暂存

scripts/setup_database.php

@@ -41,6 +41,8 @@ CREATE TABLE IF NOT EXISTS chunks (
     embedding_status INTEGER NOT NULL DEFAULT 0,
     embedding_ref JSONB,
     embedding_model TEXT,
+    created_time TIMESTAMPTZ NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    updated_time TIMESTAMPTZ NOT NULL DEFAULT CURRENT_TIMESTAMP,
     CONSTRAINT chunks_archive_uid_foreign
         FOREIGN KEY (archive_uid)
         REFERENCES archives (archive_uid)
@@ -53,9 +55,17 @@ SQL,
     'CREATE INDEX IF NOT EXISTS archives_series_index ON archives (series)',
     'CREATE INDEX IF NOT EXISTS archives_tags_gin_index ON archives USING GIN (tags)',
     'CREATE INDEX IF NOT EXISTS archives_metadata_gin_index ON archives USING GIN (metadata)',
+    'ALTER TABLE chunks ADD COLUMN IF NOT EXISTS embedding_error TEXT',
+    'ALTER TABLE chunks ADD COLUMN IF NOT EXISTS embedding_updated_at TIMESTAMPTZ',
+    'ALTER TABLE chunks ADD COLUMN IF NOT EXISTS search_index_status INTEGER NOT NULL DEFAULT 0',
+    'ALTER TABLE chunks ADD COLUMN IF NOT EXISTS search_index_error TEXT',
+    'ALTER TABLE chunks ADD COLUMN IF NOT EXISTS search_index_updated_at TIMESTAMPTZ',
+    'ALTER TABLE chunks ADD COLUMN IF NOT EXISTS created_time TIMESTAMPTZ NOT NULL DEFAULT CURRENT_TIMESTAMP',
+    'ALTER TABLE chunks ADD COLUMN IF NOT EXISTS updated_time TIMESTAMPTZ NOT NULL DEFAULT CURRENT_TIMESTAMP',
     'CREATE INDEX IF NOT EXISTS chunks_archive_uid_index ON chunks (archive_uid)',
     'CREATE INDEX IF NOT EXISTS chunks_page_range_index ON chunks (archive_uid, page_start, page_end)',
     'CREATE INDEX IF NOT EXISTS chunks_embedding_status_index ON chunks (embedding_status)',
+    'CREATE INDEX IF NOT EXISTS chunks_search_index_status_index ON chunks (search_index_status)',
     <<<SQL
 CREATE OR REPLACE FUNCTION set_updated_time()
 RETURNS TRIGGER AS $$
@@ -66,11 +76,18 @@ END;
 $$ LANGUAGE plpgsql
 SQL,
     'DROP TRIGGER IF EXISTS archives_set_updated_time ON archives',
+    'DROP TRIGGER IF EXISTS chunks_set_updated_time ON chunks',
     <<<SQL
 CREATE TRIGGER archives_set_updated_time
 BEFORE UPDATE ON archives
 FOR EACH ROW
 EXECUTE FUNCTION set_updated_time()
+SQL,
+    <<<SQL
+CREATE TRIGGER chunks_set_updated_time
+BEFORE UPDATE ON chunks
+FOR EACH ROW
+EXECUTE FUNCTION set_updated_time()
 SQL,
 ];
 

scripts/setup_opensearch.php

@@ -0,0 +1,18 @@
+#!/usr/bin/env php
+<?php
+
+use app\service\Search\OpenSearchChunkIndex;
+
+require __DIR__ . '/../vendor/autoload.php';
+require __DIR__ . '/../support/bootstrap.php';
+
+try {
+    $index = new OpenSearchChunkIndex();
+    $index->ensureExists();
+
+    echo 'OpenSearch chunk index initialized: ' . config('opensearch.indices.chunks', 'proofdb_chunks') . PHP_EOL;
+    echo 'Vector dimensions: ' . config('opensearch.vector.dimensions', 2048) . PHP_EOL;
+} catch (Throwable $exception) {
+    fwrite(STDERR, $exception::class . ': ' . $exception->getMessage() . PHP_EOL);
+    exit(1);
+}