jpountz commented on code in PR #11756:
URL: https://github.com/apache/lucene/pull/11756#discussion_r965022161
##########
lucene/core/src/java/org/apache/lucene/search/KnnVectorQuery.java:
##########
@@ -175,9 +176,42 @@ private TopDocs approximateSearch(LeafReaderContext
context, Bits acceptDocs, in
}
// We allow this to be overridden so that tests can check what search
strategy is used
- protected TopDocs exactSearch(LeafReaderContext context, DocIdSetIterator
acceptDocs)
+ protected TopDocs exactSearch(LeafReaderContext context, DocIdSetIterator
acceptIterator)
throws IOException {
- return context.reader().searchNearestVectorsExhaustively(field, target, k,
acceptDocs);
+ FieldInfo fi = context.reader().getFieldInfos().fieldInfo(field);
+ if (fi == null || fi.getVectorDimension() == 0) {
+ // The field does not exist or does not index vectors
+ return NO_RESULTS;
+ }
+
+ VectorScorer vectorScorer = VectorScorer.create(context, fi, target);
+ HitQueue queue = new HitQueue(k, true);
+ ScoreDoc topDoc = queue.top();
+ int doc;
+ while ((doc = acceptIterator.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
+ boolean advanced = vectorScorer.advanceExact(doc);
+ assert advanced;
+
+ float score = vectorScorer.score();
+ if (score >= topDoc.score) {
Review Comment:
This is pre-existing code but I would assume that we only need to update the
priority queue when we find a score that is strictly greater than the current
top entry of the priority queue.
##########
lucene/core/src/java/org/apache/lucene/search/VectorScorer.java:
##########
@@ -0,0 +1,107 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.lucene.search;
+
+import java.io.IOException;
+import org.apache.lucene.index.FieldInfo;
+import org.apache.lucene.index.LeafReaderContext;
+import org.apache.lucene.index.VectorSimilarityFunction;
+import org.apache.lucene.index.VectorValues;
+import org.apache.lucene.util.BytesRef;
+import org.apache.lucene.util.VectorUtil;
+
+/**
+ * Computes the similarity score between a given query vector and different
document vectors. This
+ * is primarily used by {@link org.apache.lucene.search.KnnVectorQuery} to run
an exact, exhaustive
+ * search over the vectors.
+ */
+interface VectorScorer {
+
+ /**
+ * Create a new vector scorer instance.
+ *
+ * @param context the reader context
+ * @param fieldInfo the field to computeinformation on the
+ * @param query the query vector to compute the similarity for
+ */
+ static VectorScorer create(LeafReaderContext context, FieldInfo fieldInfo,
float[] query)
+ throws IOException {
+ VectorValues values = context.reader().getVectorValues(fieldInfo.name);
+ VectorSimilarityFunction similarity =
fieldInfo.getVectorSimilarityFunction();
+ return switch (fieldInfo.getVectorEncoding()) {
+ case BYTE -> new ByteVectorScorer(values, query, similarity);
+ case FLOAT32 -> new FloatVectorScorer(values, query, similarity);
+ };
+ }
+
+ /**
+ * Advance the instance to the given document ID and return true if there is
a value for that
+ * document.
+ */
+ boolean advanceExact(int doc) throws IOException;
+
+ /** Compute the similarity score for the current document. */
+ float score() throws IOException;
+
+ class ByteVectorScorer implements VectorScorer {
+ private final VectorValues values;
+ private final BytesRef query;
+ private final VectorSimilarityFunction similarity;
+
+ protected ByteVectorScorer(
+ VectorValues values, float[] query, VectorSimilarityFunction
similarity) {
+ this.values = values;
+ this.similarity = similarity;
+ this.query = VectorUtil.toBytesRef(query);
+ }
+
+ @Override
+ public boolean advanceExact(int doc) throws IOException {
+ int vectorDoc = values.advance(doc);
Review Comment:
Given that `advance` requires that the target doc ID is strictly beyond the
current doc ID, I think we need to check the current doc ID and only advance if
we're not on or beyond `doc` already.
--
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
