Update nutrition score retrieval using OFF v2 REST API and title cleaning

backend/scripts/check_stores.py

@@ -0,0 +1,8 @@
+import sys
+sys.path.insert(0, ".")
+from app.services.store_db import list_stores
+
+stores = list_stores()
+print("Stores in DB:")
+for s in stores:
+    print(f"  - {s['store_id']}: {s['store_name']} ({s.get('city')}) [{s.get('tier')}]")

backend/scripts/fast_test.py

@@ -0,0 +1,34 @@
+import sys
+import os
+sys.path.insert(0, ".")
+from app.services.rag_service import retrieve, answer_query
+from app.services.query_intent import extract_max_price, extract_brand_mention, is_count_query, detected_category
+
+print("=== Q1: How many products are there in Cadbury? ===")
+print("  Is Count:", is_count_query("How many products are there in Cadbury?"))
+print("  Brand Mention:", extract_brand_mention("How many products are there in Cadbury?"))
+print("  Category:", detected_category("How many products are there in Cadbury?"))
+
+print("\n=== Q2: Suggest panner less than ₹100 ===")
+print("  Is Count:", is_count_query("Suggest panner less than ₹100"))
+print("  Brand Mention:", extract_brand_mention("Suggest panner less than ₹100"))
+print("  Category:", detected_category("Suggest panner less than ₹100"))
+print("  Max Price:", extract_max_price("Suggest panner less than ₹100"))
+q2_prods = retrieve("Suggest panner less than ₹100")
+for p in q2_prods:
+    print(f"    - [{p.brand}] {p.product_name} | Price: {p.price_range} | Category: {p.category}")
+
+print("\n=== Q3: Recommend Paneer under ₹150 ===")
+print("  Is Count:", is_count_query("Recommend Paneer under ₹150"))
+print("  Brand Mention:", extract_brand_mention("Recommend Paneer under ₹150"))
+print("  Category:", detected_category("Recommend Paneer under ₹150"))
+print("  Max Price:", extract_max_price("Recommend Paneer under ₹150"))
+q3_prods = retrieve("Recommend Paneer under ₹150")
+for p in q3_prods:
+    print(f"    - [{p.brand}] {p.product_name} | Price: {p.price_range} | Category: {p.category}")
+
+print("\n=== Q4: Suggest low sugar biscuits ===")
+print("  Category:", detected_category("Suggest low sugar biscuits"))
+q4_prods = retrieve("Suggest low sugar biscuits")
+for p in q4_prods:
+    print(f"    - [{p.brand}] {p.product_name} | Price: {p.price_range} | Category: {p.category}")

backend/scripts/seed_sample_data.py

@@ -43,8 +43,22 @@ def main() -> None:
         "--only", nargs="*", default=None,
         help="Optional list of brand names (case-insensitive substring match on filename) to limit seeding to",
     )
+    parser.add_argument(
+        "--skip-if-seeded", action="store_true",
+        help="Skip seeding if database already contains products",
+    )
     args = parser.parse_args()
 
+    if args.skip_if_seeded:
+        from app.services.vector_store import count_products_all_brands
+        try:
+            cnt = count_products_all_brands()
+            if cnt > 0:
+                logger.info("⚡ Database already contains %d products. Skipping sample data seed.", cnt)
+                return
+        except Exception:
+            pass
+
     if not SEED_DIR.exists():
         logger.error("Seed directory not found: %s", SEED_DIR)
         sys.exit(1)

backend/scripts/seed_store_intelligence.py

@@ -34,8 +34,19 @@ def main() -> None:
     parser.add_argument("--days", type=int, default=90, help="Days of order history to simulate (default: 90)")
     parser.add_argument("--seed", type=int, default=42, help="Random seed for reproducible store/order generation")
     parser.add_argument("--no-reset-orders", action="store_true", help="Append to existing order history instead of clearing it first")
+    parser.add_argument("--skip-if-seeded", action="store_true", help="Skip if stores are already provisioned")
     args = parser.parse_args()
 
+    if args.skip_if_seeded:
+        from app.services.store_db import list_stores
+        try:
+            stores = list_stores()
+            if stores and len(stores) >= 5:
+                logger.info("⚡ Stores already provisioned (%d stores). Skipping store intelligence seed.", len(stores))
+                return
+        except Exception:
+            pass
+
     from app.services.store_seed_service import run_seed
 
     logger.info("Seeding store intelligence (days=%d, seed=%d, reset_orders=%s)...", args.days, args.seed, not args.no_reset_orders)

backend/scripts/test_rag.py

@@ -0,0 +1,30 @@
+import sys
+from app.services.rag_service import retrieve, answer_query
+from app.services.query_intent import extract_max_price, extract_brand_mention, is_count_query
+
+def run_test():
+    queries = [
+        "How many products are there in Cadbury?",
+        "Suggest low sugar biscuits",
+        "Recommend Paneer under ₹150",
+        "Suggest panner less than ₹100",
+    ]
+    
+    for q in queries:
+        print("="*60)
+        print(f"QUERY: {q}")
+        print(f"  Is Count: {is_count_query(q)}")
+        print(f"  Brand Mention: {extract_brand_mention(q)}")
+        print(f"  Max Price: {extract_max_price(q)}")
+        
+        prods = retrieve(q)
+        print("  Retrieved Products:")
+        for p in prods[:5]:
+            print(f"    - {p.brand} | {p.product_name} | Price: {p.price_range} | Cat: {p.category}")
+            
+        ans = answer_query(q)
+        print(f"  ANSWER:\n{ans.answer}")
+        print("="*60)
+
+if __name__ == "__main__":
+    run_test()

backend/scripts/test_rag_response.py

@@ -0,0 +1,12 @@
+import sys
+sys.stdout.reconfigure(encoding='utf-8')
+sys.path.insert(0, ".")
+from app.services.rag_service import answer_query
+
+res = answer_query("Recommend a low sugar biscuit")
+print("=== RAG ANSWER ===")
+print(res.answer)
+print("=== SOURCES FOUND ===")
+print(len(res.sources))
+for p in res.sources[:3]:
+    print(f" - {p.product_name} ({p.brand}) - {p.price_range}")