Skip to content

Refactor VectorScorerFactoryTests to Int7SQVectorScorerFactoryTests #130620

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jul 4, 2025
Merged

Refactor VectorScorerFactoryTests to Int7SQVectorScorerFactoryTests #130620

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6f3b98f
Refactor VectorScorerFactoryTests to Int7SQVectorScorerFactoryTests.java
ChrisHegarty Jul 4, 2025
4890fbb
Merge branch 'main' into int7u_fac_test_refactor
ChrisHegarty Jul 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 3 additions & 12 deletions libs/simdvec/src/test/java/org/elasticsearch/simdvec/AbstractVectorTestCase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@

package org.elasticsearch.simdvec;

import org.apache.lucene.util.quantization.ScalarQuantizedVectorSimilarity;
import org.elasticsearch.test.ESTestCase;
import org.junit.BeforeClass;

Expand Down Expand Up @@ -62,17 +61,9 @@ public static String platformMsg() {
return "JDK=" + jdkVersion + ", os=" + osName + ", arch=" + arch;
}

/** Computes the score using the Lucene implementation. */
public static float luceneScore(
VectorSimilarityType similarityFunc,
byte[] a,
byte[] b,
float correction,
float aOffsetValue,
float bOffsetValue
) {
var scorer = ScalarQuantizedVectorSimilarity.fromVectorSimilarity(VectorSimilarityType.of(similarityFunc), correction, (byte) 7);
return scorer.score(a, aOffsetValue, b, bOffsetValue);
// Support for passing on-heap arrays/segments to native
protected static boolean supportsHeapSegments() {
return Runtime.version().feature() >= 22;
}

/** Converts a float value to a byte array. */
Expand Down
23 changes: 18 additions & 5 deletions ...rch/simdvec/VectorScorerFactoryTests.java → ...mdvec/Int7SQVectorScorerFactoryTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
import org.apache.lucene.util.hnsw.RandomVectorScorerSupplier;
import org.apache.lucene.util.hnsw.UpdateableRandomVectorScorer;
import org.apache.lucene.util.quantization.QuantizedByteVectorValues;
import org.apache.lucene.util.quantization.ScalarQuantizedVectorSimilarity;
import org.apache.lucene.util.quantization.ScalarQuantizer;

import java.io.IOException;
Expand All @@ -47,8 +48,7 @@
import static org.hamcrest.Matchers.equalTo;
import static org.hamcrest.Matchers.greaterThanOrEqualTo;

// @com.carrotsearch.randomizedtesting.annotations.Repeat(iterations = 100)
public class VectorScorerFactoryTests extends AbstractVectorTestCase {
public class Int7SQVectorScorerFactoryTests extends AbstractVectorTestCase {

// bounds of the range of values that can be seen by int7 scalar quantized vectors
static final byte MIN_INT7_VALUE = 0;
Expand Down Expand Up @@ -107,7 +107,7 @@ void testSimpleImpl(long maxChunkSize) throws IOException {
scorer.setScoringOrdinal(0);
assertThat(scorer.score(1), equalTo(expected));

if (Runtime.version().feature() >= 22) {
if (supportsHeapSegments()) {
var qScorer = factory.getInt7SQVectorScorer(VectorSimilarityType.of(sim), values, query1).get();
assertThat(qScorer.score(1), equalTo(expected));
}
Expand Down Expand Up @@ -229,11 +229,11 @@ void testRandomSupplier(long maxChunkSize, Function<Integer, byte[]> byteArraySu
}

public void testRandomScorer() throws IOException {
testRandomScorerImpl(MMapDirectory.DEFAULT_MAX_CHUNK_SIZE, VectorScorerFactoryTests.FLOAT_ARRAY_RANDOM_FUNC);
testRandomScorerImpl(MMapDirectory.DEFAULT_MAX_CHUNK_SIZE, Int7SQVectorScorerFactoryTests.FLOAT_ARRAY_RANDOM_FUNC);
}

public void testRandomScorerMax() throws IOException {
testRandomScorerImpl(MMapDirectory.DEFAULT_MAX_CHUNK_SIZE, VectorScorerFactoryTests.FLOAT_ARRAY_MAX_FUNC);
testRandomScorerImpl(MMapDirectory.DEFAULT_MAX_CHUNK_SIZE, Int7SQVectorScorerFactoryTests.FLOAT_ARRAY_MAX_FUNC);
}

public void testRandomScorerChunkSizeSmall() throws IOException {
Expand Down Expand Up @@ -461,6 +461,19 @@ QuantizedByteVectorValues vectorValues(int dims, int size, IndexInput in, Vector
return new OffHeapQuantizedByteVectorValues.DenseOffHeapVectorValues(dims, size, sq, false, sim, null, slice);
}

/** Computes the score using the Lucene implementation. */
public static float luceneScore(
VectorSimilarityType similarityFunc,
byte[] a,
byte[] b,
float correction,
float aOffsetValue,
float bOffsetValue
) {
var scorer = ScalarQuantizedVectorSimilarity.fromVectorSimilarity(VectorSimilarityType.of(similarityFunc), correction, (byte) 7);
return scorer.score(a, aOffsetValue, b, bOffsetValue);
}

RandomVectorScorerSupplier luceneScoreSupplier(QuantizedByteVectorValues values, VectorSimilarityFunction sim) throws IOException {
return new Lucene99ScalarQuantizedVectorScorer(null).getRandomVectorScorerSupplier(sim, values);
}
Expand Down