Merge branch 'main' into 2025/07/15/peek-queue-head

Author: DiannaHohensee

benchmarks/src/main/java/org/elasticsearch/benchmark/xcontent/JsonParserBenchmark.java

@@ -0,0 +1,87 @@
+/*
+ * 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.xcontent;
+
+import org.elasticsearch.common.bytes.BytesReference;
+import org.elasticsearch.common.io.Streams;
+import org.elasticsearch.xcontent.XContentParser;
+import org.elasticsearch.xcontent.XContentParserConfiguration;
+import org.elasticsearch.xcontent.XContentType;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Fork;
+import org.openjdk.jmh.annotations.Level;
+import org.openjdk.jmh.annotations.Measurement;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+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.Arrays;
+import java.util.Collections;
+import java.util.List;
+import java.util.Map;
+import java.util.Random;
+import java.util.concurrent.TimeUnit;
+import java.util.stream.Collectors;
+
+@Fork(1)
+@Warmup(iterations = 5)
+@Measurement(iterations = 10)
+@BenchmarkMode(Mode.AverageTime)
+@OutputTimeUnit(TimeUnit.NANOSECONDS)
+@State(Scope.Thread)
+public class JsonParserBenchmark {
+    private Map<String, BytesReference> sourceBytes;
+    private BytesReference source;
+    private Random random;
+    private List<String> sourcesRandomized;
+
+    final String[] sources = new String[] { "monitor_cluster_stats.json", "monitor_index_stats.json", "monitor_node_stats.json" };
+
+    @Setup(Level.Iteration)
+    public void randomizeSource() {
+        sourcesRandomized = Arrays.asList(sources);
+        Collections.shuffle(sourcesRandomized, random);
+    }
+
+    @Setup(Level.Trial)
+    public void setup() throws IOException {
+        random = new Random();
+        sourceBytes = Arrays.stream(sources).collect(Collectors.toMap(s -> s, s -> {
+            try {
+                return readSource(s);
+            } catch (IOException e) {
+                throw new RuntimeException(e);
+            }
+        }));
+    }
+
+    @Benchmark
+    public void parseJson(Blackhole bh) throws IOException {
+        sourcesRandomized.forEach(source -> {
+            try {
+                final XContentParser parser = XContentType.JSON.xContent()
+                    .createParser(XContentParserConfiguration.EMPTY, sourceBytes.get(source).streamInput());
+                bh.consume(parser.mapOrdered());
+            } catch (IOException e) {
+                throw new RuntimeException(e);
+            }
+        });
+    }
+
+    private BytesReference readSource(String fileName) throws IOException {
+        return Streams.readFully(JsonParserBenchmark.class.getResourceAsStream(fileName));
+    }
+}

docs/changelog/131341.yaml

@@ -0,0 +1,5 @@
+pr: 131341
+summary: Consider min/max from predicates when transform date_trunc/bucket to `round_to`
+area: ES|QL
+type: enhancement
+issues: []

docs/changelog/131536.yaml

@@ -1,5 +1,5 @@
 pr: 131536
-summary: "Component Templates: Add `{created,modified}_date`"
+summary: "Component Templates: Add created and modified date"
 area: Ingest Node
 type: enhancement
 issues: []

docs/changelog/132083.yaml

@@ -0,0 +1,5 @@
+pr: 132083
+summary: "Index template: Add created_date and modified_date"
+area: Ingest Node
+type: enhancement
+issues: []

docs/changelog/132143.yaml

@@ -0,0 +1,6 @@
+pr: 132143
+summary: Consider min/max from predicates when transform date_trunc/bucket to `round_to`
+  option 2
+area: ES|QL
+type: enhancement
+issues: []

docs/changelog/132459.yaml

@@ -0,0 +1,5 @@
+pr: 132459
+summary: Small fixes for COPY_SIGN
+area: ES|QL
+type: bug
+issues: []

docs/changelog/132511.yaml

@@ -0,0 +1,5 @@
+pr: 132511
+summary: Handle special regex cases for version fields
+area: Search
+type: bug
+issues: []

docs/reference/elasticsearch/mapping-reference/semantic-text.md

@@ -35,7 +35,7 @@ the embedding generation, indexing, and query to use.
 
 {applies_to}`stack: ga 9.1`  Newly created indices with `semantic_text` fields using dense embeddings will be
 [quantized](/reference/elasticsearch/mapping-reference/dense-vector.md#dense-vector-quantization)
-to `bbq_hnsw` automatically.
+to `bbq_hnsw` automatically as long as they have a minimum of 64 dimensions.
 
 ## Default and custom endpoints
 
@@ -486,6 +486,29 @@ PUT test-index
 }
 ```
 
+## Troubleshooting semantic_text fields [troubleshooting-semantic-text-fields]
+
+If you want to verify that your embeddings look correct, you can view the
+inference data that `semantic_text` typically hides using `fields`.
+
+```console
+POST test-index/_search
+{
+    "query": {
+        "match": {
+            "my_semantic_field": "Which country is Paris in?"
+        },
+        "fields": [
+            "_inference_fields"
+          ]
+    }
+}
+```
+
+This will return verbose chunked embeddings content that is used to perform
+semantic search for `semantic_text` fields.
+
+
 ## Limitations [limitations]
 
 `semantic_text` field types have the following limitations: