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 +1,97 @@
+<?php
+
+namespace app\service\Embedding;
+
+use support\Db;
+
+class ChunkEmbeddingRepository
+{
+    public function queuePendingArchiveTasks(int $limit): array
+    {
+        $statuses = [EmbeddingStatus::PENDING, EmbeddingStatus::QUEUED, EmbeddingStatus::FAILED_RETRYABLE];
+        $archiveUids = Db::table('chunks')
+            ->whereIn('embedding_status', $statuses)
+            ->select('archive_uid')
+            ->groupBy('archive_uid')
+            ->orderByRaw('MIN(id)')
+            ->limit($limit)
+            ->pluck('archive_uid')
+            ->all();
+
+        $archiveUids = array_values(array_filter(array_map('strval', $archiveUids)));
+        foreach ($archiveUids as $archiveUid) {
+            Db::table('chunks')
+                ->where('archive_uid', $archiveUid)
+                ->whereIn('embedding_status', $statuses)
+                ->update([
+                    'embedding_status' => EmbeddingStatus::QUEUED,
+                    'embedding_error' => null,
+                    'embedding_updated_at' => Db::raw('CURRENT_TIMESTAMP'),
+                ]);
+        }
+
+        return $archiveUids;
+    }
+
+    public function findQueuedChunks(string $archiveUid, int $limit): array
+    {
+        $chunks = Db::table('chunks')
+            ->where('archive_uid', $archiveUid)
+            ->whereIn('embedding_status', [EmbeddingStatus::QUEUED, EmbeddingStatus::PROCESSING])
+            ->orderBy('chunk_index')
+            ->limit($limit)
+            ->get(['chunk_uid', 'archive_uid', 'chunk_index', 'text'])
+            ->all();
+
+        return array_map(static fn (object $chunk): array => [
+            'chunk_uid' => (string) $chunk->chunk_uid,
+            'archive_uid' => (string) $chunk->archive_uid,
+            'chunk_index' => (int) $chunk->chunk_index,
+            'text' => (string) $chunk->text,
+        ], $chunks);
+    }
+
+    public function markProcessing(array $chunkUids): void
+    {
+        $this->updateStatus($chunkUids, EmbeddingStatus::PROCESSING);
+    }
+
+    public function markEmbedded(string $chunkUid, array $embeddingRef, string $model): void
+    {
+        Db::table('chunks')->where('chunk_uid', $chunkUid)->update([
+            'embedding_status' => EmbeddingStatus::EMBEDDED,
+            'embedding_ref' => json_encode($embeddingRef, JSON_UNESCAPED_UNICODE | JSON_UNESCAPED_SLASHES),
+            'embedding_model' => $model,
+            'embedding_error' => null,
+            'embedding_updated_at' => Db::raw('CURRENT_TIMESTAMP'),
+            'search_index_status' => 0,
+            'search_index_error' => null,
+            'search_index_updated_at' => null,
+        ]);
+    }
+
+    public function markFailed(array $chunkUids, string $error, bool $retryable): void
+    {
+        if ($chunkUids === []) {
+            return;
+        }
+
+        Db::table('chunks')->whereIn('chunk_uid', $chunkUids)->update([
+            'embedding_status' => $retryable ? EmbeddingStatus::FAILED_RETRYABLE : EmbeddingStatus::FAILED_TERMINAL,
+            'embedding_error' => mb_substr($error, 0, 4000),
+            'embedding_updated_at' => Db::raw('CURRENT_TIMESTAMP'),
+        ]);
+    }
+
+    private function updateStatus(array $chunkUids, int $status): void
+    {
+        if ($chunkUids === []) {
+            return;
+        }
+
+        Db::table('chunks')->whereIn('chunk_uid', $chunkUids)->update([
+            'embedding_status' => $status,
+            'embedding_updated_at' => Db::raw('CURRENT_TIMESTAMP'),
+        ]);
+    }
+}