Switch to approximation/two phase approach everywhere in hybrid query

Signed-off-by: Martin Gaievski <[email protected]>
opensearch-project · Nov 21, 2024 · dce2dd3 · dce2dd3
1 parent 0119907
commit dce2dd3
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 1 deletion.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -18,6 +18,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 ### Features
 ### Enhancements
 ### Bug Fixes
+-  Address inconsistent scoring in hybrid query results ([#998](https://github.com/opensearch-project/neural-search/pull/998)) 
 ### Infrastructure
 ### Documentation
 ### Maintenance

diff --git a/src/main/java/org/opensearch/neuralsearch/query/HybridQueryScorer.java b/src/main/java/org/opensearch/neuralsearch/query/HybridQueryScorer.java
@@ -187,7 +187,7 @@ public int docID() {
      */
     public float[] hybridScores() throws IOException {
         float[] scores = new float[numSubqueries];
-        DisiWrapper topList = subScorersPQ.topList();
+        DisiWrapper topList = getSubMatches();
         for (HybridDisiWrapper disiWrapper = (HybridDisiWrapper) topList; disiWrapper != null; disiWrapper =
             (HybridDisiWrapper) disiWrapper.next) {
             // check if this doc has match in the subQuery. If not, add score as 0.0 and continue

diff --git a/src/main/java/org/opensearch/neuralsearch/search/collector/HybridTopScoreDocCollector.java b/src/main/java/org/opensearch/neuralsearch/search/collector/HybridTopScoreDocCollector.java
@@ -108,12 +108,17 @@ public void collect(int doc) throws IOException {
                 }
                 // Increment total hit count which represents unique doc found on the shard
                 totalHits++;
+                hitsThresholdChecker.incrementHitCount();
                 for (int i = 0; i < subScoresByQuery.length; i++) {
                     float score = subScoresByQuery[i];
                     // if score is 0.0 there is no hits for that sub-query
                     if (score == 0) {
                         continue;
                     }
+                    if (hitsThresholdChecker.isThresholdReached() && totalHitsRelation == TotalHits.Relation.EQUAL_TO) {
+                        log.info("reached hits threshold check");
+                        totalHitsRelation = TotalHits.Relation.GREATER_THAN_OR_EQUAL_TO;
+                    }
                     collectedHitsPerSubQuery[i]++;
                     PriorityQueue<ScoreDoc> pq = compoundScores[i];
                     ScoreDoc currentDoc = new ScoreDoc(doc + docBase, score);