KnnVectorQueryBuilder support for allowUnmappedFields (elastic#107047)

* KnnVectorQueryBuilder support for allowUnmappedFields * Update and rename 106811.yaml to 107047.yaml * Update 107047.yaml * buildkite test * spotless * spotless * Apply suggestions from code review * fixing compilation --------- Co-authored-by: Benjamin Trent <[email protected]> Co-authored-by: Elastic Machine <[email protected]> Co-authored-by: Benjamin Trent <[email protected]>
pgomulka · Jul 10, 2024 · 3bd192c · 3bd192c
1 parent 2901711
commit 3bd192c
Show file tree

Hide file tree

Showing 5 changed files with 63 additions and 3 deletions.
diff --git a/docs/changelog/107047.yaml b/docs/changelog/107047.yaml
@@ -0,0 +1,6 @@
+pr: 107047
+summary: "Search/Mapping: KnnVectorQueryBuilder  support for allowUnmappedFields"
+area: Search
+type: bug
+issues:
+  - 106846
diff --git a/rest-api-spec/src/yamlRestTest/resources/rest-api-spec/test/search.vectors/40_knn_search.yml b/rest-api-spec/src/yamlRestTest/resources/rest-api-spec/test/search.vectors/40_knn_search.yml
@@ -287,6 +287,9 @@ setup:
   - requires:
       cluster_features: "gte_v8.4.0"
       reason: 'kNN added to search endpoint in 8.4'
+  - skip:
+      cluster_features: "gte_v8.16.0"
+      reason: 'non-existent field handling improved in 8.16'
   - do:
       catch: bad_request
       search:
@@ -298,9 +301,28 @@ setup:
             query_vector: [ -0.5, 90.0, -10, 14.8, -156.0 ]
             k: 2
             num_candidates: 3
+
   - match: { error.root_cause.0.type: "query_shard_exception" }
   - match: { error.root_cause.0.reason: "failed to create query: field [nonexistent] does not exist in the mapping" }
 
+---
+"Test nonexistent field is match none":
+  - requires:
+      cluster_features: "gte_v8.16.0"
+      reason: 'non-existent field handling improved in 8.16'
+  - do:
+      search:
+        index: test
+        body:
+          fields: [ "name" ]
+          knn:
+            field: nonexistent
+            query_vector: [ -0.5, 90.0, -10, 14.8, -156.0 ]
+            k: 2
+            num_candidates: 3
+
+  - length: {hits.hits: 0}
+
 ---
 "KNN Vector similarity search only":
   - requires:

diff --git a/...-spec/src/yamlRestTest/resources/rest-api-spec/test/search.vectors/45_knn_search_byte.yml b/...-spec/src/yamlRestTest/resources/rest-api-spec/test/search.vectors/45_knn_search_byte.yml
@@ -148,6 +148,9 @@ setup:
 
 ---
 "Test nonexistent field":
+  - skip:
+      cluster_features: 'gte_v8.16.0'
+      reason: 'non-existent field handling improved in 8.16'
   - do:
       catch: bad_request
       search:
@@ -159,8 +162,26 @@ setup:
             query_vector: [ 1, 0, 0, 0, -1 ]
             k: 2
             num_candidates: 3
+
   - match: { error.root_cause.0.type: "query_shard_exception" }
   - match: { error.root_cause.0.reason: "failed to create query: field [nonexistent] does not exist in the mapping" }
+---
+"Test nonexistent field is match none":
+  - requires:
+      cluster_features: 'gte_v8.16.0'
+      reason: 'non-existent field handling improved in 8.16'
+  - do:
+      search:
+        index: test
+        body:
+          fields: [ "name" ]
+          knn:
+            field: nonexistent
+            query_vector: [ 1, 0, 0, 0, -1 ]
+            k: 2
+            num_candidates: 3
+
+  - length: {hits.hits: 0}
 
 ---
 "Vector similarity search only":

diff --git a/server/src/main/java/org/elasticsearch/search/vectors/KnnVectorQueryBuilder.java b/server/src/main/java/org/elasticsearch/search/vectors/KnnVectorQueryBuilder.java
@@ -10,6 +10,7 @@
 
 import org.apache.lucene.search.BooleanClause;
 import org.apache.lucene.search.BooleanQuery;
+import org.apache.lucene.search.MatchNoDocsQuery;
 import org.apache.lucene.search.Query;
 import org.apache.lucene.search.join.BitSetProducer;
 import org.apache.lucene.search.join.ToChildBlockJoinQuery;
@@ -436,7 +437,7 @@ protected Query doToQuery(SearchExecutionContext context) throws IOException {
             ? Math.round(Math.min(NUM_CANDS_MULTIPLICATIVE_FACTOR * requestSize, NUM_CANDS_LIMIT))
             : numCands;
         if (fieldType == null) {
-            throw new IllegalArgumentException("field [" + fieldName + "] does not exist in the mapping");
+            return new MatchNoDocsQuery();
         }
 
         if (fieldType instanceof DenseVectorFieldType == false) {

diff --git a/...src/test/java/org/elasticsearch/search/vectors/AbstractKnnVectorQueryBuilderTestCase.java b/...src/test/java/org/elasticsearch/search/vectors/AbstractKnnVectorQueryBuilderTestCase.java
@@ -10,6 +10,7 @@
 
 import org.apache.lucene.search.BooleanClause;
 import org.apache.lucene.search.BooleanQuery;
+import org.apache.lucene.search.MatchNoDocsQuery;
 import org.apache.lucene.search.Query;
 import org.elasticsearch.TransportVersion;
 import org.elasticsearch.TransportVersions;
@@ -25,6 +26,7 @@
 import org.elasticsearch.index.query.QueryBuilder;
 import org.elasticsearch.index.query.QueryBuilders;
 import org.elasticsearch.index.query.QueryRewriteContext;
+import org.elasticsearch.index.query.QueryShardException;
 import org.elasticsearch.index.query.Rewriteable;
 import org.elasticsearch.index.query.SearchExecutionContext;
 import org.elasticsearch.index.query.TermQueryBuilder;
@@ -157,8 +159,16 @@ public void testWrongDimension() {
     public void testNonexistentField() {
         SearchExecutionContext context = createSearchExecutionContext();
         KnnVectorQueryBuilder query = new KnnVectorQueryBuilder("nonexistent", new float[] { 1.0f, 1.0f, 1.0f }, 5, 10, null);
-        IllegalArgumentException e = expectThrows(IllegalArgumentException.class, () -> query.doToQuery(context));
-        assertThat(e.getMessage(), containsString("field [nonexistent] does not exist in the mapping"));
+        context.setAllowUnmappedFields(false);
+        QueryShardException e = expectThrows(QueryShardException.class, () -> query.doToQuery(context));
+        assertThat(e.getMessage(), containsString("No field mapping can be found for the field with name [nonexistent]"));
+    }
+
+    public void testNonexistentFieldReturnEmpty() throws IOException {
+        SearchExecutionContext context = createSearchExecutionContext();
+        KnnVectorQueryBuilder query = new KnnVectorQueryBuilder("nonexistent", new float[] { 1.0f, 1.0f, 1.0f }, 5, 10, null);
+        Query queryNone = query.doToQuery(context);
+        assertThat(queryNone, instanceOf(MatchNoDocsQuery.class));
     }
 
     public void testWrongFieldType() {