorsDistribution};
use crate::vector::parsed_vectors::{ParsedVectorsDiff, VectorState, RESERVED_VECTORS_FIELD_NAME};
use crate::vector::settings::{EmbedderAction, ReindexAction};
use crate::vector::settings::ReindexAction;
use crate::vector::{Embedder, Embeddings};
use crate::{try_split_array_at, DocumentId, FieldId, FieldsIdsMap, Result, ThreadPoolNoAbort};
use crate::{try_split_array_at, DocumentId, FieldId, Result, ThreadPoolNoAbort};
/// The length of the elements that are always in the buffer when inserting new values.
const TRUNCATE_SIZE: usize = size_of::<DocumentId>();
@ -189,7 +189,13 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
let reindex_vectors = settings_diff.reindex_vectors();
let old_fields_ids_map = &settings_diff.old.fields_ids_map;
let old_fields_ids_map =
FieldsIdsMapWithMetadata::new(old_fields_ids_map, &settings_diff.old.searchable_fields_ids);
let new_fields_ids_map = &settings_diff.new.fields_ids_map;
let new_fields_ids_map =
FieldsIdsMapWithMetadata::new(new_fields_ids_map, &settings_diff.new.searchable_fields_ids);
// the vector field id may have changed
let old_vectors_fid = old_fields_ids_map.id(RESERVED_VECTORS_FIELD_NAME);
@ -202,65 +208,65 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
if reindex_vectors {
for (name, action) in settings_diff.embedding_config_updates.iter() {
match action {
EmbedderAction::WriteBackToDocuments(_) => continue, // already deleted
EmbedderAction::Reindex(action) => {
let Some((embedder_name, (embedder, prompt))) = configs.remove_entry(name)
else {
tracing::error!(embedder = name, "Requested embedder config not found");
continue;
};
if let Some(action) = action.reindex() {
let Some((embedder_name, (embedder, prompt, _quantized))) =
configs.remove_entry(name)
else {
tracing::error!(embedder = name, "Requested embedder config not found");
continue;
};
// (docid, _index) -> KvWriterDelAdd -> Vector
let manual_vectors_writer = create_writer(
indexer.chunk_compression_type,
indexer.chunk_compression_level,
tempfile::tempfile()?,
);
// (docid, _index) -> KvWriterDelAdd -> Vector
let manual_vectors_writer = create_writer(
indexer.chunk_compression_type,
indexer.chunk_compression_level,
tempfile::tempfile()?,
);
// (docid) -> (prompt)
let prompts_writer = create_writer(
indexer.chunk_compression_type,
indexer.chunk_compression_level,
tempfile::tempfile()?,
);
// (docid) -> (prompt)
let prompts_writer = create_writer(
indexer.chunk_compression_type,
indexer.chunk_compression_level,
tempfile::tempfile()?,
);
// (docid) -> ()
let remove_vectors_writer = create_writer(
indexer.chunk_compression_type,
indexer.chunk_compression_level,
tempfile::tempfile()?,
);
// (docid) -> ()
let remove_vectors_writer = create_writer(
indexer.chunk_compression_type,
indexer.chunk_compression_level,
tempfile::tempfile()?,
);
let action = match action {
ReindexAction::FullReindex => ExtractionAction::SettingsFullReindex,
ReindexAction::RegeneratePrompts => {
let Some((_, old_prompt)) = old_configs.get(name) else {
tracing::error!(embedder = name, "Old embedder config not found");
continue;
};
let action = match action {
ReindexAction::FullReindex => ExtractionAction::SettingsFullReindex,
ReindexAction::RegeneratePrompts => {
let Some((_, old_prompt, _quantized)) = old_configs.get(name) else {
tracing::error!(embedder = name, "Old embedder config not found");
continue;
};
ExtractionAction::SettingsRegeneratePrompts { old_prompt }
}
};
ExtractionAction::SettingsRegeneratePrompts { old_prompt }
}
};
extractors.push(EmbedderVectorExtractor {
embedder_name,
embedder,
prompt,
prompts_writer,
remove_vectors_writer,
manual_vectors_writer,
add_to_user_provided: RoaringBitmap::new(),
action,
});
}
extractors.push(EmbedderVectorExtractor {
embedder_name,
embedder,
prompt,
prompts_writer,
remove_vectors_writer,
manual_vectors_writer,
add_to_user_provided: RoaringBitmap::new(),
action,
});
} else {
continue;
}
}
} else {
// document operation
for (embedder_name, (embedder, prompt)) in configs.into_iter() {
for (embedder_name, (embedder, prompt, _quantized)) in configs.into_iter() {
// (docid, _index) -> KvWriterDelAdd -> Vector
let manual_vectors_writer = create_writer(
indexer.chunk_compression_type,
@ -376,7 +382,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
);
continue;
}
regenerate_prompt(obkv, prompt, new_fields_ids_map)?
regenerate_prompt(obkv, prompt, &new_fields_ids_map)?
}
},
// prompt regeneration is only triggered for existing embedders
@ -393,7 +399,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
regenerate_if_prompt_changed(
obkv,
(old_prompt, prompt),
(old_fields_ids_map, new_fields_ids_map),
(&old_fields_ids_map, &new_fields_ids_map),
)?
} else {
// we can simply ignore user provided vectors as they are not regenerated and are
@ -409,7 +415,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
prompt,
(add_to_user_provided, remove_from_user_provided),
(old, new),
(old_fields_ids_map, new_fields_ids_map),
(&old_fields_ids_map, &new_fields_ids_map),
document_id,
embedder_name,
embedder_is_manual,
@ -479,7 +485,10 @@ fn extract_vector_document_diff(
prompt: &Prompt,
(add_to_user_provided, remove_from_user_provided): (&mut RoaringBitmap, &mut RoaringBitmap),
(old, new): (VectorState, VectorState),
(old_fields_ids_map, new_fields_ids_map): (&FieldsIdsMap, &FieldsIdsMap),
(old_fields_ids_map, new_fields_ids_map): (
&FieldsIdsMapWithMetadata,
&FieldsIdsMapWithMetadata,
),
document_id: impl Fn() -> Value,
embedder_name: &str,
embedder_is_manual: bool,
@ -599,7 +608,10 @@ fn extract_vector_document_diff(
fn regenerate_if_prompt_changed(
obkv: &obkv::KvReader<FieldId>,
(old_prompt, new_prompt): (&Prompt, &Prompt),
(old_fields_ids_map, new_fields_ids_map): (&FieldsIdsMap, &FieldsIdsMap),
(old_fields_ids_map, new_fields_ids_map): (
&FieldsIdsMapWithMetadata,
&FieldsIdsMapWithMetadata,
),
) -> Result<VectorStateDelta> {
let old_prompt =
old_prompt.render(obkv, DelAdd::Deletion, old_fields_ids_map).unwrap_or(Default::default());
@ -614,7 +626,7 @@ fn regenerate_if_prompt_changed(
fn regenerate_prompt(
obkv: &obkv::KvReader<FieldId>,
prompt: &Prompt,
new_fields_ids_map: &FieldsIdsMap,
new_fields_ids_map: &FieldsIdsMapWithMetadata,
) -> Result<VectorStateDelta> {
let prompt = prompt.render(obkv, DelAdd::Addition, new_fields_ids_map)?;

42
milli/src/update/index_documents/mod.rs
View File

@ -37,7 +37,7 @@ use crate::update::index_documents::parallel::ImmutableObkvs;
use crate::update::{
IndexerConfig, UpdateIndexingStep, WordPrefixDocids, WordPrefixIntegerDocids, WordsPrefixesFst,
};
use crate::vector::EmbeddingConfigs;
use crate::vector::{ArroyWrapper, EmbeddingConfigs};
use crate::{CboRoaringBitmapCodec, Index, Object, Result};
static MERGED_DATABASE_COUNT: usize = 7;
@ -673,6 +673,24 @@ where
let number_of_documents = self.index.number_of_documents(self.wtxn)?;
let mut rng = rand::rngs::StdRng::seed_from_u64(42);
// If an embedder wasn't used in the typedchunk but must be binary quantized
// we should insert it in `dimension`
for (name, action) in settings_diff.embedding_config_updates.iter() {
if action.is_being_quantized && !dimension.contains_key(name.as_str()) {
let index = self.index.embedder_category_id.get(self.wtxn, name)?.ok_or(
InternalError::DatabaseMissingEntry {
db_name: "embedder_category_id",
key: None,
},
)?;
let first_id = crate::vector::arroy_db_range_for_embedder(index).next().unwrap();
let reader =
ArroyWrapper::new(self.index.vector_arroy, first_id, action.was_quantized);
let dim = reader.dimensions(self.wtxn)?;
dimension.insert(name.to_string(), dim);
}
}
for (embedder_name, dimension) in dimension {
let wtxn = &mut *self.wtxn;
let vector_arroy = self.index.vector_arroy;
@ -680,13 +698,23 @@ where
let embedder_index = self.index.embedder_category_id.get(wtxn, &embedder_name)?.ok_or(
InternalError::DatabaseMissingEntry { db_name: "embedder_category_id", key: None },
)?;
let embedder_config = settings_diff.embedding_config_updates.get(&embedder_name);
let was_quantized = settings_diff
.old
.embedding_configs
.get(&embedder_name)
.map_or(false, |conf| conf.2);
let is_quantizing = embedder_config.map_or(false, |action| action.is_being_quantized);
pool.install(|| {
for k in crate::vector::arroy_db_range_for_embedder(embedder_index) {
let writer = arroy::Writer::new(vector_arroy, k, dimension);
if writer.need_build(wtxn)? {
writer.build(wtxn, &mut rng, None)?;
} else if writer.is_empty(wtxn)? {
let mut writer = ArroyWrapper::new(vector_arroy, k, was_quantized);
if is_quantizing {
writer.quantize(wtxn, k, dimension)?;
}
if writer.need_build(wtxn, dimension)? {
writer.build(wtxn, &mut rng, dimension)?;
} else if writer.is_empty(wtxn, dimension)? {
break;
}
}
@ -2734,11 +2762,13 @@ mod tests {
api_key: Setting::NotSet,
dimensions: Setting::Set(3),
document_template: Setting::NotSet,
document_template_max_bytes: Setting::NotSet,
url: Setting::NotSet,
request: Setting::NotSet,
response: Setting::NotSet,
distribution: Setting::NotSet,
headers: Setting::NotSet,
binary_quantized: Setting::NotSet,
}),
);
settings.set_embedder_settings(embedders);
@ -2767,7 +2797,7 @@ mod tests {
std::sync::Arc::new(crate::vector::Embedder::new(embedder.embedder_options).unwrap());
let res = index
.search(&rtxn)
.semantic(embedder_name, embedder, Some([0.0, 1.0, 2.0].to_vec()))
.semantic(embedder_name, embedder, false, Some([0.0, 1.0, 2.0].to_vec()))
.execute()
.unwrap();
assert_eq!(res.documents_ids.len(), 3);

32
milli/src/update/index_documents/transform.rs
View File

@ -29,7 +29,8 @@ use crate::update::index_documents::GrenadParameters;
use crate::update::settings::{InnerIndexSettings, InnerIndexSettingsDiff};
use crate::update::{AvailableIds, UpdateIndexingStep};
use crate::vector::parsed_vectors::{ExplicitVectors, VectorOrArrayOfVectors};
use crate::vector::settings::{EmbedderAction, WriteBackToDocuments};
use crate::vector::settings::WriteBackToDocuments;
use crate::vector::ArroyWrapper;
use crate::{
is_faceted_by, FieldDistribution, FieldId, FieldIdMapMissingEntry, FieldsIdsMap, Index, Result,
};
@ -992,19 +993,17 @@ impl<'a, 'i> Transform<'a, 'i> {
None
};
let readers: Result<
BTreeMap<&str, (Vec<arroy::Reader<'_, arroy::distances::Angular>>, &RoaringBitmap)>,
> = settings_diff
let readers: Result<BTreeMap<&str, (Vec<ArroyWrapper>, &RoaringBitmap)>> = settings_diff
.embedding_config_updates
.iter()
.filter_map(|(name, action)| {
if let EmbedderAction::WriteBackToDocuments(WriteBackToDocuments {
embedder_id,
user_provided,
}) = action
if let Some(WriteBackToDocuments { embedder_id, user_provided }) =
action.write_back()
{
let readers: Result<Vec<_>> =
self.index.arroy_readers(wtxn, *embedder_id).collect();
let readers: Result<Vec<_>> = self
.index
.arroy_readers(wtxn, *embedder_id, action.was_quantized)
.collect();
match readers {
Ok(readers) => Some(Ok((name.as_str(), (readers, user_provided)))),
Err(error) => Some(Err(error)),
@ -1107,23 +1106,14 @@ impl<'a, 'i> Transform<'a, 'i> {
}
}
let mut writers = Vec::new();
// delete all vectors from the embedders that need removal
for (_, (readers, _)) in readers {
for reader in readers {
let dimensions = reader.dimensions();
let arroy_index = reader.index();
drop(reader);
let writer = arroy::Writer::new(self.index.vector_arroy, arroy_index, dimensions);
writers.push(writer);
let dimensions = reader.dimensions(wtxn)?;
reader.clear(wtxn, dimensions)?;
}
}
for writer in writers {
writer.clear(wtxn)?;
}
let grenad_params = GrenadParameters {
chunk_compression_type: self.indexer_settings.chunk_compression_type,
chunk_compression_level: self.indexer_settings.chunk_compression_level,

27
milli/src/update/index_documents/typed_chunk.rs
View File

@ -26,6 +26,7 @@ use crate::update::index_documents::helpers::{
as_cloneable_grenad, try_split_array_at, KeepLatestObkv,
};
use crate::update::settings::InnerIndexSettingsDiff;
use crate::vector::ArroyWrapper;
use crate::{
lat_lng_to_xyz, CboRoaringBitmapCodec, DocumentId, FieldId, GeoPoint, Index, InternalError,
Result, SerializationError, U8StrStrCodec,
@ -661,9 +662,14 @@ pub(crate) fn write_typed_chunk_into_index(
let embedder_index = index.embedder_category_id.get(wtxn, &embedder_name)?.ok_or(
InternalError::DatabaseMissingEntry { db_name: "embedder_category_id", key: None },
)?;
let binary_quantized = settings_diff
.old
.embedding_configs
.get(&embedder_name)
.map_or(false, |conf| conf.2);
// FIXME: allow customizing distance
let writers: Vec<_> = crate::vector::arroy_db_range_for_embedder(embedder_index)
.map(|k| arroy::Writer::new(index.vector_arroy, k, expected_dimension))
.map(|k| ArroyWrapper::new(index.vector_arroy, k, binary_quantized))
.collect();
// remove vectors for docids we want them removed
@ -674,7 +680,7 @@ pub(crate) fn write_typed_chunk_into_index(
for writer in &writers {
// Uses invariant: vectors are packed in the first writers.
if !writer.del_item(wtxn, docid)? {
if !writer.del_item(wtxn, expected_dimension, docid)? {
break;
}
}
@ -706,7 +712,7 @@ pub(crate) fn write_typed_chunk_into_index(
)));
}
for (embedding, writer) in embeddings.iter().zip(&writers) {
writer.add_item(wtxn, docid, embedding)?;
writer.add_item(wtxn, expected_dimension, docid, embedding)?;
}
}
@ -729,7 +735,7 @@ pub(crate) fn write_typed_chunk_into_index(
break;
};
if candidate == vector {
writer.del_item(wtxn, docid)?;
writer.del_item(wtxn, expected_dimension, docid)?;
deleted_index = Some(index);
}
}
@ -746,8 +752,13 @@ pub(crate) fn write_typed_chunk_into_index(
if let Some((last_index, vector)) = last_index_with_a_vector {
// unwrap: computed the index from the list of writers
let writer = writers.get(last_index).unwrap();
writer.del_item(wtxn, docid)?;
writers.get(deleted_index).unwrap().add_item(wtxn, docid, &vector)?;
writer.del_item(wtxn, expected_dimension, docid)?;
writers.get(deleted_index).unwrap().add_item(
wtxn,
expected_dimension,
docid,
&vector,
)?;
}
}
}
@ -757,8 +768,8 @@ pub(crate) fn write_typed_chunk_into_index(
// overflow was detected during vector extraction.
for writer in &writers {
if !writer.contains_item(wtxn, docid)? {
writer.add_item(wtxn, docid, &vector)?;
if !writer.contains_item(wtxn, expected_dimension, docid)? {
writer.add_item(wtxn, expected_dimension, docid, &vector)?;
break;
}
}

140
milli/src/update/settings.rs
View File

@ -1,5 +1,6 @@
use std::collections::{BTreeMap, BTreeSet, HashMap, HashSet};
use std::convert::TryInto;
use std::num::NonZeroUsize;
use std::result::Result as StdResult;
use std::sync::Arc;
@ -19,6 +20,7 @@ use crate::index::{
IndexEmbeddingConfig, DEFAULT_MIN_WORD_LEN_ONE_TYPO, DEFAULT_MIN_WORD_LEN_TWO_TYPOS,
};
use crate::order_by_map::OrderByMap;
use crate::prompt::default_max_bytes;
use crate::proximity::ProximityPrecision;
use crate::update::index_documents::IndexDocumentsMethod;
use crate::update::{IndexDocuments, UpdateIndexingStep};
@ -952,7 +954,7 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
let old_configs = self.index.embedding_configs(self.wtxn)?;
let remove_all: Result<BTreeMap<String, EmbedderAction>> = old_configs
.into_iter()
.map(|IndexEmbeddingConfig { name, config: _, user_provided }| -> Result<_> {
.map(|IndexEmbeddingConfig { name, config, user_provided }| -> Result<_> {
let embedder_id =
self.index.embedder_category_id.get(self.wtxn, &name)?.ok_or(
crate::InternalError::DatabaseMissingEntry {
@ -962,10 +964,10 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
)?;
Ok((
name,
EmbedderAction::WriteBackToDocuments(WriteBackToDocuments {
embedder_id,
user_provided,
}),
EmbedderAction::with_write_back(
WriteBackToDocuments { embedder_id, user_provided },
config.quantized(),
),
))
})
.collect();
@ -1002,7 +1004,8 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
match joined {
// updated config
EitherOrBoth::Both((name, (old, user_provided)), (_, new)) => {
let settings_diff = SettingsDiff::from_settings(old, new);
let was_quantized = old.binary_quantized.set().unwrap_or_default();
let settings_diff = SettingsDiff::from_settings(&name, old, new)?;
match settings_diff {
SettingsDiff::Remove => {
tracing::debug!(
@ -1021,25 +1024,29 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
self.index.embedder_category_id.delete(self.wtxn, &name)?;
embedder_actions.insert(
name,
EmbedderAction::WriteBackToDocuments(WriteBackToDocuments {
embedder_id,
user_provided,
}),
EmbedderAction::with_write_back(
WriteBackToDocuments { embedder_id, user_provided },
was_quantized,
),
);
}
SettingsDiff::Reindex { action, updated_settings } => {
SettingsDiff::Reindex { action, updated_settings, quantize } => {
tracing::debug!(
embedder = name,
user_provided = user_provided.len(),
?action,
"reindex embedder"
);
embedder_actions.insert(name.clone(), EmbedderAction::Reindex(action));
embedder_actions.insert(
name.clone(),
EmbedderAction::with_reindex(action, was_quantized)
.with_is_being_quantized(quantize),
);
let new =
validate_embedding_settings(Setting::Set(updated_settings), &name)?;
updated_configs.insert(name, (new, user_provided));
}
SettingsDiff::UpdateWithoutReindex { updated_settings } => {
SettingsDiff::UpdateWithoutReindex { updated_settings, quantize } => {
tracing::debug!(
embedder = name,
user_provided = user_provided.len(),
@ -1047,6 +1054,12 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
);
let new =
validate_embedding_settings(Setting::Set(updated_settings), &name)?;
if quantize {
embedder_actions.insert(
name.clone(),
EmbedderAction::default().with_is_being_quantized(true),
);
}
updated_configs.insert(name, (new, user_provided));
}
}
@ -1065,8 +1078,10 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
&mut setting,
);
let setting = validate_embedding_settings(setting, &name)?;
embedder_actions
.insert(name.clone(), EmbedderAction::Reindex(ReindexAction::FullReindex));
embedder_actions.insert(
name.clone(),
EmbedderAction::with_reindex(ReindexAction::FullReindex, false),
);
updated_configs.insert(name, (setting, RoaringBitmap::new()));
}
}
@ -1080,19 +1095,14 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
let mut find_free_index =
move || free_indices.find(|(_, free)| **free).map(|(index, _)| index as u8);
for (name, action) in embedder_actions.iter() {
match action {
EmbedderAction::Reindex(ReindexAction::RegeneratePrompts) => {
/* cannot be a new embedder, so has to have an id already */
}
EmbedderAction::Reindex(ReindexAction::FullReindex) => {
if self.index.embedder_category_id.get(self.wtxn, name)?.is_none() {
let id = find_free_index()
.ok_or(UserError::TooManyEmbedders(updated_configs.len()))?;
tracing::debug!(embedder = name, id, "assigning free id to new embedder");
self.index.embedder_category_id.put(self.wtxn, name, &id)?;
}
}
EmbedderAction::WriteBackToDocuments(_) => { /* already removed */ }
// ignore actions that are not possible for a new embedder
if matches!(action.reindex(), Some(ReindexAction::FullReindex))
&& self.index.embedder_category_id.get(self.wtxn, name)?.is_none()
{
let id =
find_free_index().ok_or(UserError::TooManyEmbedders(updated_configs.len()))?;
tracing::debug!(embedder = name, id, "assigning free id to new embedder");
self.index.embedder_category_id.put(self.wtxn, name, &id)?;
}
}
let updated_configs: Vec<IndexEmbeddingConfig> = updated_configs
@ -1238,7 +1248,7 @@ impl InnerIndexSettingsDiff {
old_settings: InnerIndexSettings,
new_settings: InnerIndexSettings,
primary_key_id: Option<FieldId>,
embedding_config_updates: BTreeMap<String, EmbedderAction>,
mut embedding_config_updates: BTreeMap<String, EmbedderAction>,
settings_update_only: bool,
) -> Self {
let only_additional_fields = match (
@ -1273,6 +1283,39 @@ impl InnerIndexSettingsDiff {
let cache_user_defined_searchables = old_settings.user_defined_searchable_fields
!= new_settings.user_defined_searchable_fields;
// if the user-defined searchables changed, then we need to reindex prompts.
if cache_user_defined_searchables {
for (embedder_name, (config, _, _quantized)) in
new_settings.embedding_configs.inner_as_ref()
{
let was_quantized =
old_settings.embedding_configs.get(embedder_name).map_or(false, |conf| conf.2);
// skip embedders that don't use document templates
if !config.uses_document_template() {
continue;
}
// note: this could currently be entry.or_insert(..), but we're future-proofing with an explicit match
// this always makes the code clearer by explicitly handling the cases
match embedding_config_updates.entry(embedder_name.clone()) {
std::collections::btree_map::Entry::Vacant(entry) => {
entry.insert(EmbedderAction::with_reindex(
ReindexAction::RegeneratePrompts,
was_quantized,
));
}
std::collections::btree_map::Entry::Occupied(entry) => {
let EmbedderAction {
was_quantized: _,
is_being_quantized: _,
write_back: _, // We are deleting this embedder, so no point in regeneration
reindex: _, // We are already fully reindexing
} = entry.get();
}
};
}
}
InnerIndexSettingsDiff {
old: old_settings,
new: new_settings,
@ -1518,7 +1561,7 @@ fn embedders(embedding_configs: Vec<IndexEmbeddingConfig>) -> Result<EmbeddingCo
.map(
|IndexEmbeddingConfig {
name,
config: EmbeddingConfig { embedder_options, prompt },
config: EmbeddingConfig { embedder_options, prompt, quantized },
..
}| {
let prompt = Arc::new(prompt.try_into().map_err(crate::Error::from)?);
@ -1528,7 +1571,7 @@ fn embedders(embedding_configs: Vec<IndexEmbeddingConfig>) -> Result<EmbeddingCo
.map_err(crate::vector::Error::from)
.map_err(crate::Error::from)?,
);
Ok((name, (embedder, prompt)))
Ok((name, (embedder, prompt, quantized.unwrap_or_default())))
},
)
.collect();
@ -1547,16 +1590,31 @@ fn validate_prompt(
api_key,
dimensions,
document_template: Setting::Set(template),
document_template_max_bytes,
url,
request,
response,
distribution,
headers,
binary_quantized: binary_quantize,
}) => {
let max_bytes = match document_template_max_bytes.set() {
Some(max_bytes) => NonZeroUsize::new(max_bytes).ok_or_else(|| {
crate::error::UserError::InvalidSettingsDocumentTemplateMaxBytes {
embedder_name: name.to_owned(),
}
})?,
None => default_max_bytes(),
};
// validate
let template = crate::prompt::Prompt::new(template)
.map(|prompt| crate::prompt::PromptData::from(prompt).template)
.map_err(|inner| UserError::InvalidPromptForEmbeddings(name.to_owned(), inner))?;
let template = crate::prompt::Prompt::new(
template,
// always specify a max_bytes
Some(max_bytes),
)
.map(|prompt| crate::prompt::PromptData::from(prompt).template)
.map_err(|inner| UserError::InvalidPromptForEmbeddings(name.to_owned(), inner))?;
Ok(Setting::Set(EmbeddingSettings {
source,
@ -1565,11 +1623,13 @@ fn validate_prompt(
api_key,
dimensions,
document_template: Setting::Set(template),
document_template_max_bytes,
url,
request,
response,
distribution,
headers,
binary_quantized: binary_quantize,
}))
}
new => Ok(new),
@ -1589,11 +1649,13 @@ pub fn validate_embedding_settings(
api_key,
dimensions,
document_template,
document_template_max_bytes,
url,
request,
response,
distribution,
headers,
binary_quantized: binary_quantize,
} = settings;
if let Some(0) = dimensions.set() {
@ -1628,11 +1690,13 @@ pub fn validate_embedding_settings(
api_key,
dimensions,
document_template,
document_template_max_bytes,
url,
request,
response,
distribution,
headers,
binary_quantized: binary_quantize,
}));
};
match inferred_source {
@ -1700,6 +1764,12 @@ pub fn validate_embedding_settings(
inferred_source,
name,
)?;
check_unset(
&document_template_max_bytes,
EmbeddingSettings::DOCUMENT_TEMPLATE_MAX_BYTES,
inferred_source,
name,
)?;
check_set(&dimensions, EmbeddingSettings::DIMENSIONS, inferred_source, name)?;
check_unset(&url, EmbeddingSettings::URL, inferred_source, name)?;
@ -1722,11 +1792,13 @@ pub fn validate_embedding_settings(
api_key,
dimensions,
document_template,
document_template_max_bytes,
url,
request,
response,
distribution,
headers,
binary_quantized: binary_quantize,
}))
}

225
milli/src/vector/mod.rs
View File

@ -1,8 +1,12 @@
use std::collections::HashMap;
use std::sync::Arc;
use arroy::distances::{Angular, BinaryQuantizedAngular};
use arroy::ItemId;
use deserr::{DeserializeError, Deserr};
use heed::{RoTxn, RwTxn, Unspecified};
use ordered_float::OrderedFloat;
use roaring::RoaringBitmap;
use serde::{Deserialize, Serialize};
use self::error::{EmbedError, NewEmbedderError};
@ -26,6 +30,171 @@ pub type Embedding = Vec<f32>;
pub const REQUEST_PARALLELISM: usize = 40;
pub struct ArroyWrapper {
quantized: bool,
index: u16,
database: arroy::Database<Unspecified>,
}
impl ArroyWrapper {
pub fn new(database: arroy::Database<Unspecified>, index: u16, quantized: bool) -> Self {
Self { database, index, quantized }
}
pub fn index(&self) -> u16 {
self.index
}
pub fn dimensions(&self, rtxn: &RoTxn) -> Result<usize, arroy::Error> {
if self.quantized {
Ok(arroy::Reader::open(rtxn, self.index, self.quantized_db())?.dimensions())
} else {
Ok(arroy::Reader::open(rtxn, self.index, self.angular_db())?.dimensions())
}
}
pub fn quantize(
&mut self,
wtxn: &mut RwTxn,
index: u16,
dimension: usize,
) -> Result<(), arroy::Error> {
if !self.quantized {
let writer = arroy::Writer::new(self.angular_db(), index, dimension);
writer.prepare_changing_distance::<BinaryQuantizedAngular>(wtxn)?;
self.quantized = true;
}
Ok(())
}
pub fn need_build(&self, rtxn: &RoTxn, dimension: usize) -> Result<bool, arroy::Error> {
if self.quantized {
arroy::Writer::new(self.quantized_db(), self.index, dimension).need_build(rtxn)
} else {
arroy::Writer::new(self.angular_db(), self.index, dimension).need_build(rtxn)
}
}
pub fn build<R: rand::Rng + rand::SeedableRng>(
&self,
wtxn: &mut RwTxn,
rng: &mut R,
dimension: usize,
) -> Result<(), arroy::Error> {
if self.quantized {
arroy::Writer::new(self.quantized_db(), self.index, dimension).build(wtxn, rng, None)
} else {
arroy::Writer::new(self.angular_db(), self.index, dimension).build(wtxn, rng, None)
}
}
pub fn add_item(
&self,
wtxn: &mut RwTxn,
dimension: usize,
item_id: arroy::ItemId,
vector: &[f32],
) -> Result<(), arroy::Error> {
if self.quantized {
arroy::Writer::new(self.quantized_db(), self.index, dimension)
.add_item(wtxn, item_id, vector)
} else {
arroy::Writer::new(self.angular_db(), self.index, dimension)
.add_item(wtxn, item_id, vector)
}
}
pub fn del_item(
&self,
wtxn: &mut RwTxn,
dimension: usize,
item_id: arroy::ItemId,
) -> Result<bool, arroy::Error> {
if self.quantized {
arroy::Writer::new(self.quantized_db(), self.index, dimension).del_item(wtxn, item_id)
} else {
arroy::Writer::new(self.angular_db(), self.index, dimension).del_item(wtxn, item_id)
}
}
pub fn clear(&self, wtxn: &mut RwTxn, dimension: usize) -> Result<(), arroy::Error> {
if self.quantized {
arroy::Writer::new(self.quantized_db(), self.index, dimension).clear(wtxn)
} else {
arroy::Writer::new(self.angular_db(), self.index, dimension).clear(wtxn)
}
}
pub fn is_empty(&self, rtxn: &RoTxn, dimension: usize) -> Result<bool, arroy::Error> {
if self.quantized {
arroy::Writer::new(self.quantized_db(), self.index, dimension).is_empty(rtxn)
} else {
arroy::Writer::new(self.angular_db(), self.index, dimension).is_empty(rtxn)
}
}
pub fn contains_item(
&self,
rtxn: &RoTxn,
dimension: usize,
item: arroy::ItemId,
) -> Result<bool, arroy::Error> {
if self.quantized {
arroy::Writer::new(self.quantized_db(), self.index, dimension).contains_item(rtxn, item)
} else {
arroy::Writer::new(self.angular_db(), self.index, dimension).contains_item(rtxn, item)
}
}
pub fn nns_by_item(
&self,
rtxn: &RoTxn,
item: ItemId,
limit: usize,
filter: Option<&RoaringBitmap>,
) -> Result<Option<Vec<(ItemId, f32)>>, arroy::Error> {
if self.quantized {
arroy::Reader::open(rtxn, self.index, self.quantized_db())?
.nns_by_item(rtxn, item, limit, None, None, filter)
} else {
arroy::Reader::open(rtxn, self.index, self.angular_db())?
.nns_by_item(rtxn, item, limit, None, None, filter)
}
}
pub fn nns_by_vector(
&self,
txn: &RoTxn,
item: &[f32],
limit: usize,
filter: Option<&RoaringBitmap>,
) -> Result<Vec<(ItemId, f32)>, arroy::Error> {
if self.quantized {
arroy::Reader::open(txn, self.index, self.quantized_db())?
.nns_by_vector(txn, item, limit, None, None, filter)
} else {
arroy::Reader::open(txn, self.index, self.angular_db())?
.nns_by_vector(txn, item, limit, None, None, filter)
}
}
pub fn item_vector(&self, rtxn: &RoTxn, docid: u32) -> Result<Option<Vec<f32>>, arroy::Error> {
if self.quantized {
arroy::Reader::open(rtxn, self.index, self.quantized_db())?.item_vector(rtxn, docid)
} else {
arroy::Reader::open(rtxn, self.index, self.angular_db())?.item_vector(rtxn, docid)
}
}
fn angular_db(&self) -> arroy::Database<Angular> {
self.database.remap_data_type()
}
fn quantized_db(&self) -> arroy::Database<BinaryQuantizedAngular> {
self.database.remap_data_type()
}
}
/// One or multiple embeddings stored consecutively in a flat vector.
pub struct Embeddings<F> {
data: Vec<F>,
@ -124,62 +293,48 @@ pub struct EmbeddingConfig {
pub embedder_options: EmbedderOptions,
/// Document template
pub prompt: PromptData,
/// If this embedder is binary quantized
pub quantized: Option<bool>,
// TODO: add metrics and anything needed
}
impl EmbeddingConfig {
pub fn quantized(&self) -> bool {
self.quantized.unwrap_or_default()
}
}
/// Map of embedder configurations.
///
/// Each configuration is mapped to a name.
#[derive(Clone, Default)]
pub struct EmbeddingConfigs(HashMap<String, (Arc<Embedder>, Arc<Prompt>)>);
pub struct EmbeddingConfigs(HashMap<String, (Arc<Embedder>, Arc<Prompt>, bool)>);
impl EmbeddingConfigs {
/// Create the map from its internal component.s
pub fn new(data: HashMap<String, (Arc<Embedder>, Arc<Prompt>)>) -> Self {
pub fn new(data: HashMap<String, (Arc<Embedder>, Arc<Prompt>, bool)>) -> Self {
Self(data)
}
/// Get an embedder configuration and template from its name.
pub fn get(&self, name: &str) -> Option<(Arc<Embedder>, Arc<Prompt>)> {
pub fn get(&self, name: &str) -> Option<(Arc<Embedder>, Arc<Prompt>, bool)> {
self.0.get(name).cloned()
}
/// Get the default embedder configuration, if any.
pub fn get_default(&self) -> Option<(Arc<Embedder>, Arc<Prompt>)> {
self.get(self.get_default_embedder_name())
}
pub fn inner_as_ref(&self) -> &HashMap<String, (Arc<Embedder>, Arc<Prompt>)> {
pub fn inner_as_ref(&self) -> &HashMap<String, (Arc<Embedder>, Arc<Prompt>, bool)> {
&self.0
}
pub fn into_inner(self) -> HashMap<String, (Arc<Embedder>, Arc<Prompt>)> {
pub fn into_inner(self) -> HashMap<String, (Arc<Embedder>, Arc<Prompt>, bool)> {
self.0
}
/// Get the name of the default embedder configuration.
///
/// The default embedder is determined as follows:
///
/// - If there is only one embedder, it is always the default.
/// - If there are multiple embedders and one of them is called `default`, then that one is the default embedder.
/// - In all other cases, there is no default embedder.
pub fn get_default_embedder_name(&self) -> &str {
let mut it = self.0.keys();
let first_name = it.next();
let second_name = it.next();
match (first_name, second_name) {
(None, _) => "default",
(Some(first), None) => first,
(Some(_), Some(_)) => "default",
}
}
}
impl IntoIterator for EmbeddingConfigs {
type Item = (String, (Arc<Embedder>, Arc<Prompt>));
type Item = (String, (Arc<Embedder>, Arc<Prompt>, bool));
type IntoIter = std::collections::hash_map::IntoIter<String, (Arc<Embedder>, Arc<Prompt>)>;
type IntoIter =
std::collections::hash_map::IntoIter<String, (Arc<Embedder>, Arc<Prompt>, bool)>;
fn into_iter(self) -> Self::IntoIter {
self.0.into_iter()
@ -305,6 +460,16 @@ impl Embedder {
Embedder::Rest(embedder) => embedder.distribution(),
}
}
pub fn uses_document_template(&self) -> bool {
match self {
Embedder::HuggingFace(_)
| Embedder::OpenAi(_)
| Embedder::Ollama(_)
| Embedder::Rest(_) => true,
Embedder::UserProvided(_) => false,
}
}
}
/// Describes the mean and sigma of distribution of embedding similarity in the embedding space.

2
milli/src/vector/openai.rs
View File

@ -66,11 +66,11 @@ pub enum EmbeddingModel {
// # WARNING
//
// If ever adding a model, make sure to add it to the list of supported models below.
#[default]
#[serde(rename = "text-embedding-ada-002")]
#[deserr(rename = "text-embedding-ada-002")]
TextEmbeddingAda002,
#[default]
#[serde(rename = "text-embedding-3-small")]
#[deserr(rename = "text-embedding-3-small")]
TextEmbedding3Small,

142
milli/src/vector/settings.rs
View File

@ -1,11 +1,12 @@
use std::collections::BTreeMap;
use std::num::NonZeroUsize;
use deserr::Deserr;
use roaring::RoaringBitmap;
use serde::{Deserialize, Serialize};
use super::{ollama, openai, DistributionShift};
use crate::prompt::PromptData;
use crate::prompt::{default_max_bytes, PromptData};
use crate::update::Setting;
use crate::vector::EmbeddingConfig;
use crate::UserError;
@ -31,9 +32,15 @@ pub struct EmbeddingSettings {
pub dimensions: Setting<usize>,
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[deserr(default)]
pub binary_quantized: Setting<bool>,
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[deserr(default)]
pub document_template: Setting<String>,
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[deserr(default)]
pub document_template_max_bytes: Setting<usize>,
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[deserr(default)]
pub url: Setting<String>,
#[serde(default, skip_serializing_if = "Setting::is_not_set")]
#[deserr(default)]
@ -81,23 +88,63 @@ pub enum ReindexAction {
pub enum SettingsDiff {
Remove,
Reindex { action: ReindexAction, updated_settings: EmbeddingSettings },
UpdateWithoutReindex { updated_settings: EmbeddingSettings },
Reindex { action: ReindexAction, updated_settings: EmbeddingSettings, quantize: bool },
UpdateWithoutReindex { updated_settings: EmbeddingSettings, quantize: bool },
}
pub enum EmbedderAction {
WriteBackToDocuments(WriteBackToDocuments),
Reindex(ReindexAction),
#[derive(Default, Debug)]
pub struct EmbedderAction {
pub was_quantized: bool,
pub is_being_quantized: bool,
pub write_back: Option<WriteBackToDocuments>,
pub reindex: Option<ReindexAction>,
}
impl EmbedderAction {
pub fn is_being_quantized(&self) -> bool {
self.is_being_quantized
}
pub fn write_back(&self) -> Option<&WriteBackToDocuments> {
self.write_back.as_ref()
}
pub fn reindex(&self) -> Option<&ReindexAction> {
self.reindex.as_ref()
}
pub fn with_is_being_quantized(mut self, quantize: bool) -> Self {
self.is_being_quantized = quantize;
self
}
pub fn with_write_back(write_back: WriteBackToDocuments, was_quantized: bool) -> Self {
Self {
was_quantized,
is_being_quantized: false,
write_back: Some(write_back),
reindex: None,
}
}
pub fn with_reindex(reindex: ReindexAction, was_quantized: bool) -> Self {
Self { was_quantized, is_being_quantized: false, write_back: None, reindex: Some(reindex) }
}
}
#[derive(Debug)]
pub struct WriteBackToDocuments {
pub embedder_id: u8,
pub user_provided: RoaringBitmap,
}
impl SettingsDiff {
pub fn from_settings(old: EmbeddingSettings, new: Setting<EmbeddingSettings>) -> Self {
match new {
pub fn from_settings(
embedder_name: &str,
old: EmbeddingSettings,
new: Setting<EmbeddingSettings>,
) -> Result<Self, UserError> {
let ret = match new {
Setting::Set(new) => {
let EmbeddingSettings {
mut source,
@ -111,6 +158,8 @@ impl SettingsDiff {
mut response,
mut distribution,
mut headers,
mut document_template_max_bytes,
binary_quantized: mut binary_quantize,
} = old;
let EmbeddingSettings {
@ -125,8 +174,18 @@ impl SettingsDiff {
response: new_response,
distribution: new_distribution,
headers: new_headers,
document_template_max_bytes: new_document_template_max_bytes,
binary_quantized: new_binary_quantize,
} = new;
if matches!(binary_quantize, Setting::Set(true))
&& matches!(new_binary_quantize, Setting::Set(false))
{
return Err(UserError::InvalidDisableBinaryQuantization {
embedder_name: embedder_name.to_string(),
});
}
let mut reindex_action = None;
// **Warning**: do not use short-circuiting || here, we want all these operations applied
@ -142,6 +201,7 @@ impl SettingsDiff {
&mut request,
&mut response,
&mut document_template,
&mut document_template_max_bytes,
&mut headers,
)
}
@ -165,6 +225,7 @@ impl SettingsDiff {
_ => {}
}
}
let binary_quantize_changed = binary_quantize.apply(new_binary_quantize);
if url.apply(new_url) {
match source {
// do not regenerate on an url change in OpenAI
@ -190,6 +251,23 @@ impl SettingsDiff {
);
}
if document_template_max_bytes.apply(new_document_template_max_bytes) {
let previous_document_template_max_bytes =
document_template_max_bytes.set().unwrap_or(default_max_bytes().get());
let new_document_template_max_bytes =
new_document_template_max_bytes.set().unwrap_or(default_max_bytes().get());
// only reindex if the size increased. Reasoning:
// - size decrease is a performance optimization, so we don't reindex and we keep the more accurate vectors
// - size increase is an accuracy optimization, so we want to reindex
if new_document_template_max_bytes > previous_document_template_max_bytes {
ReindexAction::push_action(
&mut reindex_action,
ReindexAction::RegeneratePrompts,
)
}
}
distribution.apply(new_distribution);
api_key.apply(new_api_key);
headers.apply(new_headers);
@ -206,16 +284,28 @@ impl SettingsDiff {
response,
distribution,
headers,
document_template_max_bytes,
binary_quantized: binary_quantize,
};
match reindex_action {
Some(action) => Self::Reindex { action, updated_settings },
None => Self::UpdateWithoutReindex { updated_settings },
Some(action) => Self::Reindex {
action,
updated_settings,
quantize: binary_quantize_changed,
},
None => Self::UpdateWithoutReindex {
updated_settings,
quantize: binary_quantize_changed,
},
}
}
Setting::Reset => Self::Remove,
Setting::NotSet => Self::UpdateWithoutReindex { updated_settings: old },
}
Setting::NotSet => {
Self::UpdateWithoutReindex { updated_settings: old, quantize: false }
}
};
Ok(ret)
}
}
@ -239,6 +329,7 @@ fn apply_default_for_source(
request: &mut Setting<serde_json::Value>,
response: &mut Setting<serde_json::Value>,
document_template: &mut Setting<String>,
document_template_max_bytes: &mut Setting<usize>,
headers: &mut Setting<BTreeMap<String, String>>,
) {
match source {
@ -286,6 +377,7 @@ fn apply_default_for_source(
*request = Setting::NotSet;
*response = Setting::NotSet;
*document_template = Setting::NotSet;
*document_template_max_bytes = Setting::NotSet;
*headers = Setting::NotSet;
}
Setting::NotSet => {}
@ -316,6 +408,7 @@ impl EmbeddingSettings {
pub const API_KEY: &'static str = "apiKey";
pub const DIMENSIONS: &'static str = "dimensions";
pub const DOCUMENT_TEMPLATE: &'static str = "documentTemplate";
pub const DOCUMENT_TEMPLATE_MAX_BYTES: &'static str = "documentTemplateMaxBytes";
pub const URL: &'static str = "url";
pub const REQUEST: &'static str = "request";
@ -458,7 +551,9 @@ impl std::fmt::Display for EmbedderSource {
impl From<EmbeddingConfig> for EmbeddingSettings {
fn from(value: EmbeddingConfig) -> Self {
let EmbeddingConfig { embedder_options, prompt } = value;
let EmbeddingConfig { embedder_options, prompt, quantized } = value;
let document_template_max_bytes =
Setting::Set(prompt.max_bytes.unwrap_or(default_max_bytes()).get());
match embedder_options {
super::EmbedderOptions::HuggingFace(super::hf::EmbedderOptions {
model,
@ -471,11 +566,13 @@ impl From<EmbeddingConfig> for EmbeddingSettings {
api_key: Setting::NotSet,
dimensions: Setting::NotSet,
document_template: Setting::Set(prompt.template),
document_template_max_bytes,
url: Setting::NotSet,
request: Setting::NotSet,
response: Setting::NotSet,
headers: Setting::NotSet,
distribution: Setting::some_or_not_set(distribution),
binary_quantized: Setting::some_or_not_set(quantized),
},
super::EmbedderOptions::OpenAi(super::openai::EmbedderOptions {
url,
@ -490,11 +587,13 @@ impl From<EmbeddingConfig> for EmbeddingSettings {
api_key: Setting::some_or_not_set(api_key),
dimensions: Setting::some_or_not_set(dimensions),
document_template: Setting::Set(prompt.template),
document_template_max_bytes,
url: Setting::some_or_not_set(url),
request: Setting::NotSet,
response: Setting::NotSet,
headers: Setting::NotSet,
distribution: Setting::some_or_not_set(distribution),
binary_quantized: Setting::some_or_not_set(quantized),
},
super::EmbedderOptions::Ollama(super::ollama::EmbedderOptions {
embedding_model,
@ -509,11 +608,13 @@ impl From<EmbeddingConfig> for EmbeddingSettings {
api_key: Setting::some_or_not_set(api_key),
dimensions: Setting::some_or_not_set(dimensions),
document_template: Setting::Set(prompt.template),
document_template_max_bytes,
url: Setting::some_or_not_set(url),
request: Setting::NotSet,
response: Setting::NotSet,
headers: Setting::NotSet,
distribution: Setting::some_or_not_set(distribution),
binary_quantized: Setting::some_or_not_set(quantized),
},
super::EmbedderOptions::UserProvided(super::manual::EmbedderOptions {
dimensions,
@ -525,11 +626,13 @@ impl From<EmbeddingConfig> for EmbeddingSettings {
api_key: Setting::NotSet,
dimensions: Setting::Set(dimensions),
document_template: Setting::NotSet,
document_template_max_bytes: Setting::NotSet,
url: Setting::NotSet,
request: Setting::NotSet,
response: Setting::NotSet,
headers: Setting::NotSet,
distribution: Setting::some_or_not_set(distribution),
binary_quantized: Setting::some_or_not_set(quantized),
},
super::EmbedderOptions::Rest(super::rest::EmbedderOptions {
api_key,
@ -546,11 +649,13 @@ impl From<EmbeddingConfig> for EmbeddingSettings {
api_key: Setting::some_or_not_set(api_key),
dimensions: Setting::some_or_not_set(dimensions),
document_template: Setting::Set(prompt.template),
document_template_max_bytes,
url: Setting::Set(url),
request: Setting::Set(request),
response: Setting::Set(response),
distribution: Setting::some_or_not_set(distribution),
headers: Setting::Set(headers),
binary_quantized: Setting::some_or_not_set(quantized),
},
}
}
@ -566,13 +671,17 @@ impl From<EmbeddingSettings> for EmbeddingConfig {
api_key,
dimensions,
document_template,
document_template_max_bytes,
url,
request,
response,
distribution,
headers,
binary_quantized,
} = value;
this.quantized = binary_quantized.set();
if let Some(source) = source.set() {
match source {
EmbedderSource::OpenAi => {
@ -648,7 +757,12 @@ impl From<EmbeddingSettings> for EmbeddingConfig {
}
if let Setting::Set(template) = document_template {
this.prompt = PromptData { template }
let max_bytes = document_template_max_bytes
.set()
.and_then(NonZeroUsize::new)
.unwrap_or(default_max_bytes());
this.prompt = PromptData { template, max_bytes: Some(max_bytes) }
}
this