Merge branch 'main' into windows-nulls

Author: prdoyle

docs/changelog/128854.yaml

@@ -0,0 +1,11 @@
+pr: 128854
+summary: Mark token pruning for sparse vector as GA
+area: Machine Learning
+type: feature
+issues: []
+highlight:
+  title: Mark Token Pruning for Sparse Vector as GA
+  body: |-
+    Token pruning for sparse_vector queries has been live since 8.13 as tech preview.
+    As of 8.19.0 and 9.1.0, this is now generally available.
+  notable: true

docs/reference/query-languages/query-dsl/query-dsl-sparse-vector-query.md

@@ -62,28 +62,36 @@ GET _search
 `query_vector`
 :   (Optional, dictionary) A dictionary of token-weight pairs representing the precomputed query vector to search. Searching using this query vector will bypass additional inference. Only one of `inference_id` and `query_vector` is allowed.
 
-`prune`
-:   (Optional, boolean) [preview] Whether to perform pruning, omitting the non-significant tokens from the query to improve query performance. If `prune` is true but the `pruning_config` is not specified, pruning will occur but default values will be used. Default: false.
+`prune` {applies_to}`stack: preview 9.0, ga 9.1`
+:   (Optional, boolean) Whether to perform pruning, omitting the non-significant tokens from the query to improve query performance. If `prune` is true but the `pruning_config` is not specified, pruning will occur but default values will be used. Default: false.
 
-`pruning_config`
-:   (Optional, object) [preview] Optional pruning configuration. If enabled, this will omit non-significant tokens from the query in order to improve query performance. This is only used if `prune` is set to `true`. If `prune` is set to `true` but `pruning_config` is not specified, default values will be used.
+`pruning_config` {applies_to}`stack: preview 9.0, ga 9.1`
+:   (Optional, object) Optional pruning configuration. If enabled, this will omit non-significant tokens from the query in order to improve query performance. This is only used if `prune` is set to `true`. If `prune` is set to `true` but `pruning_config` is not specified, default values will be used.
 
     Parameters for `pruning_config` are:
 
     `tokens_freq_ratio_threshold`
-    :   (Optional, integer) [preview] Tokens whose frequency is more than `tokens_freq_ratio_threshold` times the average frequency of all tokens in the specified field are considered outliers and pruned. This value must between 1 and 100. Default: `5`.
+    :   (Optional, integer) Tokens whose frequency is more than `tokens_freq_ratio_threshold` times the average frequency of all tokens in the specified field are considered outliers and pruned. This value must between 1 and 100. Default: `5`.
 
     `tokens_weight_threshold`
-    :   (Optional, float) [preview] Tokens whose weight is less than `tokens_weight_threshold` are considered insignificant and pruned. This value must be between 0 and 1. Default: `0.4`.
+    :   (Optional, float) Tokens whose weight is less than `tokens_weight_threshold` are considered insignificant and pruned. This value must be between 0 and 1. Default: `0.4`.
 
     `only_score_pruned_tokens`
-    :   (Optional, boolean) [preview] If `true` we only input pruned tokens into scoring, and discard non-pruned tokens. It is strongly recommended to set this to `false` for the main query, but this can be set to `true` for a rescore query to get more relevant results. Default: `false`.
+    :   (Optional, boolean) If `true` we only input pruned tokens into scoring, and discard non-pruned tokens. It is strongly recommended to set this to `false` for the main query, but this can be set to `true` for a rescore query to get more relevant results. Default: `false`.
 
     ::::{note}
     The default values for `tokens_freq_ratio_threshold` and `tokens_weight_threshold` were chosen based on tests using ELSERv2 that provided the most optimal results.
     ::::
 
+When token pruning is applied, non-significant tokens will be pruned from the query.
+Non-significant tokens can be defined as tokens that meet both of the following criteria:
+* The token appears much more frequently than most tokens, indicating that it is a very common word and may not benefit the overall search results much.
+* The weight/score is so low that the token is likely not very relevant to the original term
 
+Both the token frequency threshold and weight threshold must show the token is non-significant in order for the token to be pruned.
+This ensures that:
+* The tokens that are kept are frequent enough and have significant scoring.
+* Very infrequent tokens that may not have as high of a score are removed.
 
 ## Example ELSER query [sparse-vector-query-example]
 
@@ -198,7 +206,7 @@ GET my-index/_search
 
 ## Example ELSER query with pruning configuration and rescore [sparse-vector-query-with-pruning-config-and-rescore-example]
 
-The following is an extension to the above example that adds a [preview] pruning configuration to the `sparse_vector` query. The pruning configuration identifies non-significant tokens to prune from the query in order to improve query performance.
+The following is an extension to the above example that adds a pruning configuration to the `sparse_vector` query. The pruning configuration identifies non-significant tokens to prune from the query in order to improve query performance.
 
 Token pruning happens at the shard level. While this should result in the same tokens being labeled as insignificant across shards, this is not guaranteed based on the composition of each shard. Therefore, if you are running `sparse_vector` with a `pruning_config` on a multi-shard index, we strongly recommend adding a [Rescore filtered search results](/reference/elasticsearch/rest-apis/filter-search-results.md#rescore) function with the tokens that were originally pruned from the query. This will help mitigate any shard-level inconsistency with pruned tokens and provide better relevance overall.
 

muted-tests.yml

@@ -565,9 +565,6 @@ tests:
 - class: org.elasticsearch.index.mapper.vectors.DenseVectorFieldMapperTests
   method: testExistsQueryMinimalMapping
   issue: https://github.com/elastic/elasticsearch/issues/129911
-- class: org.elasticsearch.index.mapper.DynamicMappingIT
-  method: testDenseVectorDynamicMapping
-  issue: https://github.com/elastic/elasticsearch/issues/129928
 
 # Examples:
 #

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

@@ -920,19 +920,27 @@ public void testDenseVectorDynamicMapping() throws Exception {
 
         client().index(
             new IndexRequest("test").source("vector_int8", Randomness.get().doubles(BBQ_DIMS_DEFAULT_THRESHOLD - 1, 0.0, 5.0).toArray())
+                .setRefreshPolicy(WriteRequest.RefreshPolicy.IMMEDIATE)
         ).get();
         client().index(
             new IndexRequest("test").source("vector_bbq", Randomness.get().doubles(BBQ_DIMS_DEFAULT_THRESHOLD, 0.0, 5.0).toArray())
+                .setRefreshPolicy(WriteRequest.RefreshPolicy.IMMEDIATE)
         ).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"));
+
+        assertBusy(() -> {
+            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 {
@@ -954,14 +962,19 @@ public void testBBQDynamicMappingWhenFirstIngestingDoc() throws Exception {
         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"));
+        client().index(
+            new IndexRequest("test").source("vector", Randomness.get().doubles(BBQ_DIMS_DEFAULT_THRESHOLD, 0.0, 5.0).toArray())
+                .setRefreshPolicy(WriteRequest.RefreshPolicy.IMMEDIATE)
+        ).get();
+
+        assertBusy(() -> {
+            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("").toString().equals("bbq_hnsw"));
+        });
     }
 }

server/src/main/java/org/elasticsearch/TransportVersions.java

@@ -314,6 +314,7 @@ static TransportVersion def(int id) {
     public static final TransportVersion ML_INFERENCE_CUSTOM_SERVICE_INPUT_TYPE = def(9_105_0_00);
     public static final TransportVersion ML_INFERENCE_SAGEMAKER_ELASTIC = def(9_106_0_00);
     public static final TransportVersion SPARSE_VECTOR_FIELD_PRUNING_OPTIONS = def(9_107_0_00);
+    public static final TransportVersion CLUSTER_STATE_PROJECTS_SETTINGS = def(9_108_0_00);
 
     /*
      * STOP! READ THIS FIRST! No, really,

server/src/main/java/org/elasticsearch/cluster/ClusterModule.java

@@ -28,6 +28,7 @@
 import org.elasticsearch.cluster.metadata.RepositoriesMetadata;
 import org.elasticsearch.cluster.metadata.StreamsMetadata;
 import org.elasticsearch.cluster.project.ProjectResolver;
+import org.elasticsearch.cluster.project.ProjectStateRegistry;
 import org.elasticsearch.cluster.routing.DelayedAllocationService;
 import org.elasticsearch.cluster.routing.ShardRouting;
 import org.elasticsearch.cluster.routing.ShardRoutingRoleStrategy;
@@ -292,6 +293,7 @@ public static List<Entry> getNamedWriteables() {
             RegisteredPolicySnapshots::new,
             RegisteredPolicySnapshots.RegisteredSnapshotsDiff::new
         );
+        registerClusterCustom(entries, ProjectStateRegistry.TYPE, ProjectStateRegistry::new, ProjectStateRegistry::readDiffFrom);
         // Secrets
         registerClusterCustom(entries, ClusterSecrets.TYPE, ClusterSecrets::new, ClusterSecrets::readDiffFrom);
         registerProjectCustom(entries, ProjectSecrets.TYPE, ProjectSecrets::new, ProjectSecrets::readDiffFrom);

server/src/main/java/org/elasticsearch/cluster/ClusterState.java

@@ -1047,7 +1047,7 @@ public Builder(ClusterState state) {
         public Builder(ClusterName clusterName) {
             this.compatibilityVersions = new HashMap<>();
             this.nodeFeatures = new HashMap<>();
-            customs = ImmutableOpenMap.builder();
+            this.customs = ImmutableOpenMap.builder();
             this.clusterName = clusterName;
         }
 
@@ -1330,7 +1330,6 @@ public void writeTo(StreamOutput out) throws IOException {
     }
 
     private static class ClusterStateDiff implements Diff<ClusterState> {
-
         private final long toVersion;
 
         private final String fromUuid;

server/src/main/java/org/elasticsearch/cluster/ProjectState.java

@@ -12,8 +12,10 @@
 import org.elasticsearch.cluster.block.ClusterBlocks;
 import org.elasticsearch.cluster.metadata.ProjectId;
 import org.elasticsearch.cluster.metadata.ProjectMetadata;
+import org.elasticsearch.cluster.project.ProjectStateRegistry;
 import org.elasticsearch.cluster.routing.RoutingTable;
 import org.elasticsearch.common.Strings;
+import org.elasticsearch.common.settings.Settings;
 
 import java.util.Objects;
 import java.util.function.Consumer;
@@ -26,6 +28,7 @@ public final class ProjectState {
     private final ClusterState cluster;
     private final ProjectId project;
     private final ProjectMetadata projectMetadata;
+    private final Settings projectSettings;
     private final RoutingTable routingTable;
 
     ProjectState(ClusterState clusterState, ProjectId projectId) {
@@ -34,6 +37,7 @@ public final class ProjectState {
         this.cluster = clusterState;
         this.project = projectId;
         this.projectMetadata = clusterState.metadata().getProject(projectId);
+        this.projectSettings = ProjectStateRegistry.getProjectSettings(projectId, clusterState);
         this.routingTable = clusterState.routingTable(projectId);
     }
 
@@ -57,6 +61,10 @@ public ClusterBlocks blocks() {
         return cluster().blocks();
     }
 
+    public Settings settings() {
+        return projectSettings;
+    }
+
     @Override
     public boolean equals(Object obj) {
         if (obj == this) return true;

server/src/main/java/org/elasticsearch/cluster/metadata/Metadata.java

@@ -985,13 +985,7 @@ private MetadataDiff(StreamInput in) throws IOException {
                     RESERVED_DIFF_VALUE_READER
                 );
 
-                singleProject = new ProjectMetadata.ProjectMetadataDiff(
-                    indices,
-                    templates,
-                    projectCustoms,
-                    DiffableUtils.emptyDiff(),
-                    Settings.EMPTY_DIFF
-                );
+                singleProject = new ProjectMetadata.ProjectMetadataDiff(indices, templates, projectCustoms, DiffableUtils.emptyDiff());
                 multiProject = null;
             } else {
                 fromNodeBeforeMultiProjectsSupport = false;