暂存

2026-05-07 01:40:58 +08:00
parent 093ce2e8bc
commit 549b706fcc
30 changed files with 2159 additions and 53 deletions
@@ -0,0 +1,113 @@
+<?php
+
+namespace app\service\Search;
+
+use OpenSearch\Client;
+
+class OpenSearchChunkIndex
+{
+    public function __construct(private readonly ?Client $client = null)
+    {
+    }
+
+    public function ensureExists(): void
+    {
+        $client = $this->client();
+        $index = $this->indexName();
+
+        if ($client->indices()->exists(['index' => $index])) {
+            return;
+        }
+
+        $client->indices()->create([
+            'index' => $index,
+            'body' => $this->mapping(),
+        ]);
+    }
+
+    public function bulkIndex(array $documents): array
+    {
+        if ($documents === []) {
+            return ['items' => [], 'errors' => false];
+        }
+
+        $body = [];
+        foreach ($documents as $document) {
+            $body[] = [
+                'index' => [
+                    '_index' => $this->indexName(),
+                    '_id' => $document['chunk_uid'],
+                ],
+            ];
+            $body[] = $document;
+        }
+
+        return $this->client()->bulk([
+            'refresh' => config('opensearch.bulk.refresh', 'false'),
+            'body' => $body,
+        ]);
+    }
+
+    public function mapping(): array
+    {
+        return [
+            'settings' => [
+                'index' => [
+                    'knn' => true,
+                ],
+            ],
+            'mappings' => [
+                'properties' => [
+                    'chunk_uid' => ['type' => 'keyword'],
+                    'archive_uid' => ['type' => 'keyword'],
+                    'chunk_index' => ['type' => 'integer'],
+                    'page_start' => ['type' => 'integer'],
+                    'page_end' => ['type' => 'integer'],
+                    'title' => $this->textWithKeyword(),
+                    'source' => $this->textWithKeyword(),
+                    'author' => $this->textWithKeyword(),
+                    'year' => ['type' => 'integer'],
+                    'series' => $this->textWithKeyword(),
+                    'tags' => ['type' => 'keyword'],
+                    'text' => ['type' => 'text'],
+                    'embedding' => [
+                        'type' => 'knn_vector',
+                        'dimension' => (int) config('opensearch.vector.dimensions', 2048),
+                        'method' => [
+                            'name' => 'hnsw',
+                            'space_type' => config('opensearch.vector.space_type', 'cosinesimil'),
+                            'engine' => config('opensearch.vector.engine', 'lucene'),
+                        ],
+                    ],
+                    'embedding_model' => ['type' => 'keyword'],
+                    'embedding_dimensions' => ['type' => 'integer'],
+                    'created_time' => ['type' => 'date'],
+                    'updated_time' => ['type' => 'date'],
+                ],
+            ],
+        ];
+    }
+
+    private function client(): Client
+    {
+        return $this->client ?? (new OpenSearchClientFactory())->make();
+    }
+
+    private function indexName(): string
+    {
+        return config('opensearch.indices.chunks', 'proofdb_chunks');
+    }
+
+    private function textWithKeyword(): array
+    {
+        return [
+            'type' => 'text',
+            'fields' => [
+                'keyword' => [
+                    'type' => 'keyword',
+                    'ignore_above' => 512,
+                ],
+            ],
+        ];
+    }
+}