You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@lucene.apache.org by GitBox <gi...@apache.org> on 2022/12/10 14:04:21 UTC
[GitHub] [lucene] jpountz commented on a diff in pull request #12004: Move byte vector queries into new KnnByteVectorQuery
jpountz commented on code in PR #12004:
URL: https://github.com/apache/lucene/pull/12004#discussion_r1045087956
##########
lucene/core/src/java/org/apache/lucene/search/KnnByteVectorQuery.java:
##########
@@ -0,0 +1,124 @@
+/*
+ * 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 java.util.Objects;
+import org.apache.lucene.codecs.KnnVectorsReader;
+import org.apache.lucene.document.KnnVectorField;
+import org.apache.lucene.index.FieldInfo;
+import org.apache.lucene.index.LeafReaderContext;
+import org.apache.lucene.index.VectorEncoding;
+import org.apache.lucene.util.Bits;
+import org.apache.lucene.util.BytesRef;
+
+/**
+ * Uses {@link KnnVectorsReader#search(String, BytesRef, int, Bits, int)} to perform nearest
+ * neighbour search.
+ *
+ * <p>This query also allows for performing a kNN search subject to a filter. In this case, it first
+ * executes the filter for each leaf, then chooses a strategy dynamically:
+ *
+ * <ul>
+ * <li>If the filter cost is less than k, just execute an exact search
+ * <li>Otherwise run a kNN search subject to the filter
+ * <li>If the kNN search visits too many vectors without completing, stop and run an exact search
+ * </ul>
+ */
+public class KnnByteVectorQuery extends AbstractKnnVectorQuery {
+
+ private static final TopDocs NO_RESULTS = TopDocsCollector.EMPTY_TOPDOCS;
+
+ private final BytesRef target;
+
+ /**
+ * Find the <code>k</code> nearest documents to the target vector according to the vectors in the
+ * given field. <code>target</code> vector.
+ *
+ * @param field a field that has been indexed as a {@link KnnVectorField}.
+ * @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 KnnByteVectorQuery(String field, BytesRef target, int k) {
+ this(field, target, k, null);
+ }
+
+ /**
+ * Find the <code>k</code> nearest documents to the target vector according to the vectors in the
+ * given field. <code>target</code> vector.
+ *
+ * @param field a field that has been indexed as a {@link KnnVectorField}.
+ * @param target the target of the search
+ * @param k the number of documents to find
+ * @param filter a filter applied before the vector search
+ * @throws IllegalArgumentException if <code>k</code> is less than 1
+ */
+ public KnnByteVectorQuery(String field, BytesRef target, int k, Query filter) {
+ super(field, k, filter);
+ this.target = target;
+ }
+
+ @Override
+ protected TopDocs approximateSearch(LeafReaderContext context, Bits acceptDocs, int visitedLimit)
+ throws IOException {
+ TopDocs results =
+ context.reader().searchNearestVectors(field, target, k, acceptDocs, visitedLimit);
+ return results != null ? results : NO_RESULTS;
+ }
+
+ @Override
+ VectorScorer createVectorScorer(LeafReaderContext context, FieldInfo fi) throws IOException {
+ if (fi.getVectorEncoding() != VectorEncoding.BYTE) {
+ return null;
+ }
+ return VectorScorer.create(context, fi, target);
+ }
+
+ @Override
+ public String toString(String field) {
+ return getClass().getSimpleName()
+ + ":"
+ + this.field
+ + "["
+ + target.bytes[target.offset]
+ + ",...]["
+ + k
+ + "]";
+ }
+
+ @Override
+ public void visit(QueryVisitor visitor) {
+ if (visitor.acceptField(field)) {
+ visitor.visitLeaf(this);
+ }
+ }
Review Comment:
It looks the same in the parent class, maybe it doesn't need to be overridden?
##########
lucene/core/src/java/org/apache/lucene/search/KnnByteVectorQuery.java:
##########
@@ -0,0 +1,124 @@
+/*
+ * 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 java.util.Objects;
+import org.apache.lucene.codecs.KnnVectorsReader;
+import org.apache.lucene.document.KnnVectorField;
+import org.apache.lucene.index.FieldInfo;
+import org.apache.lucene.index.LeafReaderContext;
+import org.apache.lucene.index.VectorEncoding;
+import org.apache.lucene.util.Bits;
+import org.apache.lucene.util.BytesRef;
+
+/**
+ * Uses {@link KnnVectorsReader#search(String, BytesRef, int, Bits, int)} to perform nearest
+ * neighbour search.
+ *
+ * <p>This query also allows for performing a kNN search subject to a filter. In this case, it first
+ * executes the filter for each leaf, then chooses a strategy dynamically:
+ *
+ * <ul>
+ * <li>If the filter cost is less than k, just execute an exact search
+ * <li>Otherwise run a kNN search subject to the filter
+ * <li>If the kNN search visits too many vectors without completing, stop and run an exact search
+ * </ul>
+ */
+public class KnnByteVectorQuery extends AbstractKnnVectorQuery {
+
+ private static final TopDocs NO_RESULTS = TopDocsCollector.EMPTY_TOPDOCS;
+
+ private final BytesRef target;
+
+ /**
+ * Find the <code>k</code> nearest documents to the target vector according to the vectors in the
+ * given field. <code>target</code> vector.
+ *
+ * @param field a field that has been indexed as a {@link KnnVectorField}.
+ * @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 KnnByteVectorQuery(String field, BytesRef target, int k) {
+ this(field, target, k, null);
+ }
+
+ /**
+ * Find the <code>k</code> nearest documents to the target vector according to the vectors in the
+ * given field. <code>target</code> vector.
+ *
+ * @param field a field that has been indexed as a {@link KnnVectorField}.
+ * @param target the target of the search
+ * @param k the number of documents to find
+ * @param filter a filter applied before the vector search
+ * @throws IllegalArgumentException if <code>k</code> is less than 1
+ */
+ public KnnByteVectorQuery(String field, BytesRef target, int k, Query filter) {
+ super(field, k, filter);
+ this.target = target;
+ }
+
+ @Override
+ protected TopDocs approximateSearch(LeafReaderContext context, Bits acceptDocs, int visitedLimit)
+ throws IOException {
+ TopDocs results =
+ context.reader().searchNearestVectors(field, target, k, acceptDocs, visitedLimit);
+ return results != null ? results : NO_RESULTS;
+ }
+
+ @Override
+ VectorScorer createVectorScorer(LeafReaderContext context, FieldInfo fi) throws IOException {
+ if (fi.getVectorEncoding() != VectorEncoding.BYTE) {
+ return null;
+ }
+ return VectorScorer.create(context, fi, target);
+ }
+
+ @Override
+ public String toString(String field) {
+ return getClass().getSimpleName()
+ + ":"
+ + this.field
+ + "["
+ + target.bytes[target.offset]
+ + ",...]["
+ + k
+ + "]";
+ }
+
+ @Override
+ public void visit(QueryVisitor visitor) {
+ if (visitor.acceptField(field)) {
+ visitor.visitLeaf(this);
+ }
+ }
+
+ @Override
+ public boolean equals(Object o) {
+ if (this == o) return true;
+ if (o == null || getClass() != o.getClass()) return false;
Review Comment:
this case is already covered by the parent class I think?
##########
lucene/core/src/java/org/apache/lucene/codecs/perfield/PerFieldKnnVectorsFormat.java:
##########
@@ -267,6 +268,17 @@ public TopDocs search(String field, float[] target, int k, Bits acceptDocs, int
}
}
+ @Override
+ public TopDocs search(String field, BytesRef target, int k, Bits acceptDocs, int visitedLimit)
+ throws IOException {
+ KnnVectorsReader knnVectorsReader = fields.get(field);
+ if (knnVectorsReader == null) {
Review Comment:
I wonder if this can ever be null, since codec readers should not be called on fields that don't have vectors enabled.
--
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-unsubscribe@lucene.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@lucene.apache.org
For additional commands, e-mail: issues-help@lucene.apache.org