dungba88 commented on code in PR #14009: URL: https://github.com/apache/lucene/pull/14009#discussion_r2164192783
########## lucene/core/src/test/org/apache/lucene/search/TestRescoreTopNQuery.java: ########## @@ -0,0 +1,140 @@ +/* + * 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.util.HashMap; +import java.util.Map; +import java.util.Random; +import org.apache.lucene.codecs.lucene99.Lucene99HnswVectorsFormat; +import org.apache.lucene.document.Document; +import org.apache.lucene.document.Field; +import org.apache.lucene.document.IntField; +import org.apache.lucene.document.KnnFloatVectorField; +import org.apache.lucene.index.DirectoryReader; +import org.apache.lucene.index.IndexReader; +import org.apache.lucene.index.IndexWriter; +import org.apache.lucene.index.IndexWriterConfig; +import org.apache.lucene.index.Term; +import org.apache.lucene.index.VectorSimilarityFunction; +import org.apache.lucene.store.ByteBuffersDirectory; +import org.apache.lucene.store.Directory; +import org.apache.lucene.tests.util.LuceneTestCase; +import org.apache.lucene.tests.util.TestUtil; +import org.junit.Assert; +import org.junit.Before; +import org.junit.Test; + +public class TestRescoreTopNQuery extends LuceneTestCase { + + private static final String FIELD = "vector"; + private static final String RESCORE_FIELD = "vector-rescore"; + private static final VectorSimilarityFunction VECTOR_SIMILARITY_FUNCTION = + VectorSimilarityFunction.COSINE; + private static final int NUM_VECTORS = 1000; + private static final int VECTOR_DIMENSION = 128; + + private Directory directory; + private IndexWriterConfig config; + + @Before + @Override + public void setUp() throws Exception { + super.setUp(); + directory = new ByteBuffersDirectory(); + + // Set up the IndexWriterConfig to use quantized vector storage + config = new IndexWriterConfig(); + config.setCodec(TestUtil.alwaysKnnVectorsFormat(new Lucene99HnswVectorsFormat())); + } + + @Test + public void testInvalidN() { + expectThrows( + IllegalArgumentException.class, + () -> + new RescoreTopNQuery( + new TermQuery(new Term("test")), DoubleValuesSource.constant(0), 0)); + } + + @Test + public void testRescoreField() throws Exception { + Map<Integer, float[]> vectors = new HashMap<>(); + + Random random = random(); + + int numVectors = atLeast(NUM_VECTORS); + int numSegments = random.nextInt(2, 10); + + // Step 1: Index random vectors in quantized format + try (IndexWriter writer = new IndexWriter(directory, config)) { + for (int j = 0; j < numSegments; j++) { + for (int i = 0; i < numVectors; i++) { + float[] vector = randomFloatVector(VECTOR_DIMENSION, random); + float[] rescoreVector = randomFloatVector(VECTOR_DIMENSION, random); + Document doc = new Document(); + int id = j * numVectors + i; + doc.add(new IntField("id", id, Field.Store.YES)); + doc.add(new KnnFloatVectorField(FIELD, vector, VECTOR_SIMILARITY_FUNCTION)); + doc.add( + new KnnFloatVectorField(RESCORE_FIELD, rescoreVector, VECTOR_SIMILARITY_FUNCTION)); + writer.addDocument(doc); + vectors.put(id, rescoreVector); + + writer.flush(); + } + } + } + + // Step 2: Run TwoPhaseKnnVectorQuery with a random target vector + try (IndexReader reader = DirectoryReader.open(directory)) { + IndexSearcher searcher = new IndexSearcher(reader); + float[] targetVector = randomFloatVector(VECTOR_DIMENSION, random); + int k = 10; + double oversample = random.nextFloat(1.5f, 3.0f); + + FloatVectorSimilarityValuesSource valueSource = Review Comment: Good idea, I'll use that to test. -- 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
