Add semanticHitCount

This commit is contained in:
Louis Dureuil 2024-04-03 09:35:07 +02:00
parent 3c6e9851a4
commit 1ff2a2d6fb
No known key found for this signature in database
4 changed files with 108 additions and 36 deletions

View file

@ -760,6 +760,7 @@ impl SearchAggregator {
query: _,
processing_time_ms,
hits_info: _,
semantic_hit_count: _,
facet_distribution: _,
facet_stats: _,
degraded,

View file

@ -385,6 +385,9 @@ pub struct SearchResult {
#[serde(skip_serializing_if = "Option::is_none")]
pub facet_stats: Option<BTreeMap<String, FacetStats>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub semantic_hit_count: Option<u32>,
// These fields are only used for analytics purposes
#[serde(skip)]
pub degraded: bool,
@ -553,16 +556,23 @@ pub fn perform_search(
let (search, is_finite_pagination, max_total_hits, offset) =
prepare_search(index, &rtxn, &query, &search_kind, time_budget)?;
let milli::SearchResult {
documents_ids,
matching_words,
candidates,
document_scores,
degraded,
used_negative_operator,
..
} = match &search_kind {
SearchKind::KeywordOnly | SearchKind::SemanticOnly { .. } => search.execute()?,
let (
milli::SearchResult {
documents_ids,
matching_words,
candidates,
document_scores,
degraded,
used_negative_operator,
},
semantic_hit_count,
) = match &search_kind {
SearchKind::KeywordOnly => (search.execute()?, None),
SearchKind::SemanticOnly { .. } => {
let results = search.execute()?;
let semantic_hit_count = results.document_scores.len() as u32;
(results, Some(semantic_hit_count))
}
SearchKind::Hybrid { semantic_ratio, .. } => search.execute_hybrid(*semantic_ratio)?,
};
@ -760,6 +770,7 @@ pub fn perform_search(
facet_stats,
degraded,
used_negative_operator,
semantic_hit_count,
};
Ok(result)
}

View file

@ -77,6 +77,16 @@ async fn simple_search() {
.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["semanticHitCount"], @"0");
let (response, code) = index
.search_post(
json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.5}}),
)
.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]},"_semanticScore":0.9472136}]"###);
snapshot!(response["semanticHitCount"], @"1");
let (response, code) = index
.search_post(
@ -85,6 +95,7 @@ async fn simple_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]},"_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}]"###);
snapshot!(response["semanticHitCount"], @"3");
}
#[actix_rt::test]
@ -136,6 +147,7 @@ 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"]}}},{"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["semanticHitCount"], @"0");
let (response, code) = index
.search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
@ -149,6 +161,7 @@ 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"]}},"_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}]"###);
snapshot!(response["semanticHitCount"], @"3");
// no highlighting on full semantic
let (response, code) = index
@ -163,6 +176,7 @@ 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"]}},"_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"]}}}]"###);
snapshot!(response["semanticHitCount"], @"3");
}
#[actix_rt::test]
@ -250,4 +264,20 @@ async fn single_document() {
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,"_semanticScore":1.0}"###);
snapshot!(response["semanticHitCount"], @"1");
}
#[actix_rt::test]
async fn query_combination() {
let server = Server::new().await;
let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
// search without query and vector, but with hybrid => still placeholder
let (response, code) = index
.search_post(json!({"hybrid": {"semanticRatio": 1.0}, "showRankingScore": 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,"_semanticScore":1.0}"###);
snapshot!(response["semanticHitCount"], @"1");
}