dungba88 commented on code in PR #14009: URL: https://github.com/apache/lucene/pull/14009#discussion_r1859817240
########## lucene/core/src/java/org/apache/lucene/search/RerankKnnFloatVectorQuery.java: ########## @@ -0,0 +1,117 @@ +/* + * 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 static org.apache.lucene.search.AbstractKnnVectorQuery.createRewrittenQuery; + +import java.io.IOException; +import java.util.Arrays; +import java.util.Objects; +import org.apache.lucene.index.FieldInfo; +import org.apache.lucene.index.FloatVectorValues; +import org.apache.lucene.index.IndexReader; +import org.apache.lucene.index.VectorSimilarityFunction; + +/** + * A wrapper of KnnFloatVectorQuery which does full-precision reranking. + * + * @lucene.experimental + */ +public class RerankKnnFloatVectorQuery extends Query { + + private final int k; + private final float[] target; + private final KnnFloatVectorQuery query; + + /** + * Execute the KnnFloatVectorQuery and re-rank using full-precision vectors + * + * @param query the KNN query to execute as initial phase + * @param target the target of the search + * @param k the number of documents to find + * @throws IllegalArgumentException if <code>k</code> is less than 1 + */ + public RerankKnnFloatVectorQuery(KnnFloatVectorQuery query, float[] target, int k) { + this.query = query; + this.target = target; + this.k = k; + } + + @Override + public Query rewrite(IndexSearcher indexSearcher) throws IOException { + IndexReader reader = indexSearcher.getIndexReader(); + Query rewritten = indexSearcher.rewrite(query); + // short-circuit: don't re-rank if we already got all possible results + if (query.getK() <= k) { + return rewritten; + } + Weight weight = indexSearcher.createWeight(rewritten, ScoreMode.COMPLETE_NO_SCORES, 1.0f); + HitQueue queue = new HitQueue(k, false); + for (var leaf : reader.leaves()) { Review Comment: Good question, I was using single-thread as a simple version and try to benchmark the latency first, since multi-thread could add some overhead as well. This class only does vector loading and similarity computation for a small set of vectors (k * oversample * num_segments) so it's not as CPU-intensive as the [AbstractKnnVectorQuery](https://github.com/apache/lucene/blob/main/lucene/core/src/java/org/apache/lucene/search/AbstractKnnVectorQuery.java#L93) I'll change this to multi-thread and run the benchmark again. From the below benchmark, the re-ranking phase only adds a trivial amount of latency it might not help much. Also the benchmark code seems to force merge so there's only a single partition, we need to change so that there are multiple partitions. -- 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
