feat(ai): 建立 PixelRAG VLM replay worker

2026-07-09 23:30:43 +08:00
parent e34c9d777b
commit 55ce12e6b0
12 changed files with 1012 additions and 10 deletions
--- a/scripts/ops/run_pixelrag_vlm_replay_worker.py
+++ b/scripts/ops/run_pixelrag_vlm_replay_worker.py
@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+"""Run or dry-run the PixelRAG Ollama VLM replay worker."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[2]
+if str(ROOT) not in sys.path:
+    sys.path.insert(0, str(ROOT))
+
+from services.pixelrag_vlm_replay_worker_service import (  # noqa: E402
+    DEFAULT_MODEL,
+    run_pixelrag_ollama_vlm_replay_worker,
+)
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(
+        description="執行或 dry-run PixelRAG Ollama-first VLM replay worker。"
+    )
+    parser.add_argument(
+        "--artifact-root",
+        help="PixelRAG visual evidence artifact root；預設使用 production/container 設定。",
+    )
+    parser.add_argument(
+        "--output-root",
+        help="VLM replay artifact receipt output root。",
+    )
+    parser.add_argument(
+        "--platform",
+        action="append",
+        dest="platforms",
+        help="限制平台，可重複指定，例如 --platform shopee_tw --platform coupang_tw。",
+    )
+    parser.add_argument(
+        "--max-age-hours",
+        type=int,
+        default=168,
+        help="receipt 最大新鮮度小時數。",
+    )
+    parser.add_argument(
+        "--limit",
+        type=int,
+        default=25,
+        help="最多處理 receipt 數。",
+    )
+    parser.add_argument(
+        "--tile-limit",
+        type=int,
+        default=4,
+        help="每個 receipt 最多送入 VLM 的 tile 數。",
+    )
+    parser.add_argument(
+        "--model",
+        default=DEFAULT_MODEL,
+        help="Ollama VLM model。",
+    )
+    parser.add_argument(
+        "--timeout",
+        type=int,
+        default=90,
+        help="單次 Ollama generate timeout 秒數。",
+    )
+    parser.add_argument(
+        "--execute",
+        action="store_true",
+        help="真的呼叫 Ollama VLM；未指定時只做 no-write dry-run。",
+    )
+    parser.add_argument(
+        "--write-receipt",
+        action="store_true",
+        help="execute 後寫入 VLM replay artifact receipt；不寫 DB。",
+    )
+    args = parser.parse_args()
+
+    payload = run_pixelrag_ollama_vlm_replay_worker(
+        artifact_root=args.artifact_root,
+        output_root=args.output_root,
+        platform=tuple(args.platforms or ()),
+        max_age_hours=args.max_age_hours,
+        limit=args.limit,
+        tile_limit=args.tile_limit,
+        model=args.model,
+        timeout=args.timeout,
+        execute=args.execute,
+        write_receipt=bool(args.write_receipt and args.execute),
+    )
+    print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
+    return 0 if payload.get("success") else 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())