jmazanec15 commented on code in PR #12050:
URL: https://github.com/apache/lucene/pull/12050#discussion_r1061902422
##########
lucene/core/src/java/org/apache/lucene/codecs/lucene95/Lucene95HnswVectorsWriter.java:
##########
@@ -461,6 +467,126 @@ public void mergeOneField(FieldInfo fieldInfo, MergeState
mergeState) throws IOE
}
}
+ private void maybeInitializeFromGraph(
+ HnswGraphBuilder<?> hnswGraphBuilder, MergeState mergeState, FieldInfo
fieldInfo)
+ throws IOException {
+ int initializerIndex = selectGraphForInitialization(mergeState, fieldInfo);
+ if (initializerIndex == -1) {
+ return;
+ }
+
+ HnswGraph initializerGraph =
+ getHnswGraphFromReader(fieldInfo.name,
mergeState.knnVectorsReaders[initializerIndex]);
+ Map<Integer, Integer> ordinalMapper =
+ getOldToNewOrdinalMap(mergeState, fieldInfo, initializerIndex);
+ hnswGraphBuilder.initializeFromGraph(initializerGraph, ordinalMapper);
+ }
+
+ private int selectGraphForInitialization(MergeState mergeState, FieldInfo
fieldInfo)
+ throws IOException {
+ // Find the KnnVectorReader with the most docs that meets the following
criteria:
+ // 1. Does not contain any deleted docs
+ // 2. Is a Lucene95HnswVectorsReader/PerFieldKnnVectorReader
+ // If no readers exist that meet this criteria, return -1. If they do,
return their index in
+ // merge state
+ int maxCandidateVectorCount = 0;
+ int initializerIndex = -1;
+
+ for (int i = 0; i < mergeState.liveDocs.length; i++) {
+ KnnVectorsReader currKnnVectorsReader = mergeState.knnVectorsReaders[i];
+ if (mergeState.knnVectorsReaders[i]
+ instanceof PerFieldKnnVectorsFormat.FieldsReader candidateReader) {
+ currKnnVectorsReader = candidateReader.getFieldReader(fieldInfo.name);
+ }
+
+ if (!allMatch(mergeState.liveDocs[i])
+ || !(currKnnVectorsReader instanceof Lucene95HnswVectorsReader
candidateReader)) {
+ continue;
+ }
+
+ VectorValues vectorValues =
candidateReader.getVectorValues(fieldInfo.name);
+ if (vectorValues == null) {
+ continue;
+ }
+
+ int candidateVectorCount = vectorValues.size();
+ if (candidateVectorCount > maxCandidateVectorCount) {
+ maxCandidateVectorCount = candidateVectorCount;
+ initializerIndex = i;
+ }
+ }
+ return initializerIndex;
+ }
+
+ private HnswGraph getHnswGraphFromReader(String fieldName, KnnVectorsReader
knnVectorsReader)
+ throws IOException {
+ if (knnVectorsReader instanceof PerFieldKnnVectorsFormat.FieldsReader
perFieldReader
+ && perFieldReader.getFieldReader(fieldName)
+ instanceof Lucene95HnswVectorsReader fieldReader) {
+ return fieldReader.getGraph(fieldName);
+ }
+
+ if (knnVectorsReader instanceof Lucene95HnswVectorsReader) {
+ return ((Lucene95HnswVectorsReader)
knnVectorsReader).getGraph(fieldName);
+ }
+
Review Comment:
Good idea, I will add this comment here
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For additional commands, e-mail: issues-h...@lucene.apache.org
