updates on the backend

cli/ingest_brand.py

@@ -0,0 +1,51 @@
+#!/usr/bin/env python3
+"""
+CLI for running brand catalog ingestion (discovery -> images -> embeddings
+-> pgvector) without going through the API - useful for bulk-loading
+brands before the React app or FastAPI server are even running, exactly
+like the original project's `pipeline_runner.py`.
+
+Usage:
+    python cli/ingest_brand.py "Parle" --max-products 50
+    python cli/ingest_brand.py "Britannia" --max-products 100 -v
+"""
+from __future__ import annotations
+
+import argparse
+import asyncio
+import logging
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
+
+from app.core.ingestion import ingest_brand  # noqa: E402
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Ingest a brand's catalog into pgvector")
+    parser.add_argument("brand", help="Brand name to discover and ingest, e.g. 'Parle'")
+    parser.add_argument("--max-products", type=int, default=50, help="Max products to discover (default: 50)")
+    parser.add_argument("-v", "--verbose", action="store_true", help="Verbose (DEBUG) logging")
+    args = parser.parse_args()
+
+    logging.basicConfig(
+        level=logging.DEBUG if args.verbose else logging.INFO,
+        format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    )
+
+    print(f"Starting ingestion for brand: {args.brand} (max_products={args.max_products})")
+    summary = asyncio.run(ingest_brand(args.brand, max_products=args.max_products))
+
+    print("\n" + "=" * 60)
+    print("INGESTION SUMMARY")
+    print("=" * 60)
+    print(f"Brand:      {summary['brand']}")
+    print(f"Products:   {summary['total_products']}")
+    print(f"Images:     {summary['total_images']}")
+    print(f"Duration:   {summary['duration_seconds']}s")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()