backend apis updation

scripts/seed_sample_data.py

@@ -20,22 +20,17 @@ Usage:
 from __future__ import annotations
 
 import argparse
-import json
 import logging
 import sys
 from pathlib import Path
-from collections import defaultdict
 
 sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
 
-from app.services.vector_store import ensure_brand_schema, upsert_brand_products, _connect, _sanitize_name  # noqa: E402
-from app.services.brand_registry import resolve_parent_brand  # noqa: E402
+from app.services.brand_sync import SEED_DIR, load_seed_catalogs, seed_brands  # noqa: E402
 
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
 
-SEED_DIR = Path(__file__).resolve().parents[1] / "data" / "seed_catalogs"
-
 
 def main() -> None:
     parser = argparse.ArgumentParser(description="Seed pgvector with bundled sample catalogs")
@@ -63,34 +58,11 @@ def main() -> None:
         logger.error("Seed directory not found: %s", SEED_DIR)
         sys.exit(1)
 
-    files = sorted(SEED_DIR.glob("*.json"))
-    if args.only:
-        wanted = [w.lower() for w in args.only]
-        files = [f for f in files if any(w in f.name.lower() for w in wanted)]
-
-    if not files:
-        logger.warning("No matching seed files found in %s", SEED_DIR)
-        return
-
-    # Aggregate products by resolved (canonical) brand so that multiple
+    # Products are aggregated by resolved (canonical) brand so that multiple
     # seed files contributing to the same brand table are upserted as a
     # single batch. This ensures the stale-product cleanup (cleanup=True)
     # doesn't orphan products from a sibling file.
-    brand_products: dict[str, list[dict]] = defaultdict(list)
-    file_brand_map: dict[str, str] = {}
-
-    for f in files:
-        data = json.loads(f.read_text(encoding="utf-8-sig"))
-        products = data.get("products", [])
-        brand = data.get("brand") or (products[0].get("brand_name") if products else None)
-        if not brand or not products:
-            logger.warning("Skipping %s - no brand/products found", f.name)
-            continue
-
-        resolved = resolve_parent_brand(brand)
-        brand_products[resolved].extend(products)
-        file_brand_map[f.name] = resolved
-        logger.info("Read %d products from %s -> resolved brand '%s'", len(products), f.name, resolved)
+    brand_products = load_seed_catalogs(only=args.only)
 
     if not brand_products:
         logger.warning("No valid seed data found in %s", SEED_DIR)
@@ -99,17 +71,7 @@ def main() -> None:
     # Do not drop existing brand tables to preserve user database state.
     # Stale table cleanup disabled per environment requirements.
 
-
-    total = 0
-    for resolved_brand, all_products in brand_products.items():
-        logger.info("Seeding %d product(s) for brand '%s'", len(all_products), resolved_brand)
-        table = ensure_brand_schema(resolved_brand)
-        if not table:
-            logger.error("Could not create/verify table for brand '%s' - is pgvector reachable?", resolved_brand)
-            continue
-        upsert_brand_products(resolved_brand, all_products, cleanup=True)
-        logger.info("Seeded %d products for brand '%s' (table=%s)", len(all_products), resolved_brand, table)
-        total += len(all_products)
+    total = seed_brands(brand_products, cleanup=True)
 
     print(f"\nDone. Seeded {total} products across {len(brand_products)} brand(s) into pgvector.")
     print("Start the API with `uvicorn app.main:app --reload` and try a search/chat query.")