snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-29 16:45:30 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Merge #4352

Browse Source 
4352: Restore highlighting when possible for hybrid search r=ManyTheFish a=dureuill

# Pull Request

## Related issue
Fixes #4351 

## What does this PR do?
- Use `MatchingWords` from keyword search instead of the one from vector search
- New: When `semanticRatio < 1.0`, all words from the query are now highlighted in all results, regardless of their source (keyword or semantic)
- No change: When `semanticRatio == 1.0`, no highlighting is applied, like before this PR

## Draft status

Should we merge this in a v1.6.1 version?


Co-authored-by: Louis Dureuil <louis@meilisearch.com>
This commit is contained in:
meili-bors[bot] 2024-01-24 12:32:16 +00:00 committed by GitHub
commit d77df4ecdb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 47 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
meilisearch/tests/search/hybrid.rs
View File

@ -87,6 +87,52 @@ async fn simple_search() {
snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":[2.0,3.0]},"_semanticScore":0.99029034},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":[1.0,2.0]},"_semanticScore":0.97434163},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":[1.0,3.0]},"_semanticScore":0.9472136}]"###);
}
#[actix_rt::test]
async fn highlighter() {
let server = Server::new().await;
let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
let (response, code) = index
.search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
"hybrid": {"semanticRatio": 0.2},
"attributesToHighlight": [
"desc"
],
"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"]}}}]"###);
let (response, code) = index
.search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
"hybrid": {"semanticRatio": 0.8},
"attributesToHighlight": [
"desc"
],
"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"]}},"_semanticScore":0.99029034},{"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"]}},"_semanticScore":0.97434163},{"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"]}},"_semanticScore":0.9472136}]"###);
// no highlighting on full semantic
let (response, code) = index
.search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
"hybrid": {"semanticRatio": 1.0},
"attributesToHighlight": [
"desc"
],
"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"]}},"_semanticScore":0.99029034},{"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"]}},"_semanticScore":0.97434163},{"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"]}}}]"###);
}
#[actix_rt::test]
async fn invalid_semantic_ratio() {
let server = Server::new().await;

2
milli/src/search/hybrid.rs
View File

@ -102,7 +102,7 @@ impl ScoreWithRatioResult {
}
SearchResult {
matching_words: left.matching_words,
matching_words: right.matching_words,
candidates: left.candidates | right.candidates,
documents_ids,
document_scores,