4649: Don't store the vectors in the documents database r=dureuill a=irevoire

# Pull Request

## Related issue
Fixes https://github.com/meilisearch/meilisearch/issues/4607

## What does this PR do?
- Ensure that anything falling under `_vectors` is NOT searchable, filterable or sortable
- [x] per embedder, add a roaring bitmap of documents that provide "userProvided" embeddings
- [x] in the indexing process in extract_vector_points, set the bit corresponding to the document depending on the "userProvided" subfield in the _vectors field.
- [x] in the document DB in typed chunks, when writing the _vectors field, remove all keys corresponding to an embedder

Co-authored-by: Tamo <tamo@meilisearch.com>
Co-authored-by: Louis Dureuil <louis@meilisearch.com>
This commit is contained in:
meili-bors[bot] 2024-06-17 12:32:03 +00:00 committed by GitHub
commit e9bf4c43a4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
60 changed files with 3920 additions and 1126 deletions

View file

@ -167,6 +167,74 @@ async fn search_bad_hits_per_page() {
"###);
}
#[actix_rt::test]
async fn search_bad_attributes_to_retrieve() {
let server = Server::new().await;
let index = server.index("test");
let (response, code) = index.search_post(json!({"attributesToRetrieve": "doggo"})).await;
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Invalid value type at `.attributesToRetrieve`: expected an array, but found a string: `\"doggo\"`",
"code": "invalid_search_attributes_to_retrieve",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_retrieve"
}
"###);
// Can't make the `attributes_to_retrieve` fail with a get search since it'll accept anything as an array of strings.
}
#[actix_rt::test]
async fn search_bad_retrieve_vectors() {
let server = Server::new().await;
let index = server.index("test");
let (response, code) = index.search_post(json!({"retrieveVectors": "doggo"})).await;
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Invalid value type at `.retrieveVectors`: expected a boolean, but found a string: `\"doggo\"`",
"code": "invalid_search_retrieve_vectors",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_search_retrieve_vectors"
}
"###);
let (response, code) = index.search_post(json!({"retrieveVectors": [true]})).await;
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Invalid value type at `.retrieveVectors`: expected a boolean, but found an array: `[true]`",
"code": "invalid_search_retrieve_vectors",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_search_retrieve_vectors"
}
"###);
let (response, code) = index.search_get("retrieveVectors=").await;
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Invalid value in parameter `retrieveVectors`: could not parse `` as a boolean, expected either `true` or `false`",
"code": "invalid_search_retrieve_vectors",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_search_retrieve_vectors"
}
"###);
let (response, code) = index.search_get("retrieveVectors=doggo").await;
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Invalid value in parameter `retrieveVectors`: could not parse `doggo` as a boolean, expected either `true` or `false`",
"code": "invalid_search_retrieve_vectors",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_search_retrieve_vectors"
}
"###);
}
#[actix_rt::test]
async fn search_bad_attributes_to_crop() {
let server = Server::new().await;

View file

@ -124,29 +124,29 @@ async fn simple_search() {
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2}}),
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2}, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]}},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]}},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]}}]"###);
snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}}},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}}},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}}}]"###);
snapshot!(response["semanticHitCount"], @"0");
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.5}, "showRankingScore": true}),
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.5}, "showRankingScore": true, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_rankingScore":0.9848484848484848},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_rankingScore":0.9472135901451112}]"###);
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":0.9848484848484848},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.9472135901451112}]"###);
snapshot!(response["semanticHitCount"], @"2");
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.8}, "showRankingScore": true}),
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.8}, "showRankingScore": true, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_rankingScore":0.9472135901451112}]"###);
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}]"###);
snapshot!(response["semanticHitCount"], @"3");
}
@ -204,10 +204,10 @@ 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}});
let search = json!({"q": "Captain", "vector": [1.0, 1.0], "showRankingScore": true, "hybrid": {"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":[2.0,3.0]},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_rankingScore":0.9472135901451112}]"###);
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}]"###);
let (response, code) = index
.update_settings(json!({
@ -228,7 +228,7 @@ async fn distribution_shift() {
let (response, code) = index.search_post(search).await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_rankingScore":0.19161224365234375},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_rankingScore":1.1920928955078125e-7},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_rankingScore":1.1920928955078125e-7}]"###);
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.19161224365234375},{"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":1.1920928955078125e-7},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":1.1920928955078125e-7}]"###);
}
#[actix_rt::test]
@ -239,20 +239,23 @@ async fn highlighter() {
let (response, code) = index
.search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
"hybrid": {"semanticRatio": 0.2},
"attributesToHighlight": [
"desc"
"retrieveVectors": true,
"attributesToHighlight": [
"desc",
"_vectors",
],
"highlightPreTag": "**BEGIN**",
"highlightPostTag": "**END**"
"highlightPreTag": "**BEGIN**",
"highlightPostTag": "**END**",
}))
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_formatted":{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":["2.0","3.0"]}}},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_formatted":{"title":"Shazam!","desc":"a **BEGIN**Captain**END** **BEGIN**Marvel**END** ersatz","id":"1","_vectors":{"default":["1.0","3.0"]}}},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_formatted":{"title":"Captain Planet","desc":"He's not part of the **BEGIN**Marvel**END** Cinematic Universe","id":"2","_vectors":{"default":["1.0","2.0"]}}}]"###);
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_formatted":{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"}},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_formatted":{"title":"Shazam!","desc":"a **BEGIN**Captain**END** **BEGIN**Marvel**END** ersatz","id":"1"}},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_formatted":{"title":"Captain Planet","desc":"He's not part of the **BEGIN**Marvel**END** Cinematic Universe","id":"2"}}]"###);
snapshot!(response["semanticHitCount"], @"0");
let (response, code) = index
.search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
"hybrid": {"semanticRatio": 0.8},
"retrieveVectors": true,
"showRankingScore": true,
"attributesToHighlight": [
"desc"
@ -262,13 +265,14 @@ async fn highlighter() {
}))
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_formatted":{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":["2.0","3.0"]}},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_formatted":{"title":"Captain Planet","desc":"He's not part of the **BEGIN**Marvel**END** Cinematic Universe","id":"2","_vectors":{"default":["1.0","2.0"]}},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_formatted":{"title":"Shazam!","desc":"a **BEGIN**Captain**END** **BEGIN**Marvel**END** ersatz","id":"1","_vectors":{"default":["1.0","3.0"]}},"_rankingScore":0.9472135901451112}]"###);
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_formatted":{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},"_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}},"_formatted":{"title":"Captain Planet","desc":"He's not part of the **BEGIN**Marvel**END** Cinematic Universe","id":"2"},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_formatted":{"title":"Shazam!","desc":"a **BEGIN**Captain**END** **BEGIN**Marvel**END** ersatz","id":"1"},"_rankingScore":0.9472135901451112}]"###);
snapshot!(response["semanticHitCount"], @"3");
// no highlighting on full semantic
let (response, code) = index
.search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
"hybrid": {"semanticRatio": 1.0},
"retrieveVectors": true,
"showRankingScore": true,
"attributesToHighlight": [
"desc"
@ -278,7 +282,7 @@ async fn highlighter() {
}))
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_formatted":{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":["2.0","3.0"]}},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_formatted":{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":["1.0","2.0"]}},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_formatted":{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":["1.0","3.0"]}},"_rankingScore":0.9472135901451112}]"###);
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_formatted":{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},"_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}},"_formatted":{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_formatted":{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"},"_rankingScore":0.9472135901451112}]"###);
snapshot!(response["semanticHitCount"], @"3");
}
@ -361,12 +365,12 @@ async fn single_document() {
let (response, code) = index
.search_post(
json!({"vector": [1.0, 3.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true}),
json!({"vector": [1.0, 3.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"][0], @r###"{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_rankingScore":1.0}"###);
snapshot!(response["hits"][0], @r###"{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":1.0}"###);
snapshot!(response["semanticHitCount"], @"1");
}
@ -377,25 +381,25 @@ 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}))
.search_post(json!({"hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_rankingScore":1.0},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_rankingScore":1.0},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_rankingScore":1.0}]"###);
snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":1.0},{"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":1.0},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":1.0}]"###);
snapshot!(response["semanticHitCount"], @"null");
// same with a different semantic ratio
let (response, code) = index
.search_post(json!({"hybrid": {"semanticRatio": 0.76}, "showRankingScore": true}))
.search_post(json!({"hybrid": {"semanticRatio": 0.76}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_rankingScore":1.0},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_rankingScore":1.0},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_rankingScore":1.0}]"###);
snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":1.0},{"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":1.0},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":1.0}]"###);
snapshot!(response["semanticHitCount"], @"null");
// wrong vector dimensions
let (response, code) = index
.search_post(json!({"vector": [1.0, 0.0, 1.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true}))
.search_post(json!({"vector": [1.0, 0.0, 1.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"400 Bad Request");
@ -410,34 +414,34 @@ async fn query_combination() {
// full vector
let (response, code) = index
.search_post(json!({"vector": [1.0, 0.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true}))
.search_post(json!({"vector": [1.0, 0.0], "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_rankingScore":0.7773500680923462},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_rankingScore":0.7236068248748779},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_rankingScore":0.6581138968467712}]"###);
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.7773500680923462},{"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":0.7236068248748779},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.6581138968467712}]"###);
snapshot!(response["semanticHitCount"], @"3");
// full keyword, without a query
let (response, code) = index
.search_post(json!({"vector": [1.0, 0.0], "hybrid": {"semanticRatio": 0.0}, "showRankingScore": true}))
.search_post(json!({"vector": [1.0, 0.0], "hybrid": {"semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_rankingScore":1.0},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_rankingScore":1.0},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_rankingScore":1.0}]"###);
snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":1.0},{"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":1.0},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":1.0}]"###);
snapshot!(response["semanticHitCount"], @"null");
// 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}))
.search_post(json!({"q": "Captain", "vector": [1.0, 0.0], "hybrid": {"semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_rankingScore":0.9848484848484848},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_rankingScore":0.9848484848484848},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_rankingScore":0.9242424242424242}]"###);
snapshot!(response["hits"], @r###"[{"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":0.9848484848484848},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.9848484848484848},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.9242424242424242}]"###);
snapshot!(response["semanticHitCount"], @"null");
// query + vector, no hybrid keyword =>
let (response, code) = index
.search_post(json!({"q": "Captain", "vector": [1.0, 0.0], "showRankingScore": true}))
.search_post(json!({"q": "Captain", "vector": [1.0, 0.0], "showRankingScore": true, "retrieveVectors": true}))
.await;
snapshot!(code, @"400 Bad Request");
@ -453,7 +457,7 @@ 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}),
json!({"q": "Captain", "hybrid": {"semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}),
)
.await;
@ -470,11 +474,93 @@ 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}),
json!({"q": "Planet", "hybrid": {"semanticRatio": 0.99}, "showRankingScore": true, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_rankingScore":0.9242424242424242}]"###);
snapshot!(response["hits"], @r###"[{"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":0.9242424242424242}]"###);
snapshot!(response["semanticHitCount"], @"0");
}
#[actix_rt::test]
async fn retrieve_vectors() {
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}, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
insta::assert_json_snapshot!(response["hits"], {"[]._vectors.default.embeddings" => "[vectors]"}, @r###"
[
{
"title": "Captain Planet",
"desc": "He's not part of the Marvel Cinematic Universe",
"id": "2",
"_vectors": {
"default": {
"embeddings": "[vectors]",
"regenerate": true
}
}
},
{
"title": "Captain Marvel",
"desc": "a Shazam ersatz",
"id": "3",
"_vectors": {
"default": {
"embeddings": "[vectors]",
"regenerate": true
}
}
},
{
"title": "Shazam!",
"desc": "a Captain Marvel ersatz",
"id": "1",
"_vectors": {
"default": {
"embeddings": "[vectors]",
"regenerate": true
}
}
}
]
"###);
// remove `_vectors` from displayed attributes
let (response, code) =
index.update_settings(json!({ "displayedAttributes": ["id", "title", "desc"]} )).await;
assert_eq!(202, code, "{:?}", response);
index.wait_task(response.uid()).await;
let (response, code) = index
.search_post(
json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2}, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
insta::assert_json_snapshot!(response["hits"], {"[]._vectors.default.embeddings" => "[vectors]"}, @r###"
[
{
"title": "Captain Planet",
"desc": "He's not part of the Marvel Cinematic Universe",
"id": "2"
},
{
"title": "Captain Marvel",
"desc": "a Shazam ersatz",
"id": "3"
},
{
"title": "Shazam!",
"desc": "a Captain Marvel ersatz",
"id": "1"
}
]
"###);
}

View file

@ -1290,21 +1290,38 @@ async fn experimental_feature_vector_store() {
index.add_documents(json!(documents), None).await;
index.wait_task(0).await;
let (response, code) = index
.search_post(json!({
index
.search(json!({
"vector": [1.0, 2.0, 3.0],
"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;
index
.search(json!({
"retrieveVectors": true,
"showRankingScore": true
}), |response, code|{
meili_snap::snapshot!(code, @"400 Bad Request");
meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
{
"message": "Passing `retrieveVectors` 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 query 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"
}
"###);
let (response, code) = server.set_features(json!({"vectorStore": true})).await;
meili_snap::snapshot!(code, @"200 OK");
@ -1337,6 +1354,7 @@ async fn experimental_feature_vector_store() {
.search_post(json!({
"vector": [1.0, 2.0, 3.0],
"showRankingScore": true,
"retrieveVectors": true,
}))
.await;
@ -1348,11 +1366,16 @@ async fn experimental_feature_vector_store() {
"title": "Shazam!",
"id": "287947",
"_vectors": {
"manual": [
1.0,
2.0,
3.0
]
"manual": {
"embeddings": [
[
1.0,
2.0,
3.0
]
],
"regenerate": false
}
},
"_rankingScore": 1.0
},
@ -1360,11 +1383,16 @@ async fn experimental_feature_vector_store() {
"title": "Captain Marvel",
"id": "299537",
"_vectors": {
"manual": [
1.0,
2.0,
54.0
]
"manual": {
"embeddings": [
[
1.0,
2.0,
54.0
]
],
"regenerate": false
}
},
"_rankingScore": 0.9129111766815186
},
@ -1372,11 +1400,16 @@ async fn experimental_feature_vector_store() {
"title": "Gläss",
"id": "450465",
"_vectors": {
"manual": [
-100.0,
340.0,
90.0
]
"manual": {
"embeddings": [
[
-100.0,
340.0,
90.0
]
],
"regenerate": false
}
},
"_rankingScore": 0.8106412887573242
},
@ -1384,11 +1417,16 @@ async fn experimental_feature_vector_store() {
"title": "How to Train Your Dragon: The Hidden World",
"id": "166428",
"_vectors": {
"manual": [
-100.0,
231.0,
32.0
]
"manual": {
"embeddings": [
[
-100.0,
231.0,
32.0
]
],
"regenerate": false
}
},
"_rankingScore": 0.7412010431289673
},
@ -1396,11 +1434,16 @@ async fn experimental_feature_vector_store() {
"title": "Escape Room",
"id": "522681",
"_vectors": {
"manual": [
10.0,
-23.0,
32.0
]
"manual": {
"embeddings": [
[
10.0,
-23.0,
32.0
]
],
"regenerate": false
}
},
"_rankingScore": 0.6972063183784485
}