Make bbq_hnsw the default index option for dense-vector fields with more than 384 dimensions

docs/reference/elasticsearch/mapping-reference/dense-vector.md

@@ -55,7 +55,7 @@ In many cases, a brute-force kNN search is not efficient enough. For this reason
 
 Unmapped array fields of float elements with size between 128 and 4096 are dynamically mapped as `dense_vector` with a default similariy of `cosine`. You can override the default similarity by explicitly mapping the field as `dense_vector` with the desired similarity.
 
-Indexing is enabled by default for dense vector fields and indexed as `int8_hnsw`. When indexing is enabled, you can define the vector similarity to use in kNN search:
+Indexing is enabled by default for dense vector fields and indexed as `bbq_hnsw` if dimensions are greater than or equal to 384, otherwise they are indexed as `int8_hnsw`. When indexing is enabled, you can define the vector similarity to use in kNN search:
 
 ```console
 PUT my-index-2
@@ -105,7 +105,7 @@ The `dense_vector` type supports quantization to reduce the memory footprint req
 
 When using a quantized format, you may want to oversample and rescore the results to improve accuracy. See [oversampling and rescoring](docs-content://solutions/search/vector/knn.md#dense-vector-knn-search-rescoring) for more information.
 
-To use a quantized index, you can set your index type to `int8_hnsw`, `int4_hnsw`, or `bbq_hnsw`. When indexing `float` vectors, the current default index type is `int8_hnsw`.
+To use a quantized index, you can set your index type to `int8_hnsw`, `int4_hnsw`, or `bbq_hnsw`. When indexing `float` vectors, the current default index type is `bbq_hnsw` for vectors with greater than or equal to 384 dimensions, otherwise it's `int8_hnsw`.
 
 Quantized vectors can use [oversampling and rescoring](docs-content://solutions/search/vector/knn.md#dense-vector-knn-search-rescoring) to improve accuracy on approximate kNN search results.
 
@@ -255,9 +255,9 @@ $$$dense-vector-index-options$$$
 `type`
 :   (Required, string) The type of kNN algorithm to use. Can be either any of:
     * `hnsw` - This utilizes the [HNSW algorithm](https://arxiv.org/abs/1603.09320) for scalable approximate kNN search. This supports all `element_type` values.
-    * `int8_hnsw` - The default index type for float vectors. This utilizes the [HNSW algorithm](https://arxiv.org/abs/1603.09320) in addition to automatically scalar quantization for scalable approximate kNN search with `element_type` of `float`. This can reduce the memory footprint by 4x at the cost of some accuracy. See [Automatically quantize vectors for kNN search](#dense-vector-quantization).
+    * `int8_hnsw` - The default index type for float vectors with less than 384 dimensions. This utilizes the [HNSW algorithm](https://arxiv.org/abs/1603.09320) in addition to automatically scalar quantization for scalable approximate kNN search with `element_type` of `float`. This can reduce the memory footprint by 4x at the cost of some accuracy. See [Automatically quantize vectors for kNN search](#dense-vector-quantization).
     * `int4_hnsw` - This utilizes the [HNSW algorithm](https://arxiv.org/abs/1603.09320) in addition to automatically scalar quantization for scalable approximate kNN search with `element_type` of `float`. This can reduce the memory footprint by 8x at the cost of some accuracy. See [Automatically quantize vectors for kNN search](#dense-vector-quantization).
-    * `bbq_hnsw` - This utilizes the [HNSW algorithm](https://arxiv.org/abs/1603.09320) in addition to automatically binary quantization for scalable approximate kNN search with `element_type` of `float`. This can reduce the memory footprint by 32x at the cost of accuracy. See [Automatically quantize vectors for kNN search](#dense-vector-quantization).
+    * `bbq_hnsw` - The default index type for float vectors with greater than or equal to 384 dimensions. This utilizes the [HNSW algorithm](https://arxiv.org/abs/1603.09320) in addition to automatically binary quantization for scalable approximate kNN search with `element_type` of `float`. This can reduce the memory footprint by 32x at the cost of accuracy. See [Automatically quantize vectors for kNN search](#dense-vector-quantization).
     * `flat` - This utilizes a brute-force search algorithm for exact kNN search. This supports all `element_type` values.
     * `int8_flat` - This utilizes a brute-force search algorithm in addition to automatically scalar quantization. Only supports `element_type` of `float`.
     * `int4_flat` - This utilizes a brute-force search algorithm in addition to automatically half-byte scalar quantization. Only supports `element_type` of `float`.

rest-api-spec/build.gradle

@@ -63,6 +63,7 @@ tasks.named("yamlRestCompatTestTransform").configure ({ task ->
   task.skipTest("cat.shards/10_basic/Help", "sync_id is removed in 9.0")
   task.skipTest("search/500_date_range/from, to, include_lower, include_upper deprecated", "deprecated parameters are removed in 9.0")
   task.skipTest("search.highlight/30_max_analyzed_offset/Plain highlighter with max_analyzed_offset < 0 should FAIL", "semantics of test has changed")
+  task.skipTest("search.vectors/70_dense_vector_telemetry/Field mapping stats with field details", "default dense vector field mapping has changed")
   task.skipTest("range/20_synthetic_source/Double range", "_source.mode mapping attribute is no-op since 9.0.0")
   task.skipTest("range/20_synthetic_source/Float range", "_source.mode mapping attribute is no-op since 9.0.0")
   task.skipTest("range/20_synthetic_source/Integer range", "_source.mode mapping attribute is no-op since 9.0.0")

rest-api-spec/src/yamlRestTest/resources/rest-api-spec/test/search.vectors/70_dense_vector_telemetry.yml

@@ -1,7 +1,8 @@
 setup:
   - requires:
-      cluster_features: [ "gte_v8.4.0" ]
-      reason: "Cluster mappings stats for indexed dense vector was added in 8.4"
+      cluster_features: [ "search.vectors.mappers.default_bbq_hnsw" ]
+      reason: "Test cluster feature 'search.vectors.mappers.default_bbq_hnsw' is required for using bbq as default
+      indexing for vector fields."
   - skip:
       features: headers
 
@@ -13,7 +14,7 @@ setup:
             index.number_of_shards: 2
           mappings:
             properties:
-              vector1:
+              vector_hnsw_explicit:
                 type: dense_vector
                 dims: 768
                 index: true
@@ -23,12 +24,16 @@ setup:
                   type: hnsw
                   m: 16
                   ef_construction: 100
-              vector2:
+              vector_bbq_default:
                 type: dense_vector
                 dims: 1024
                 index: true
                 similarity: dot_product
-              vector3:
+              vector_int8_hnsw_default:
+                type: dense_vector
+                dims: 100
+                index: true
+              vector_no_index:
                 type: dense_vector
                 dims: 100
                 index: false
@@ -52,10 +57,10 @@ setup:
   - do: { cluster.stats: { } }
   - length: { indices.mappings.field_types: 1 }
   - match: { indices.mappings.field_types.0.name: dense_vector }
-  - match: { indices.mappings.field_types.0.count: 4 }
+  - match: { indices.mappings.field_types.0.count: 5 }
   - match: { indices.mappings.field_types.0.index_count: 2 }
-  - match: { indices.mappings.field_types.0.indexed_vector_count: 3 }
-  - match: { indices.mappings.field_types.0.indexed_vector_dim_min: 768 }
+  - match: { indices.mappings.field_types.0.indexed_vector_count: 4 }
+  - match: { indices.mappings.field_types.0.indexed_vector_dim_min: 100 }
   - match: { indices.mappings.field_types.0.indexed_vector_dim_max: 1024 }
 ---
 "Field mapping stats with field details":
@@ -70,15 +75,16 @@ setup:
   - do: { cluster.stats: { } }
   - length: { indices.mappings.field_types: 1 }
   - match: { indices.mappings.field_types.0.name: dense_vector }
-  - match: { indices.mappings.field_types.0.count: 4 }
+  - match: { indices.mappings.field_types.0.count: 5 }
   - match: { indices.mappings.field_types.0.index_count: 2 }
-  - match: { indices.mappings.field_types.0.indexed_vector_count: 3 }
-  - match: { indices.mappings.field_types.0.indexed_vector_dim_min: 768 }
+  - match: { indices.mappings.field_types.0.indexed_vector_count: 4 }
+  - match: { indices.mappings.field_types.0.indexed_vector_dim_min: 100 }
   - match: { indices.mappings.field_types.0.indexed_vector_dim_max: 1024 }
   - match: { indices.mappings.field_types.0.vector_index_type_count.hnsw: 1 }
-  - match: { indices.mappings.field_types.0.vector_index_type_count.int8_hnsw: 2 }
+  - match: { indices.mappings.field_types.0.vector_index_type_count.int8_hnsw: 1 }
+  - match: { indices.mappings.field_types.0.vector_index_type_count.bbq_hnsw: 2 }
   - match: { indices.mappings.field_types.0.vector_index_type_count.not_indexed: 1 }
   - match: { indices.mappings.field_types.0.vector_similarity_type_count.l2_norm: 2 }
   - match: { indices.mappings.field_types.0.vector_similarity_type_count.dot_product: 1 }
-  - match: { indices.mappings.field_types.0.vector_element_type_count.float: 3 }
+  - match: { indices.mappings.field_types.0.vector_element_type_count.float: 4 }
   - match: { indices.mappings.field_types.0.vector_element_type_count.byte: 1 }

server/src/internalClusterTest/java/org/elasticsearch/index/mapper/DynamicMappingIT.java

@@ -53,6 +53,7 @@
 import static org.elasticsearch.index.mapper.MapperService.INDEX_MAPPING_IGNORE_DYNAMIC_BEYOND_LIMIT_SETTING;
 import static org.elasticsearch.index.mapper.MapperService.INDEX_MAPPING_NESTED_FIELDS_LIMIT_SETTING;
 import static org.elasticsearch.index.mapper.MapperService.INDEX_MAPPING_TOTAL_FIELDS_LIMIT_SETTING;
+import static org.elasticsearch.index.mapper.vectors.DenseVectorFieldMapper.BBQ_DIMS_DEFAULT_THRESHOLD;
 import static org.elasticsearch.index.mapper.vectors.DenseVectorFieldMapper.MIN_DIMS_FOR_DYNAMIC_FLOAT_MAPPING;
 import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertAcked;
 import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertHitCount;
@@ -908,6 +909,59 @@ public void testKnnSubObject() throws Exception {
         client().index(
             new IndexRequest("test").source("obj.vector", Randomness.get().doubles(MIN_DIMS_FOR_DYNAMIC_FLOAT_MAPPING, 0.0, 5.0).toArray())
         ).get();
+    }
+
+    public void testDenseVectorDynamicMapping() throws Exception {
+        assertAcked(indicesAdmin().prepareCreate("test").setMapping("""
+            {
+                "dynamic": "true"
+            }
+            """).get());
+
+        client().index(
+            new IndexRequest("test").source("vector_int8", Randomness.get().doubles(BBQ_DIMS_DEFAULT_THRESHOLD - 1, 0.0, 5.0).toArray())
+        ).get();
+        client().index(
+            new IndexRequest("test").source("vector_bbq", Randomness.get().doubles(BBQ_DIMS_DEFAULT_THRESHOLD, 0.0, 5.0).toArray())
+        ).get();
+        Map<String, Object> mappings = indicesAdmin().prepareGetMappings(TEST_REQUEST_TIMEOUT, "test")
+            .get()
+            .mappings()
+            .get("test")
+            .sourceAsMap();
+        assertTrue(new WriteField("properties.vector_int8", () -> mappings).exists());
+        assertTrue(new WriteField("properties.vector_int8.index_options.type", () -> mappings).get(null).toString().equals("int8_hnsw"));
+        assertTrue(new WriteField("properties.vector_bbq", () -> mappings).exists());
+        assertTrue(new WriteField("properties.vector_bbq.index_options.type", () -> mappings).get(null).toString().equals("bbq_hnsw"));
+    }
+
+    public void testBBQDynamicMappingWhenFirstIngestingDoc() throws Exception {
+        assertAcked(indicesAdmin().prepareCreate("test").setMapping("""
+            {
+                "properties": {
+                    "vector": {
+                        "type": "dense_vector"
+                    }
+                }
+            }
+            """).get());
 
+        Map<String, Object> mappings = indicesAdmin().prepareGetMappings(TEST_REQUEST_TIMEOUT, "test")
+            .get()
+            .mappings()
+            .get("test")
+            .sourceAsMap();
+        assertTrue(new WriteField("properties.vector", () -> mappings).exists());
+        assertFalse(new WriteField("properties.vector.index_options.type", () -> mappings).exists());
+
+        client().index(new IndexRequest("test").source("vector", Randomness.get().doubles(BBQ_DIMS_DEFAULT_THRESHOLD, 0.0, 5.0).toArray()))
+            .get();
+        Map<String, Object> updatedMappings = indicesAdmin().prepareGetMappings(TEST_REQUEST_TIMEOUT, "test")
+            .get()
+            .mappings()
+            .get("test")
+            .sourceAsMap();
+        assertTrue(new WriteField("properties.vector", () -> updatedMappings).exists());
+        assertTrue(new WriteField("properties.vector.index_options.type", () -> updatedMappings).get(null).toString().equals("bbq_hnsw"));
     }
 }

server/src/main/java/org/elasticsearch/index/IndexVersions.java

@@ -177,6 +177,7 @@ private static Version parseUnchecked(String version) {
     public static final IndexVersion MAPPER_TEXT_MATCH_ONLY_MULTI_FIELDS_DEFAULT_NOT_STORED = def(9_029_0_00, Version.LUCENE_10_2_1);
     public static final IndexVersion UPGRADE_TO_LUCENE_10_2_2 = def(9_030_0_00, Version.LUCENE_10_2_2);
     public static final IndexVersion SPARSE_VECTOR_PRUNING_INDEX_OPTIONS_SUPPORT = def(9_031_0_00, Version.LUCENE_10_2_2);
+    public static final IndexVersion DEFAULT_DENSE_VECTOR_TO_BBQ_HNSW = def(9_032_0_00, Version.LUCENE_10_2_2);
 
     /*
      * STOP! READ THIS FIRST! No, really,

server/src/main/java/org/elasticsearch/index/mapper/DocumentParser.java

@@ -806,6 +806,7 @@ private static void postProcessDynamicArrayMapping(DocumentParserContext context
                 fieldName,
                 context.indexSettings().getIndexVersionCreated()
             );
+            builder.dimensions(mappers.size());
             DenseVectorFieldMapper denseVectorFieldMapper = builder.build(builderContext);
             context.updateDynamicMappers(fullFieldName, List.of(denseVectorFieldMapper));
         }