Merge branch 'main' into esql-decay-function

Author: timgrein

benchmarks/src/main/java/org/elasticsearch/benchmark/vector/ComputeNeighboursBenchmark.java

@@ -0,0 +1,77 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the "Elastic License
+ * 2.0", the "GNU Affero General Public License v3.0 only", and the "Server Side
+ * Public License v 1"; you may not use this file except in compliance with, at
+ * your election, the "Elastic License 2.0", the "GNU Affero General Public
+ * License v3.0 only", or the "Server Side Public License, v 1".
+ */
+
+package org.elasticsearch.benchmark.vector;
+
+import org.elasticsearch.common.logging.LogConfigurator;
+import org.elasticsearch.index.codec.vectors.cluster.NeighborHood;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Fork;
+import org.openjdk.jmh.annotations.Measurement;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Param;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.Setup;
+import org.openjdk.jmh.annotations.State;
+import org.openjdk.jmh.annotations.Warmup;
+import org.openjdk.jmh.infra.Blackhole;
+
+import java.io.IOException;
+import java.util.Random;
+import java.util.concurrent.TimeUnit;
+
+@BenchmarkMode(Mode.AverageTime)
+@OutputTimeUnit(TimeUnit.SECONDS)
+@State(Scope.Benchmark)
+// first iteration is complete garbage, so make sure we really warmup
+@Warmup(iterations = 1, time = 1)
+// real iterations. not useful to spend tons of time here, better to fork more
+@Measurement(iterations = 3, time = 1)
+// engage some noise reduction
+@Fork(value = 1)
+public class ComputeNeighboursBenchmark {
+
+    static {
+        LogConfigurator.configureESLogging(); // native access requires logging to be initialized
+    }
+
+    @Param({ "1000", "2000", "3000", "5000", "10000", "20000", "50000" })
+    int numVectors;
+
+    @Param({ "384", "782", "1024" })
+    int dims;
+
+    float[][] vectors;
+    int clusterPerNeighbour = 128;
+
+    @Setup
+    public void setup() throws IOException {
+        Random random = new Random(123);
+        vectors = new float[numVectors][dims];
+        for (float[] vector : vectors) {
+            for (int i = 0; i < dims; i++) {
+                vector[i] = random.nextFloat();
+            }
+        }
+    }
+
+    @Benchmark
+    @Fork(jvmArgsPrepend = { "--add-modules=jdk.incubator.vector" })
+    public void bruteForce(Blackhole bh) {
+        bh.consume(NeighborHood.computeNeighborhoodsBruteForce(vectors, clusterPerNeighbour));
+    }
+
+    @Benchmark
+    @Fork(jvmArgsPrepend = { "--add-modules=jdk.incubator.vector" })
+    public void graph(Blackhole bh) throws IOException {
+        bh.consume(NeighborHood.computeNeighborhoodsGraph(vectors, clusterPerNeighbour));
+    }
+}

docs/changelog/132003.yaml

@@ -0,0 +1,5 @@
+pr: 132003
+summary: Add `copy_from` option to the Append processor
+area: Ingest Node
+type: enhancement
+issues: []

docs/changelog/133546.yaml

@@ -0,0 +1,5 @@
+pr: 133546
+summary: "Support geohash, geotile and geohex grid types in ST_INTERSECTS and ST_DISJOINT"
+area: "ES|QL"
+type: enhancement
+issues: []

docs/changelog/133599.yaml

@@ -0,0 +1,5 @@
+pr: 133599
+summary: Support Gemini thinking budget in inference API
+area: Machine Learning
+type: enhancement
+issues: []

docs/changelog/134198.yaml

@@ -0,0 +1,5 @@
+pr: 134198
+summary: Improve `ShardLockObtainFailedException` message
+area: Store
+type: enhancement
+issues: []

docs/reference/elasticsearch/mapping-reference/doc-values.md

@@ -73,6 +73,13 @@ PUT my-index-000001
 1. The `status_code` field has `doc_values` enabled by default.
 2. The `session_id` has `doc_values` disabled, but can still be queried.
 
+## Multi-valued doc values note
+
+Elasticsearch supports storing multi-valued fields at index time. Multi-valued fields can be provided as a json array. However in the doc values format, the values aren't stored in the order as was provided at index time. Additionally, duplicates may be lost.
+This implementation detail of doc values is visible when features directly interact with doc values, which may be the case for example in ES|QL or aggregations in the search API. Note, that _source always returns arrays in the way that was provided at index time.
+
+How the ordering differs depends on whether the array is mapped as keyword or a numeric field type. In case of the `keyword` field type, the multi-valued values for each document are ordered lexicographically and duplicates are lost. If retaining duplicates is important then the `counted_keyword` field type should be used.
+In case of numeric field types (e.g. `long`, `double`, `scaled_float`, etc.), the multi-valued values for each document are ordered in natural order and duplicates are retained.
 
 
 

docs/reference/enrich-processor/append-processor.md

@@ -14,9 +14,10 @@ $$$append-options$$$
 | Name | Required | Default | Description |
 | --- | --- | --- | --- |
 | `field` | yes | - | The field to be appended to. Supports [template snippets](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md#template-snippets). |
-| `value` | yes | - | The value to be appended. Supports [template snippets](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md#template-snippets). |
+| `value` | yes* | - | The value to be appended. Supports [template snippets](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md#template-snippets). May specify only one of `value` or `copy_from`. |
+| `copy_from` {applies_to}`stack: ga 9.2.0` | no | - | The origin field which will be appended to `field`, cannot set `value` simultaneously. |
 | `allow_duplicates` | no | true | If `false`, the processor does not appendvalues already present in the field. |
-| `media_type` | no | `application/json` | The media type for encoding `value`. Applies only when `value` is a[template snippet](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md#template-snippets). Must be one of `application/json`, `text/plain`, or`application/x-www-form-urlencoded`. |
+| `media_type` | no | `application/json` | The media type for encoding `value`. Applies only when `value` is a [template snippet](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md#template-snippets). Must be one of `application/json`, `text/plain`, or`application/x-www-form-urlencoded`. |
 | `description` | no | - | Description of the processor. Useful for describing the purpose of the processor or its configuration. |
 | `if` | no | - | Conditionally execute the processor. See [Conditionally run a processor](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md#conditionally-run-processor). |
 | `ignore_failure` | no | `false` | Ignore failures for the processor. See [Handling pipeline failures](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md#handling-pipeline-failures). |