From 014eaea428f9968b3bb92aa6e674a03d89f3dc05 Mon Sep 17 00:00:00 2001
From: Louis Dureuil <louis@meilisearch.com>
Date: Tue, 23 Jan 2024 14:47:28 +0100
Subject: [PATCH 1/2] Use MatchingWords from keyword search instead of the one
 from vector search

---
 milli/src/search/hybrid.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/milli/src/search/hybrid.rs b/milli/src/search/hybrid.rs
index 67365cf52..b4c79f7f5 100644
--- a/milli/src/search/hybrid.rs
+++ b/milli/src/search/hybrid.rs
@@ -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,

From da7c796be188e4b53690dfa8d53ece286095a7a4 Mon Sep 17 00:00:00 2001
From: Louis Dureuil <louis@meilisearch.com>
Date: Tue, 23 Jan 2024 15:09:49 +0100
Subject: [PATCH 2/2] Add test

---
 meilisearch/tests/search/hybrid.rs | 46 ++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/meilisearch/tests/search/hybrid.rs b/meilisearch/tests/search/hybrid.rs
index 79819cab2..6ea9920f6 100644
--- a/meilisearch/tests/search/hybrid.rs
+++ b/meilisearch/tests/search/hybrid.rs
@@ -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;