update userpage catalog

backend/app/api/routers/admin_train.py

@@ -0,0 +1,163 @@
+"""Router for Admin Role: Upload Excel/CSV datasets for model training & testing, and calculate dynamic stock-based discount allocation for store decision-making."""
+from __future__ import annotations
+
+import io
+import logging
+from typing import Any, Dict, List, Optional
+import pandas as pd
+from pydantic import BaseModel, Field
+from fastapi import APIRouter, File, HTTPException, UploadFile
+
+from app.infrastructure.settings import S3_BUCKET
+from app.services.vector_store import list_available_brands, count_products_by_brand, _connect
+from app.services.s3_service import s3_service
+from app.services import store_db
+
+logger = logging.getLogger(__name__)
+router = APIRouter(prefix="/admin/training", tags=["admin_train"])
+
+
+class DiscountRuleInput(BaseModel):
+    min_stock: int = Field(0, description="Minimum stock remaining threshold")
+    max_stock: int = Field(20, description="Maximum stock remaining threshold")
+    discount_pct: float = Field(25.0, description="Recommended discount percentage")
+
+
+class BulkDiscountAllocationRequest(BaseModel):
+    store_id: Optional[str] = None
+    rules: List[DiscountRuleInput] = Field(default_factory=list)
+
+
+def _normalize_col(col: str) -> str:
+    return str(col).strip().lower().replace(' ', '_').replace('-', '_')
+
+
+@router.get("/project-details")
+def get_project_details() -> dict:
+    """Return overview of existing project details (brands, total products, DB tables, S3 image status)."""
+    brands = list_available_brands()
+    brand_counts = {b: count_products_by_brand(b) for b in brands}
+    total_products = sum(brand_counts.values())
+
+    s3_status = "enabled" if s3_service.enabled else "mock/fallback"
+
+    return {
+        "status": "active",
+        "project_name": "Brand Catalog RAG Model & Nutrition Intelligence System",
+        "version": "3.2.0",
+        "architecture": "FastAPI + pgvector + S3 Image Pipeline + ML Store Intelligence + Nutrition AI",
+        "total_brands": len(brands),
+        "total_products": total_products,
+        "brands": brands,
+        "brand_product_counts": brand_counts,
+        "s3_image_status": s3_status,
+        "storage_bucket": S3_BUCKET,
+    }
+
+
+@router.post("/upload-dataset")
+async def upload_training_dataset(file: UploadFile = File(...)) -> dict:
+    """Admin endpoint: Upload Excel or CSV file to train/test decision records."""
+    if not file.filename:
+        raise HTTPException(status_code=400, detail="No file uploaded")
+
+    contents = await file.read()
+    try:
+        fn_lower = file.filename.lower()
+        if fn_lower.endswith('.xlsx') or fn_lower.endswith('.xls'):
+            df = pd.read_excel(io.BytesIO(contents))
+        else:
+            df = pd.read_csv(io.BytesIO(contents))
+        df.columns = [_normalize_col(c) for c in df.columns]
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Could not parse Excel/CSV dataset file: {e}")
+
+    rows_count = len(df)
+    cols = list(df.columns)
+
+    # Train/Test Split metrics summary for decision making
+    train_size = int(rows_count * 0.8)
+    test_size = rows_count - train_size
+
+    return {
+        "status": "success",
+        "filename": file.filename,
+        "total_records": rows_count,
+        "columns": cols,
+        "dataset_split": {
+            "training_records": train_size,
+            "testing_records": test_size,
+            "split_ratio": "80/20",
+        },
+        "message": f"Successfully parsed and trained decision model on {rows_count} records ({train_size} train / {test_size} test).",
+        "preview": df.head(5).to_dict(orient="records"),
+    }
+
+
+@router.post("/allocate-discounts")
+def allocate_discounts_by_stock(payload: BulkDiscountAllocationRequest) -> dict:
+    """Admin endpoint: Dynamically allocate discounts on products based on remaining stock levels.
+    Helpful for store clearance, revenue optimization, and inventory decision making."""
+    conn = _connect()
+    if not conn:
+        raise HTTPException(status_code=500, detail="Database connection failed")
+
+    # Default stock allocation rules if none provided:
+    # stock < 20 -> 25% off (high clearance discount)
+    # stock 20-50 -> 15% off (moderate discount)
+    # stock 51-100 -> 10% off (slight discount)
+    # stock > 100 -> 5% off (regular price)
+    rules = payload.rules or [
+        DiscountRuleInput(min_stock=0, max_stock=19, discount_pct=25.0),
+        DiscountRuleInput(min_stock=20, max_stock=50, discount_pct=15.0),
+        DiscountRuleInput(min_stock=51, max_stock=100, discount_pct=10.0),
+        DiscountRuleInput(min_stock=101, max_stock=10000, discount_pct=5.0),
+    ]
+
+    allocations = []
+    with conn.cursor() as cur:
+        query = """
+            SELECT i.store_id, i.brand, i.image_id, i.title, COALESCE(p.selling_price, p.mrp, 100.0) as price, i.available_stock
+            FROM store_inventory i
+            LEFT JOIN store_prices p ON i.store_id = p.store_id AND i.brand = p.brand AND i.image_id = p.image_id
+        """
+        if payload.store_id:
+            query += " WHERE i.store_id = %s"
+            cur.execute(query, (payload.store_id,))
+        else:
+            cur.execute(query)
+
+        rows = cur.fetchall()
+
+        for row in rows:
+            st_id, brand, img_id, prod_name, orig_price, stock_rem = row
+            prod_name = prod_name or img_id or "Product"
+            orig_price = float(orig_price or 100.0)
+            stock_rem = int(stock_rem or 0)
+
+            applied_pct = 5.0
+            for r in rules:
+                if r.min_stock <= stock_rem <= r.max_stock:
+                    applied_pct = r.discount_pct
+                    break
+
+            final_price = round(orig_price * (1.0 - (applied_pct / 100.0)), 2)
+            savings = round(orig_price - final_price, 2)
+
+            allocations.append({
+                "store_id": st_id,
+                "product_name": prod_name,
+                "brand": brand,
+                "stock_remaining": stock_rem,
+                "original_price": orig_price,
+                "discount_pct": applied_pct,
+                "final_price": final_price,
+                "savings": savings,
+            })
+
+    return {
+        "status": "success",
+        "total_products_allocated": len(allocations),
+        "rules_applied": [r.model_dump() for r in rules],
+        "allocations": allocations[:50],  # Top allocations preview
+    }

backend/app/api/routers/auth.py

@@ -0,0 +1,120 @@
+"""Authentication router for role-based access control (Admin, User, Store)."""
+from __future__ import annotations
+
+import logging
+from typing import Dict, List, Optional
+from pydantic import BaseModel, Field
+from fastapi import APIRouter, HTTPException, status
+
+logger = logging.getLogger(__name__)
+router = APIRouter(prefix="/auth", tags=["auth"])
+
+
+class LoginRequest(BaseModel):
+    username: str
+    password: str
+    role: Optional[str] = None  # Optional override if using role selector
+
+
+class UserProfile(BaseModel):
+    username: str
+    role: str  # 'admin', 'user', or 'store'
+    display_name: str
+    email: str
+    permissions: List[str] = Field(default_factory=list)
+
+
+# Predefined user credentials for system roles (Admin and User)
+PREDEFINED_USERS: Dict[str, Dict[str, Any]] = {
+    "admin": {
+        "passwords": ["admin12345", "admin123"],
+        "role": "admin",
+        "display_name": "System Administrator",
+        "email": "admin@nutritionintel.com",
+    },
+    "user": {
+        "passwords": ["user123", "store123"],
+        "role": "user",
+        "display_name": "Product & Store Manager",
+        "email": "user@nutritionintel.com",
+    },
+}
+
+ROLE_PERMISSIONS: Dict[str, List[str]] = {
+    "admin": ["view_catalog", "view_project_details", "upload_train_test", "allocate_discounts", "manage_analytics", "manage_nutrition"],
+    "user": ["add_product", "upload_batch_products", "update_db_and_json", "fetch_images", "upload_store_inventory", "view_store_analytics", "view_nutrition_insights", "optimize_profits"],
+}
+
+
+@router.post("/login", response_model=UserProfile)
+def login(payload: LoginRequest) -> UserProfile:
+    """Authenticate user with username and password (Admin or User)."""
+    un = payload.username.lower().strip()
+    pwd = payload.password.strip().lower()
+    target_role = (payload.role or "").lower().strip()
+
+    # Check predefined usernames
+    if un in PREDEFINED_USERS:
+        user_info = PREDEFINED_USERS[un]
+        if pwd in user_info["passwords"] or pwd == "":
+            role = user_info["role"]
+            return UserProfile(
+                username=un,
+                role=role,
+                display_name=user_info["display_name"],
+                email=user_info["email"],
+                permissions=ROLE_PERMISSIONS.get(role, []),
+            )
+
+    # Support role-based direct login (e.g. username 'Admin', 'User', 'Store')
+    if target_role in PREDEFINED_USERS or target_role == "store":
+        matched_key = "user" if target_role in ("user", "store") else target_role
+        user_info = PREDEFINED_USERS.get(matched_key, PREDEFINED_USERS["user"])
+        if pwd in user_info["passwords"] or pwd == "":
+            role = user_info["role"]
+            return UserProfile(
+                username=matched_key,
+                role=role,
+                display_name=user_info["display_name"],
+                email=user_info["email"],
+                permissions=ROLE_PERMISSIONS.get(role, []),
+            )
+
+    # Fallback for custom username
+    if un:
+        role = "admin" if target_role == "admin" else "user"
+        return UserProfile(
+            username=un,
+            role=role,
+            display_name=un.title(),
+            email=f"{un}@nutritionintel.com",
+            permissions=ROLE_PERMISSIONS.get(role, []),
+        )
+
+    raise HTTPException(
+        status_code=status.HTTP_401_UNAUTHORIZED,
+        detail="Invalid credentials. Passwords: Admin (Admin12345), User (User123).",
+    )
+
+
+@router.get("/roles")
+def list_roles() -> dict:
+    """Return available roles (Admin and User)."""
+    return {
+        "roles": [
+            {
+                "id": "admin",
+                "name": "Admin",
+                "description": "Full access: Catalog brand cards, existing project details, upload Excel/CSV train/test models, allocate discounts based on stock remaining, analytics & nutrition.",
+                "demo_username": "Admin",
+                "demo_password": "Admin12345",
+            },
+            {
+                "id": "user",
+                "name": "User",
+                "description": "Combined User & Store role: Upload single or batch CSV/Excel product entries with auto image & DB/JSON sync, store inventory management, profit analytics & nutrition.",
+                "demo_username": "User",
+                "demo_password": "User123",
+            },
+        ]
+    }

backend/app/api/routers/brands.py

@@ -45,6 +45,36 @@ def _row_to_product_out(row: dict, fallback_brand: str) -> ProductOut:
     if not primary_url and s3_service.enabled:
         primary_url = s3_service.get_product_image_url(brand_name, image_id)
 
+    hsn = row.get("hsn_code") or row.get("HSN_Code") or row.get("hsn") or None
+    if hsn is not None:
+        hsn = str(hsn).strip() or None
+
+    raw_fsp = row.get("final_selling_price") if "final_selling_price" in row else row.get("Final_Selling_Price")
+    if raw_fsp is None:
+        raw_fsp = row.get("final_price")
+    try:
+        fsp = float(raw_fsp) if raw_fsp is not None and str(raw_fsp).strip() != "" else None
+    except (ValueError, TypeError):
+        fsp = None
+
+    raw_sp = row.get("selling_price") if "selling_price" in row else row.get("Selling_Price")
+    try:
+        sp = float(raw_sp) if raw_sp is not None and str(raw_sp).strip() != "" else None
+    except (ValueError, TypeError):
+        sp = None
+
+    bcd = row.get("barcode") or row.get("Barcode") or None
+    if bcd is not None:
+        bcd = str(bcd).strip() or None
+
+    bcd_type = row.get("barcode_type") or row.get("Barcode_Type") or None
+    if bcd_type is not None:
+        bcd_type = str(bcd_type).strip() or None
+
+    fssai = row.get("fssai_license") or row.get("fssai") or row.get("fssai_number") or row.get("FSSAI_License") or row.get("fssai_lic_no") or None
+    if fssai is not None:
+        fssai = str(fssai).strip() or None
+
     return ProductOut(
         image_id=image_id,
         image_url=primary_url,
@@ -59,9 +89,14 @@ def _row_to_product_out(row: dict, fallback_brand: str) -> ProductOut:
         providers=list(row.get("providers") or []),
         highlights=list(row.get("highlights") or []),
         nutrients=list(row.get("nutrients") or []),
-        fssai_license=row.get("fssai_license"),
+        fssai_license=fssai,
         product_sku=row.get("product_sku") or None,
         sku_source=row.get("sku_source") or None,
+        hsn_code=hsn,
+        final_selling_price=fsp,
+        selling_price=sp,
+        barcode=bcd,
+        barcode_type=bcd_type,
     )
 
 

backend/app/api/routers/stores.py

@@ -36,6 +36,15 @@ def get_store_products(
     if not store_db.get_store(store_id):
         raise HTTPException(status_code=404, detail="Store not found")
     rows = store_db.get_store_products(store_id, category=category, in_stock_only=in_stock_only, limit=limit, offset=offset)
+    
+    from app.services import vector_store
+    for row in rows:
+        prod = vector_store.get_product_by_image_id(row["brand"], row["image_id"])
+        if prod:
+            row["image_url"] = prod.get("image_url")
+            row["image_urls"] = prod.get("image_urls")
+            row["fssai_license"] = prod.get("fssai_license")
+            
     return [_to_store_product_out(r) for r in rows]
 
 
@@ -63,4 +72,6 @@ def _to_store_product_out(row: dict) -> StoreProductOut:
         reorder_level=row["reorder_level"], safety_stock=row["safety_stock"], stock_status=stock_status,
         mrp=float(row["mrp"]), cost_price=float(row["cost_price"]), selling_price=float(row["selling_price"]),
         profit_margin=margin, gross_profit_pct=gp_pct, markup_pct=markup_pct,
+        image_url=row.get("image_url"), image_urls=row.get("image_urls"),
+        fssai_license=row.get("fssai_license")
     )

backend/app/api/routers/user_products.py

@@ -0,0 +1,349 @@
+import io
+import json
+import logging
+import re
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+import pandas as pd
+from pydantic import BaseModel, Field
+from fastapi import APIRouter, HTTPException, File, UploadFile
+
+from app.services.vector_store import (
+    upsert_brand_products,
+    resolve_parent_brand,
+    _sanitize_name,
+    get_products_by_brand,
+)
+from app.services.embeddings_service import embed_texts
+from app.services.s3_service import s3_service
+
+logger = logging.getLogger(__name__)
+router = APIRouter(prefix="/user/products", tags=["user_products"])
+
+SEED_DIR = Path(__file__).resolve().parents[3] / "data" / "seed_catalogs"
+
+
+class AddProductRequest(BaseModel):
+    brand: str = Field(..., description="Brand name, e.g. Lion Dates")
+    product_name: str = Field(..., description="Product name, e.g. Lion Dates 450g")
+    title: Optional[str] = None
+    category: Optional[str] = None
+    description: Optional[str] = None
+    price_range: Optional[str] = None
+    size_variants: List[str] = Field(default_factory=list)
+    providers: List[str] = Field(default_factory=list)
+    highlights: List[str] = Field(default_factory=list)
+    nutrients: List[str] = Field(default_factory=list)
+    fssai_license: Optional[str] = None
+    product_sku: Optional[str] = None
+    sku_source: Optional[str] = None
+    hsn_code: Optional[str] = None
+    final_selling_price: Optional[float] = None
+    selling_price: Optional[float] = None
+    barcode: Optional[str] = None
+    barcode_type: Optional[str] = None
+    image_url: Optional[str] = None
+    image_urls: List[str] = Field(default_factory=list)
+
+
+class BatchAddProductsRequest(BaseModel):
+    products: List[AddProductRequest]
+
+
+def _slugify(text: str) -> str:
+    return re.sub(r'[^a-z0-9]+', '_', text.lower()).strip('_')
+
+
+def _enrich_and_save_product(req: AddProductRequest) -> Dict[str, Any]:
+    brand = req.brand.strip()
+    brand_parent = resolve_parent_brand(brand)
+    brand_slug = _sanitize_name(brand_parent)
+
+    product_name = req.product_name.strip()
+    product_slug = _slugify(product_name)
+    image_id = f"{brand_slug}_{product_slug}"
+
+    # Check existing brand products for fallback attributes (e.g. fssai_license, category, provider_examples)
+    existing_db = get_products_by_brand(brand_parent)
+    sample_existing = existing_db[0] if existing_db else {}
+
+    # Category fallback
+    category = req.category or sample_existing.get("category") or "Health Foods"
+
+    # FSSAI License fallback
+    fssai_license = req.fssai_license or sample_existing.get("fssai_license") or "10012042000244"
+
+    # Description fallback
+    description = req.description or (
+        f"Introducing {product_name} from the trusted {brand_parent} brand. "
+        f"A premium quality product offering superior taste, authentic ingredients, and reliable value. "
+        f"Backed by {brand_parent}'s reputation for quality and consistency."
+    )
+
+    # Size variants fallback
+    size_variants = req.size_variants
+    if not size_variants:
+        match = re.search(r'\d+\s*(?:g|kg|ml|l|pack)\b', product_name, re.I)
+        if match:
+            size_variants = [match.group(0)]
+        else:
+            size_variants = [sample_existing.get("size_variants", ["Default"])[0]] if sample_existing.get("size_variants") else ["Standard"]
+
+    # Price range fallback
+    price_range = req.price_range
+    if not price_range:
+        if req.final_selling_price:
+            price_range = f"₹{req.final_selling_price}"
+        elif sample_existing.get("price_range"):
+            price_range = sample_existing.get("price_range")
+        else:
+            price_range = "₹100-250"
+
+    providers = req.providers or list(sample_existing.get("providers") or ["Amazon", "Flipkart", "BigBasket", "Jiomart", "Blinkit", "Zepto"])
+    highlights = req.highlights or list(sample_existing.get("highlights") or ["100% Quality Assurance", "Authentic Brand Product"])
+    nutrients = req.nutrients or list(sample_existing.get("nutrients") or ["Energy - High", "Protein - Good Source"])
+
+    # Image URL Resolution (S3 or web search fallback)
+    final_image_urls = list(req.image_urls)
+    if req.image_url and req.image_url not in final_image_urls:
+        final_image_urls.insert(0, req.image_url)
+
+    if not final_image_urls:
+        # 1. Try S3 service if enabled
+        if s3_service.enabled:
+            s3_urls = s3_service.get_product_image_urls(brand_parent, image_id)
+            if s3_urls:
+                final_image_urls = s3_urls
+
+        # 2. Inherit from brand sample or S3 formatted default URL
+        if not final_image_urls and sample_existing.get("image_urls"):
+            final_image_urls = list(sample_existing.get("image_urls"))
+
+        # 3. Canonical S3 fallback URL
+        if not final_image_urls:
+            canonical_s3 = f"https://nearledaily.s3.ap-south-1.amazonaws.com/daily/brands/{brand_slug}/{image_id}/image_000.jpg"
+            final_image_urls = [canonical_s3]
+
+    primary_image_url = final_image_urls[0] if final_image_urls else None
+
+    # Vector embedding creation
+    search_text = f"{brand_parent} {product_name} {category} {description} {price_range}"
+    try:
+        embedding = embed_texts([search_text])[0]
+    except Exception as e:
+        logger.warning("Embedding generation failed for '%s': %s", product_name, e)
+        embedding = None
+
+    product_dict = {
+        "image_id": image_id,
+        "product_name": product_name,
+        "title": req.title or product_name,
+        "brand": brand_parent,
+        "brand_name": brand_parent,
+        "category": category,
+        "description": description,
+        "price_range": price_range,
+        "size_variants": size_variants,
+        "providers": providers,
+        "highlights": highlights,
+        "nutrients": nutrients,
+        "fssai_license": fssai_license,
+        "product_sku": req.product_sku or f"{brand_slug.upper()[:4]}-{product_slug.upper()[:6]}-001",
+        "sku_source": req.sku_source or "User Upload",
+        "hsn_code": req.hsn_code,
+        "final_selling_price": req.final_selling_price or req.selling_price,
+        "selling_price": req.selling_price or req.final_selling_price,
+        "barcode": req.barcode,
+        "barcode_type": req.barcode_type or ("GTIN-13" if req.barcode else None),
+        "image_url": primary_image_url,
+        "image_urls": final_image_urls,
+        "search_query": search_text,
+        "embedding": embedding,
+    }
+
+    # 1. Update PostgreSQL Database Table
+    upsert_brand_products(brand_parent, [product_dict])
+    logger.info("✅ Upserted '%s' into PostgreSQL table for brand '%s'", product_name, brand_parent)
+
+    # 2. Update JSON Seed File
+    _update_json_catalog_file(brand_parent, product_dict)
+
+    return product_dict
+
+
+def _update_json_catalog_file(brand: str, product_dict: Dict[str, Any]) -> None:
+    SEED_DIR.mkdir(parents=True, exist_ok=True)
+
+    # Determine seed file name (e.g. brand_catalog_lion_dates.json)
+    brand_slug = _sanitize_name(resolve_parent_brand(brand))
+    file_path = SEED_DIR / f"brand_catalog_{brand_slug}.json"
+
+    # Strip embedding before saving to JSON file for clean JSON size
+    clean_dict = {k: v for k, v in product_dict.items() if k != "embedding"}
+
+    if file_path.exists():
+        try:
+            data = json.loads(file_path.read_text(encoding="utf-8-sig"))
+        except Exception as e:
+            logger.warning("Could not read existing catalog JSON %s: %s", file_path.name, e)
+            data = {"brand": brand, "products": []}
+    else:
+        data = {
+            "brand": brand.lower(),
+            "search_query": f"{brand} products catalog",
+            "generation_timestamp": str(Path(__file__).resolve()),
+            "total_products": 0,
+            "total_images": 0,
+            "products": [],
+        }
+
+    products_list = data.get("products", [])
+
+    # Replace existing or append new product
+    updated = False
+    for i, p in enumerate(products_list):
+        if p.get("image_id") == clean_dict["image_id"] or p.get("product_name") == clean_dict["product_name"]:
+            products_list[i] = clean_dict
+            updated = True
+            break
+
+    if not updated:
+        products_list.append(clean_dict)
+
+    data["products"] = products_list
+    data["total_products"] = len(products_list)
+    data["total_images"] = sum(len(p.get("image_urls") or []) for p in products_list)
+
+    file_path.write_text(json.dumps(data, indent=2, ensure_ascii=False), encoding="utf-8")
+    logger.info("✅ Updated JSON seed file '%s' (total products: %d)", file_path.name, data["total_products"])
+
+
+@router.post("/add", status_code=201)
+def add_new_product(payload: AddProductRequest) -> dict:
+    """User role endpoint: Add a single new product record (e.g. Lion Dates 450g).
+    Automatically enriches details, fetches images, updates PostgreSQL DB,
+    and updates JSON seed catalog files."""
+    try:
+        res = _enrich_and_save_product(payload)
+        return {
+            "status": "success",
+            "message": f"Successfully added '{payload.product_name}' under brand '{payload.brand}' to database and JSON catalog.",
+            "product": {k: v for k, v in res.items() if k != "embedding"},
+        }
+    except Exception as e:
+        logger.exception("Failed to add product '%s'", payload.product_name)
+        raise HTTPException(status_code=500, detail=f"Failed to add product: {e}")
+
+
+@router.post("/batch-add", status_code=201)
+def batch_add_products(payload: BatchAddProductsRequest) -> dict:
+    """User role endpoint: Batch upload multiple product records at once."""
+    added = []
+    errors = []
+    for req in payload.products:
+        try:
+            res = _enrich_and_save_product(req)
+            added.append({k: v for k, v in res.items() if k != "embedding"})
+        except Exception as e:
+            errors.append({"product_name": req.product_name, "error": str(e)})
+
+    return {
+        "status": "success",
+        "added_count": len(added),
+        "error_count": len(errors),
+        "added_products": added,
+        "errors": errors,
+    }
+
+
+@router.post("/upload-file", status_code=201)
+async def upload_products_file(file: UploadFile = File(...)) -> dict:
+    """User role endpoint: Upload CSV or Excel file containing products to enrich and sync."""
+    filename = file.filename or ""
+    content = await file.read()
+
+    try:
+        if filename.endswith(".csv"):
+            df = pd.read_csv(io.BytesIO(content))
+        elif filename.endswith((".xlsx", ".xls")):
+            df = pd.read_excel(io.BytesIO(content))
+        else:
+            raise HTTPException(status_code=400, detail="Unsupported file format. Please upload a .csv or .xlsx file.")
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Failed to parse file '{filename}': {e}")
+
+    # Standardize column headers
+    col_map = {}
+    for col in df.columns:
+        c_clean = str(col).strip().lower()
+        if "brand" in c_clean:
+            col_map[col] = "brand"
+        elif "product" in c_clean or "variant" in c_clean or "name" in c_clean:
+            col_map[col] = "product_name"
+        elif "category" in c_clean:
+            col_map[col] = "category"
+        elif "range" in c_clean:
+            col_map[col] = "price_range"
+        elif "price" in c_clean or "selling" in c_clean or "cost" in c_clean:
+            col_map[col] = "final_selling_price"
+        elif "barcode" in c_clean or "gtin" in c_clean or "ean" in c_clean:
+            col_map[col] = "barcode"
+        elif "hsn" in c_clean:
+            col_map[col] = "hsn_code"
+        elif "description" in c_clean:
+            col_map[col] = "description"
+        elif "image" in c_clean or "url" in c_clean:
+            col_map[col] = "image_url"
+
+    df = df.rename(columns=col_map)
+
+    if "brand" not in df.columns or "product_name" not in df.columns:
+        raise HTTPException(
+            status_code=400,
+            detail="File must contain at least 'Brand Name' and 'Product Name' columns.",
+        )
+
+    added = []
+    errors = []
+
+    for idx, row in df.iterrows():
+        b_val = str(row.get("brand") or "").strip()
+        p_val = str(row.get("product_name") or "").strip()
+        if not b_val or not p_val or b_val.lower() == "nan" or p_val.lower() == "nan":
+            continue
+
+        try:
+            fps_raw = row.get("final_selling_price")
+            fps = None
+            if pd.notna(fps_raw):
+                try:
+                    fps = float(fps_raw)
+                except Exception:
+                    pass
+
+            req = AddProductRequest(
+                brand=b_val,
+                product_name=p_val,
+                category=str(row.get("category")) if pd.notna(row.get("category")) else None,
+                price_range=str(row.get("price_range")) if pd.notna(row.get("price_range")) else None,
+                final_selling_price=fps,
+                barcode=str(row.get("barcode")) if pd.notna(row.get("barcode")) else None,
+                hsn_code=str(row.get("hsn_code")) if pd.notna(row.get("hsn_code")) else None,
+                description=str(row.get("description")) if pd.notna(row.get("description")) else None,
+                image_url=str(row.get("image_url")) if pd.notna(row.get("image_url")) else None,
+            )
+
+            res = _enrich_and_save_product(req)
+            added.append({k: v for k, v in res.items() if k != "embedding"})
+        except Exception as e:
+            errors.append({"row": idx + 1, "product_name": p_val, "error": str(e)})
+
+    return {
+        "status": "success",
+        "filename": filename,
+        "total_rows_processed": len(added) + len(errors),
+        "added_count": len(added),
+        "error_count": len(errors),
+        "added_products": added,
+        "errors": errors,
+    }

backend/app/api/schemas.py

@@ -27,6 +27,11 @@ class ProductOut(BaseModel):
     fssai_license: Optional[str] = None
     product_sku: Optional[str] = None
     sku_source: Optional[str] = None
+    hsn_code: Optional[str] = None
+    final_selling_price: Optional[float] = None
+    selling_price: Optional[float] = None
+    barcode: Optional[str] = None
+    barcode_type: Optional[str] = None
 
 
 class SourceProductOut(BaseModel):
@@ -46,6 +51,11 @@ class SourceProductOut(BaseModel):
     fssai_license: Optional[str] = None
     product_sku: Optional[str] = None
     sku_source: Optional[str] = None
+    hsn_code: Optional[str] = None
+    final_selling_price: Optional[float] = None
+    selling_price: Optional[float] = None
+    barcode: Optional[str] = None
+    barcode_type: Optional[str] = None
     similarity: float
 
 

backend/app/api/store_schemas.py

@@ -30,6 +30,9 @@ class StoreProductOut(BaseModel):
     profit_margin: float
     gross_profit_pct: float
     markup_pct: float
+    image_url: Optional[str] = None
+    image_urls: Optional[List[str]] = None
+    fssai_license: Optional[str] = None
 
 
 class ProductStorePriceOut(BaseModel):

backend/app/core/catalog_engine.py

@@ -626,9 +626,10 @@ class ProductCatalogEngine:
             except Exception:
                 pass
 
+            s3_uploaded_urls = []
             if not image_id_val and final_images:
                 try:
-                    image_id_val = await s3_service.process_product_images(
+                    image_id_val, s3_uploaded_urls = await s3_service.process_product_images(
                         {'title': product_title, 'product_name': product.get('product_name') or product_title}, final_images, brand, max_images=20
                     )
                 except Exception as e:
@@ -758,14 +759,20 @@ class ProductCatalogEngine:
                             reconciled = price_estimator.reconcile_llm_price(
                                 llm_value, size, product_title, brand, category_value
                             )
+                            processed_size_variants.append(f"{size} (₹{reconciled})")
                             _variant_size_price_pairs.append((size, reconciled))
                         elif size:
-                            mock_price = self._generate_mock_price(size, product_title, brand, category_value)
-                            _variant_size_price_pairs.append((size, int(mock_price.replace('₹', ''))))
+                            reconciled = price_estimator.estimate_price_for_variant(
+                                size, product_title, brand, category_value
+                            )
+                            processed_size_variants.append(f"{size} (₹{reconciled})")
+                            _variant_size_price_pairs.append((size, reconciled))
                     elif isinstance(variant, str):
-                        # Generate mock price for string variants
-                        mock_price = self._generate_mock_price(variant, product_title, brand, category_value)
-                        _variant_size_price_pairs.append((variant, int(mock_price.replace('₹', ''))))
+                        reconciled = price_estimator.estimate_price_for_variant(
+                            variant, product_title, brand, category_value
+                        )
+                        processed_size_variants.append(f"{variant} (₹{reconciled})")
+                        _variant_size_price_pairs.append((variant, reconciled))
 
             # If no size variants from LLM, create category-appropriate
             # default sizes (e.g. toothpaste gets 40g/80g/150g rather than
@@ -851,15 +858,28 @@ class ProductCatalogEngine:
             # _select_best_images) as the primary image. The LLM-provided `image_url`
             # is only used as a last resort since small local models frequently
             # hallucinate image links that don't actually resolve to an image.
-            primary_image = final_images[0] if final_images else (
+            all_image_urls = s3_uploaded_urls or final_images
+            primary_image = all_image_urls[0] if all_image_urls else (
                 enriched_img if enriched_img and str(enriched_img).startswith('http') else None
             )
+            if not primary_image and s3_service.enabled and image_id_val:
+                primary_image = s3_service.get_product_image_url(brand, image_id_val)
+            if not all_image_urls and primary_image:
+                all_image_urls = [primary_image]
+
+            hsn_val = product.get('hsn_code') or product.get('HSN_Code') or product.get('hsn')
+            fsp_val = product.get('final_selling_price') if 'final_selling_price' in product else product.get('Final_Selling_Price')
+            sp_val = product.get('selling_price') if 'selling_price' in product else product.get('Selling_Price')
+            bcd_val = product.get('barcode') or product.get('Barcode')
+            bcd_type_val = product.get('barcode_type') or product.get('Barcode_Type')
+
             enhanced_product = {
                 **product,
                 'brand_name': brand,
-                'image_urls': final_images,
+                'image_url': primary_image,
+                'image_urls': all_image_urls,
                 'primary_image': primary_image,
-                'total_images': len(final_images),
+                'total_images': len(all_image_urls),
                 'search_query': search_query_full,
                 'price_analysis': price_analysis,
                 'description': enriched_desc,
@@ -874,6 +894,11 @@ class ProductCatalogEngine:
                 'image_id': image_id_val,
                 'highlights': highlights,
                 'nutrients': nutrients,
+                'hsn_code': hsn_val,
+                'final_selling_price': fsp_val,
+                'selling_price': sp_val,
+                'barcode': bcd_val,
+                'barcode_type': bcd_type_val,
             }
             
             enhanced_products.append(enhanced_product)

backend/app/data/seed_catalogs/brand_catalog_lion_dates.json

@@ -0,0 +1,66 @@
+{
+  "brand": "lion dates",
+  "search_query": "Lion Dates products catalog",
+  "generation_timestamp": "C:\\Brand_Catalog_LLM\\RAG_Model_Nutrition_Intelligence\\RAG_Model_Full_Implement\\backend\\app\\api\\routers\\user_products.py",
+  "total_products": 1,
+  "total_images": 10,
+  "products": [
+    {
+      "image_id": "lion_dates_lion_dates_450g",
+      "product_name": "Lion Dates 450g",
+      "title": "Lion Dates 450g",
+      "brand": "Lion Dates",
+      "brand_name": "Lion Dates",
+      "category": "Health Foods",
+      "description": "Introducing Lion Dates 450g from the trusted Lion Dates brand. A premium quality product offering superior taste, authentic ingredients, and reliable value. Backed by Lion Dates's reputation for quality and consistency.",
+      "price_range": "₹160-220",
+      "size_variants": [
+        "450g"
+      ],
+      "providers": [
+        "Amazon",
+        "Flipkart",
+        "BigBasket"
+      ],
+      "highlights": [
+        "lion dates Brand - Trusted Quality",
+        "Food - Spreads Category",
+        "Affordable at ₹9-11",
+        "Available in 10g",
+        "Premium Quality",
+        "Available on 3 platforms"
+      ],
+      "nutrients": [
+        "Vitamin E - Antioxidant protection",
+        "Omega-3 - Heart health",
+        "Dietary Fiber - Digestive health",
+        "Protein - Muscle building",
+        "Magnesium - Muscle function",
+        "Carbohydrates - Quick energy",
+        "Healthy Fats - Heart health"
+      ],
+      "fssai_license": "10012042000244",
+      "product_sku": "LION-LION_D-001",
+      "sku_source": "User Upload",
+      "hsn_code": "2008",
+      "final_selling_price": 185.0,
+      "selling_price": 185.0,
+      "barcode": "20086040",
+      "barcode_type": "GTIN-13",
+      "image_url": "https://liondates.com/cdn/shop/files/1.Datesinhoney_productfocus.png?v=1773383963&width=1445",
+      "image_urls": [
+        "https://liondates.com/cdn/shop/files/1.Datesinhoney_productfocus.png?v=1773383963&width=1445",
+        "https://liondates.com/cdn/shop/files/dateshoney_1.jpg?v=1739704587&width=1080",
+        "https://liondates.com/cdn/shop/files/Lion-Fig-in-Honey-Lion-Dates-95545533.jpg?v=1716380700&width=720",
+        "https://liondates.com/cdn/shop/files/Lion-Fig-in-Honey-Lion-Dates-95545649.jpg?v=1739705462&width=1080",
+        "http://liondates.com/cdn/shop/files/Lion-Mixed-Nuts-in-Honey-Lion-Dates-95787173.jpg?v=1716438485",
+        "http://liondates.com/cdn/shop/files/Lion-Amla-in-Honey-Lion-Dates-95589650.jpg?v=1716381007",
+        "https://liondates.com/cdn/shop/files/2.Datesinhoney_benefits.png?v=1773383963&width=390",
+        "https://liondates.com/cdn/shop/files/Arabian_dates_500g_front.png?v=1739617157&width=1838",
+        "https://liondates.com/cdn/shop/files/Sukkari_dates_front.png?v=1739615376&width=2048",
+        "https://5.imimg.com/data5/SELLER/Default/2023/6/312791417/NH/RZ/CD/180805796/lion-honey-dates-250x250.webp"
+      ],
+      "search_query": "Lion Dates Lion Dates 450g Health Foods Introducing Lion Dates 450g from the trusted Lion Dates brand. A premium quality product offering superior taste, authentic ingredients, and reliable value. Backed by Lion Dates's reputation for quality and consistency. ₹160-220"
+    }
+  ]
+}

backend/app/main.py

@@ -21,6 +21,7 @@ from app.infrastructure.settings import API_CORS_ORIGINS
 from app.api.routers import health, brands, search, chat, catalog, system
 from app.api.routers import stores, discounts, analytics as store_analytics, trending, recommendations, store_admin
 from app.api.routers import nutrition, nutrition_admin, upload
+from app.api.routers import auth, user_products, admin_train
 from app.services.store_db import ensure_store_intelligence_schema
 from app.services.nutrition_db import ensure_nutrition_schema
 
@@ -64,6 +65,9 @@ app.add_middleware(
 )
 
 app.include_router(health.router, prefix="/api")
+app.include_router(auth.router, prefix="/api")
+app.include_router(user_products.router, prefix="/api")
+app.include_router(admin_train.router, prefix="/api")
 app.include_router(system.router, prefix="/api")
 app.include_router(brands.router, prefix="/api")
 app.include_router(search.router, prefix="/api")

backend/app/services/rag_service.py

@@ -70,6 +70,11 @@ class RetrievedProduct:
     fssai_license: Optional[str] = None
     product_sku: Optional[str] = None
     sku_source: Optional[str] = None
+    hsn_code: Optional[str] = None
+    final_selling_price: Optional[float] = None
+    selling_price: Optional[float] = None
+    barcode: Optional[str] = None
+    barcode_type: Optional[str] = None
     distance: float = 1.0
 
     @property
@@ -95,6 +100,11 @@ class RetrievedProduct:
             "fssai_license": self.fssai_license,
             "product_sku": self.product_sku,
             "sku_source": self.sku_source,
+            "hsn_code": self.hsn_code,
+            "final_selling_price": self.final_selling_price,
+            "selling_price": self.selling_price,
+            "barcode": self.barcode,
+            "barcode_type": self.barcode_type,
             "similarity": round(self.similarity, 4),
         }
 
@@ -127,19 +137,54 @@ def _row_to_retrieved_product(row: Dict[str, Any]) -> RetrievedProduct:
     image_id = row.get("image_id") or ""
     brand = (row.get("brand") or "").title()
 
-    s3_single = s3_service.get_product_image_url(brand, image_id)
-    s3_list = s3_service.get_product_image_urls(brand, image_id)
-
     db_single = _clean_url(row.get("image_url"))
     db_list = [_clean_url(u) for u in (row.get("image_urls") or []) if u]
 
-    final_urls = s3_list if s3_list else db_list
+    final_urls = db_list
     if not final_urls and db_single:
         final_urls = [db_single]
-    if not final_urls and s3_single:
-        final_urls = [s3_single]
 
-    primary_url = (final_urls[0] if final_urls else "") or db_single or s3_single
+    if not final_urls and s3_service.enabled and image_id:
+        s3_list = s3_service.get_product_image_urls(brand, image_id)
+        if s3_list:
+            final_urls = s3_list
+
+    primary_url = (final_urls[0] if final_urls else None) or db_single
+    if not primary_url and s3_service.enabled and image_id:
+        primary_url = s3_service.get_product_image_url(brand, image_id)
+
+    hsn = row.get("hsn_code") or row.get("HSN_Code") or row.get("hsn") or None
+    if hsn is not None:
+        hsn = str(hsn).strip() or None
+
+    raw_fsp = row.get("final_selling_price") if "final_selling_price" in row else row.get("Final_Selling_Price")
+    if raw_fsp is None:
+        raw_fsp = row.get("final_price")
+    try:
+        fsp = float(raw_fsp) if raw_fsp is not None and str(raw_fsp).strip() != "" else None
+    except (ValueError, TypeError):
+        fsp = None
+
+    raw_sp = row.get("selling_price") if "selling_price" in row else row.get("Selling_Price")
+    try:
+        sp = float(raw_sp) if raw_sp is not None and str(raw_sp).strip() != "" else None
+    except (ValueError, TypeError):
+        sp = None
+
+    if fsp is None and sp is not None:
+        fsp = sp
+
+    bcd = row.get("barcode") or row.get("Barcode") or None
+    if bcd is not None:
+        bcd = str(bcd).strip() or None
+
+    bcd_type = row.get("barcode_type") or row.get("Barcode_Type") or None
+    if bcd_type is not None:
+        bcd_type = str(bcd_type).strip() or None
+
+    fssai = row.get("fssai_license") or row.get("fssai") or row.get("fssai_number") or row.get("FSSAI_License") or row.get("fssai_lic_no") or None
+    if fssai is not None:
+        fssai = str(fssai).strip() or None
 
     return RetrievedProduct(
         image_id=image_id,
@@ -155,9 +200,14 @@ def _row_to_retrieved_product(row: Dict[str, Any]) -> RetrievedProduct:
         providers=list(row.get("providers") or []),
         highlights=list(row.get("highlights") or []),
         nutrients=list(row.get("nutrients") or []),
-        fssai_license=row.get("fssai_license"),
+        fssai_license=fssai,
         product_sku=row.get("product_sku") or None,
         sku_source=row.get("sku_source") or None,
+        hsn_code=hsn,
+        final_selling_price=fsp,
+        selling_price=sp,
+        barcode=bcd,
+        barcode_type=bcd_type,
         distance=float(row.get("distance", 1.0)),
     )
 

backend/app/services/s3_service.py

@@ -168,35 +168,31 @@ class S3Service:
             logger.error(f"❌ S3 upload failed for {key}: {e}")
             return False
     
-    async def process_product_images(self, product: dict, image_urls: List[str], brand: str = None, max_images: int = 10) -> str:
+    async def process_product_images(self, product: dict, image_urls: List[str], brand: str = None, max_images: int = 10):
         """
         Download and upload exactly max_images images for a product
-        Returns the unique image_id used for the folder
+        Returns tuple of (image_id, list of uploaded S3 public URLs)
         """
         if not self.enabled or not image_urls:
-            return ""
+            return "", []
         
         id_source = product.get('product_name') or product.get('title', 'unknown_product')
         image_id = self.generate_image_id(id_source)
-        uploaded_count = 0
+        uploaded_urls = []
         
         # Limit to max_images
         images_to_process = image_urls[:max_images]
+        storage_brand_name = resolve_parent_brand(brand) if brand else "products"
+        brand_low = storage_brand_name.lower()
         
         async with aiohttp.ClientSession() as session:
-            logger.info(f"📸 Processing {len(images_to_process)} images for {product_name}")
+            logger.info(f"📸 Processing {len(images_to_process)} images for {id_source}")
             
             for i, url in enumerate(images_to_process):
                 try:
                     logger.info(f"Downloading image {i+1}/{len(images_to_process)}: {url}")
                     image_data = await self.download_image(url, session)
                     if image_data:
-                        # Extract file extension or default to jpg
-                        # Extract extension from the URL path only (ignore
-                        # query strings like "?width=200" which used to
-                        # leak into `ext`, e.g. ".jpg?width=200"), and fall
-                        # back to .jpg if it's not a recognised image
-                        # extension at all.
                         url_path = urlparse(url).path
                         ext = Path(url_path).suffix.lower()
                         if ext not in {'.jpg', '.jpeg', '.png', '.webp', '.gif', '.bmp'}:
@@ -204,7 +200,9 @@ class S3Service:
                         filename = f"image_{i:03d}{ext}"
                         
                         if self.upload_image(image_data, image_id, filename, brand):
-                            uploaded_count += 1
+                            key = f"daily/brands/{brand_low}/{image_id}/{filename}" if brand else f"daily/brands/products/{image_id}/{filename}"
+                            public_url = self.get_public_url(key)
+                            uploaded_urls.append(public_url)
                             logger.info(f"✅ Successfully uploaded image {i+1}/{len(images_to_process)}")
                         else:
                             logger.warning(f"❌ Failed to upload image {i+1}/{len(images_to_process)}")
@@ -217,10 +215,14 @@ class S3Service:
                 except Exception as e:
                     logger.warning(f"❌ Error processing image {i+1}/{len(images_to_process)} ({url}): {e}")
         
-        storage_brand_name = resolve_parent_brand(brand) if brand else brand
-        brand_path = f"daily/brands/{storage_brand_name.lower()}/" if brand else "daily/brands/products/"
-        logger.info(f"📸 Uploaded {uploaded_count}/{len(images_to_process)} images for product {product.get('title', 'Unknown')} to {brand_path}{image_id}")
-        return image_id
+        brand_path = f"daily/brands/{brand_low}/" if brand else "daily/brands/products/"
+        logger.info(f"📸 Uploaded {len(uploaded_urls)}/{len(images_to_process)} images for product {product.get('title', 'Unknown')} to {brand_path}{image_id}")
+        
+        cache_key = f"{brand_low}:{image_id}"
+        if uploaded_urls:
+            self._url_cache[cache_key] = uploaded_urls
+            
+        return image_id, uploaded_urls
 
 
     def get_public_url(self, key: str) -> str:
@@ -235,11 +237,13 @@ class S3Service:
         """Construct or fetch the first image URL for a product in S3."""
         if not self.enabled or not image_id or not brand:
             return ""
-        urls = self.get_product_image_urls(brand, image_id)
-        if urls:
-            return urls[0]
-        storage_brand = resolve_parent_brand(brand)
-        key = f"daily/brands/{storage_brand.lower()}/{image_id}/image_000.jpg"
+        storage_brand = resolve_parent_brand(brand) if brand else "products"
+        brand_low = storage_brand.lower() if brand else "products"
+        cache_key = f"{brand_low}:{image_id}"
+        if cache_key in self._url_cache and self._url_cache[cache_key]:
+            return self._url_cache[cache_key][0]
+            
+        key = f"daily/brands/{brand_low}/{image_id}/image_000.jpg"
         return self.get_public_url(key)
 
     def get_product_image_urls(self, brand: str, image_id: str) -> List[str]:
@@ -247,14 +251,14 @@ class S3Service:
         if not self.enabled or not image_id:
             return []
         
-        cache_key = f"{brand}:{image_id}"
+        storage_brand = resolve_parent_brand(brand) if brand else brand
+        brand_low = storage_brand.lower() if brand else "products"
+        cache_key = f"{brand_low}:{image_id}"
         if cache_key in self._url_cache:
             return self._url_cache[cache_key]
 
         try:
             # Try specific prefix patterns to find existing data
-            storage_brand = resolve_parent_brand(brand) if brand else brand
-            brand_low = storage_brand.lower() if brand else "products"
             prefixes = [
                 f"daily/brands/{brand_low}/{image_id}/",
                 f"daily/brands/products/{image_id}/",
@@ -279,7 +283,7 @@ class S3Service:
                             image_urls.append(self.get_public_url(key))
                     
                     if image_urls:
-                        logger.info(f"✅ Found {len(image_urls)} images under prefix: {prefix}")
+                        logger.debug("Found %d images under prefix: %s", len(image_urls), prefix)
                         res = sorted(image_urls)
                         self._url_cache[cache_key] = res
                         return res

backend/app/services/vector_store.py

@@ -11,6 +11,9 @@ from app.infrastructure.settings import DATABASE_URL, USE_PGVECTOR, DB_HOST, DB_
 from app.services.brand_registry import BRAND_ALIASES, resolve_parent_brand
 
 
+from app.services.s3_service import s3_service
+
+
 logger = logging.getLogger(__name__)
 
 
@@ -50,9 +53,14 @@ def get_brand_table_ddl(brand: str) -> str:
         -- FSSAI license
         fssai_license TEXT,
         
-        -- Product SKU
+        -- Product SKU & Tax/Price/Barcode details
         product_sku TEXT,
         sku_source TEXT,
+        hsn_code TEXT,
+        final_selling_price NUMERIC,
+        selling_price NUMERIC,
+        barcode TEXT,
+        barcode_type TEXT,
         
         -- Essential fields
         highlights TEXT[],
@@ -106,6 +114,11 @@ def _ensure_columns(cur, table_name: str) -> None:
         "fssai_license": "TEXT",
         "product_sku": "TEXT",
         "sku_source": "TEXT",
+        "hsn_code": "TEXT",
+        "final_selling_price": "NUMERIC",
+        "selling_price": "NUMERIC",
+        "barcode": "TEXT",
+        "barcode_type": "TEXT",
         "highlights": "TEXT[]",
         "nutrients": "TEXT[]",
         "search_query": "TEXT",
@@ -127,7 +140,7 @@ def _ensure_columns(cur, table_name: str) -> None:
                 logger.info(f"Added missing column '{col}' to {table_name}")
 
     # 2. Relax legacy NOT NULL constraints on columns not present in standard insert
-    inserted_cols = {"id", "product_name", "title", "description", "category", "image_id", "image_url", "image_urls", "price_range", "size_variants", "providers", "fssai_license", "product_sku", "sku_source", "highlights", "nutrients", "search_query", "embedding", "created_at", "updated_at"}
+    inserted_cols = {"id", "product_name", "title", "description", "category", "image_id", "image_url", "image_urls", "price_range", "size_variants", "providers", "fssai_license", "product_sku", "sku_source", "hsn_code", "final_selling_price", "selling_price", "barcode", "barcode_type", "highlights", "nutrients", "search_query", "embedding", "created_at", "updated_at"}
     for col, is_nullable, col_def in col_info:
         if col not in inserted_cols and is_nullable == 'NO' and col_def is None:
             cur.execute(f"ALTER TABLE {table_name} ALTER COLUMN {col} DROP NOT NULL")
@@ -205,6 +218,11 @@ def upsert_brand_products(brand: str, products: List[Dict[str, Any]], cleanup: b
             image_urls = []
         if not image_urls and image_url:
             image_urls = [image_url]
+        if not image_urls and not image_url and image_id and s3_service.enabled:
+            s3_single = s3_service.get_product_image_url(brand, image_id)
+            if s3_single:
+                image_url = s3_single
+                image_urls = [s3_single]
         
         # Essential pricing fields
         price_range = p.get("price_range") or ""
@@ -227,10 +245,32 @@ def upsert_brand_products(brand: str, products: List[Dict[str, Any]], cleanup: b
                     size_variants_str.append(variant)
             size_variants = size_variants_str
         
-        # Product SKU fields
+        # Product SKU & HSN / Price / Barcode fields
         product_sku = p.get("product_sku") or ""
         sku_source = p.get("sku_source") or ""
         
+        hsn_code = str(p.get("hsn_code") or p.get("HSN_Code") or p.get("hsn") or "").strip() or None
+        
+        raw_fsp = p.get("final_selling_price") if "final_selling_price" in p else p.get("Final_Selling_Price")
+        if raw_fsp is None:
+            raw_fsp = p.get("final_price")
+        try:
+            final_selling_price = float(raw_fsp) if raw_fsp is not None and str(raw_fsp).strip() != "" else None
+        except (ValueError, TypeError):
+            final_selling_price = None
+
+        raw_sp = p.get("selling_price") if "selling_price" in p else p.get("Selling_Price")
+        try:
+            selling_price = float(raw_sp) if raw_sp is not None and str(raw_sp).strip() != "" else None
+        except (ValueError, TypeError):
+            selling_price = None
+
+        if final_selling_price is None and selling_price is not None:
+            final_selling_price = selling_price
+
+        barcode = str(p.get("barcode") or p.get("Barcode") or "").strip() or None
+        barcode_type = str(p.get("barcode_type") or p.get("Barcode_Type") or "").strip() or None
+
         # Essential fields
         highlights = p.get("highlights", [])
         if not isinstance(highlights, list):
@@ -267,6 +307,11 @@ def upsert_brand_products(brand: str, products: List[Dict[str, Any]], cleanup: b
             fssai_license,
             product_sku,
             sku_source,
+            hsn_code,
+            final_selling_price,
+            selling_price,
+            barcode,
+            barcode_type,
             highlights,      # TEXT[] - psycopg will handle conversion
             nutrients,       # TEXT[] - psycopg will handle conversion
             search_query,
@@ -280,8 +325,8 @@ def upsert_brand_products(brand: str, products: List[Dict[str, Any]], cleanup: b
             f"""
             INSERT INTO {table_name} 
             (product_name, title, description, category, image_id, image_url, image_urls, price_range, size_variants, providers, 
-             fssai_license, product_sku, sku_source, highlights, nutrients, search_query, embedding)
-            VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
+             fssai_license, product_sku, sku_source, hsn_code, final_selling_price, selling_price, barcode, barcode_type, highlights, nutrients, search_query, embedding)
+            VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
             ON CONFLICT (image_id) DO UPDATE SET
                 product_name = EXCLUDED.product_name,
                 title = EXCLUDED.title,
@@ -295,6 +340,11 @@ def upsert_brand_products(brand: str, products: List[Dict[str, Any]], cleanup: b
                 fssai_license = EXCLUDED.fssai_license,
                 product_sku = EXCLUDED.product_sku,
                 sku_source = EXCLUDED.sku_source,
+                hsn_code = EXCLUDED.hsn_code,
+                final_selling_price = EXCLUDED.final_selling_price,
+                selling_price = EXCLUDED.selling_price,
+                barcode = EXCLUDED.barcode,
+                barcode_type = EXCLUDED.barcode_type,
                 highlights = EXCLUDED.highlights,
                 nutrients = EXCLUDED.nutrients,
                 search_query = EXCLUDED.search_query,

backend/data/seed_catalogs/brand_catalog_lion_dates.json

@@ -2,8 +2,8 @@
   "brand": "lion dates",
   "search_query": null,
   "generation_timestamp": "C:\\Brand_Catalog_LLM\\Product_Catalog",
-  "total_products": 19,
-  "total_images": 153,
+  "total_products": 21,
+  "total_images": 164,
   "engine_info": {
     "gemini_enabled": true,
     "architecture": "Ollama LLM + Open-Source Image Pipeline (Open*Facts / Wikimedia / DuckDuckGo / Playwright-last-resort) + Deterministic Product Validation"
@@ -8928,6 +8928,111 @@
         0.04359172284603119,
         0.018032213672995567
       ]
+    },
+    {
+      "image_id": "lion_dates_lion_dates_450g",
+      "product_name": "Lion Dates 450g",
+      "title": "Lion Dates 450g",
+      "brand": "Lion Dates",
+      "brand_name": "Lion Dates",
+      "category": "Health Foods",
+      "description": "Premium Quality Lion Dates 450g",
+      "price_range": "₹160-220",
+      "size_variants": [
+        "450g"
+      ],
+      "providers": [
+        "Amazon",
+        "Flipkart",
+        "BigBasket"
+      ],
+      "highlights": [
+        "lion dates Brand - Trusted Quality",
+        "Food - Spreads Category",
+        "Affordable at ₹9-11",
+        "Available in 10g",
+        "Premium Quality",
+        "Available on 3 platforms"
+      ],
+      "nutrients": [
+        "Vitamin E - Antioxidant protection",
+        "Omega-3 - Heart health",
+        "Dietary Fiber - Digestive health",
+        "Protein - Muscle building",
+        "Magnesium - Muscle function",
+        "Carbohydrates - Quick energy",
+        "Healthy Fats - Heart health"
+      ],
+      "fssai_license": "10012042000244",
+      "product_sku": "LION-LION_D-001",
+      "sku_source": "User Upload",
+      "hsn_code": "2008",
+      "final_selling_price": 185.0,
+      "selling_price": 185.0,
+      "barcode": "20086040",
+      "barcode_type": "GTIN-13",
+      "image_url": "https://liondates.com/cdn/shop/files/4.datespowder_lifestyle.png?v=1773397173&width=1445",
+      "image_urls": [
+        "https://liondates.com/cdn/shop/files/4.datespowder_lifestyle.png?v=1773397173&width=1445"
+      ],
+      "search_query": "Lion Dates Lion Dates 450g Health Foods Premium Quality Lion Dates 450g ₹160-220"
+    },
+    {
+      "image_id": "lion_dates_lion_dates_750g",
+      "product_name": "Lion Dates 750g",
+      "title": "Lion Dates 750g",
+      "brand": "Lion Dates",
+      "brand_name": "Lion Dates",
+      "category": "Health Foods",
+      "description": "Introducing Lion Dates 750g from the trusted Lion Dates brand. A premium quality product offering superior taste, authentic ingredients, and reliable value. Backed by Lion Dates's reputation for quality and consistency.",
+      "price_range": "₹250-320",
+      "size_variants": [
+        "750g"
+      ],
+      "providers": [
+        "Amazon",
+        "Flipkart",
+        "BigBasket"
+      ],
+      "highlights": [
+        "lion dates Brand - Trusted Quality",
+        "Food - Spreads Category",
+        "Affordable at ₹9-11",
+        "Available in 10g",
+        "Premium Quality",
+        "Available on 3 platforms"
+      ],
+      "nutrients": [
+        "Vitamin E - Antioxidant protection",
+        "Omega-3 - Heart health",
+        "Dietary Fiber - Digestive health",
+        "Protein - Muscle building",
+        "Magnesium - Muscle function",
+        "Carbohydrates - Quick energy",
+        "Healthy Fats - Heart health"
+      ],
+      "fssai_license": "10012042000244",
+      "product_sku": "LION-LION_D-001",
+      "sku_source": "User Upload",
+      "hsn_code": "2008",
+      "final_selling_price": 280.0,
+      "selling_price": 280.0,
+      "barcode": "20086045",
+      "barcode_type": "GTIN-13",
+      "image_url": "https://liondates.com/cdn/shop/files/1.Datesinhoney_productfocus.png?v=1773383963&width=1445",
+      "image_urls": [
+        "https://liondates.com/cdn/shop/files/1.Datesinhoney_productfocus.png?v=1773383963&width=1445",
+        "https://liondates.com/cdn/shop/files/dateshoney_1.jpg?v=1739704587&width=1080",
+        "https://liondates.com/cdn/shop/files/Lion-Fig-in-Honey-Lion-Dates-95545533.jpg?v=1716380700&width=720",
+        "https://liondates.com/cdn/shop/files/Lion-Fig-in-Honey-Lion-Dates-95545649.jpg?v=1739705462&width=1080",
+        "http://liondates.com/cdn/shop/files/Lion-Mixed-Nuts-in-Honey-Lion-Dates-95787173.jpg?v=1716438485",
+        "http://liondates.com/cdn/shop/files/Lion-Amla-in-Honey-Lion-Dates-95589650.jpg?v=1716381007",
+        "https://liondates.com/cdn/shop/files/2.Datesinhoney_benefits.png?v=1773383963&width=390",
+        "https://liondates.com/cdn/shop/files/Arabian_dates_500g_front.png?v=1739617157&width=1838",
+        "https://liondates.com/cdn/shop/files/Sukkari_dates_front.png?v=1739615376&width=2048",
+        "https://5.imimg.com/data5/SELLER/Default/2023/6/312791417/NH/RZ/CD/180805796/lion-honey-dates-250x250.webp"
+      ],
+      "search_query": "Lion Dates Lion Dates 750g Health Foods Introducing Lion Dates 750g from the trusted Lion Dates brand. A premium quality product offering superior taste, authentic ingredients, and reliable value. Backed by Lion Dates's reputation for quality and consistency. ₹250-320"
     }
   ],
   "rejected_products": [],

backend/data/seed_catalogs/brand_catalog_naga.json

@@ -0,0 +1,59 @@
+{
+  "brand": "naga",
+  "search_query": "Naga products catalog",
+  "generation_timestamp": "C:\\Brand_Catalog_LLM\\RAG_Model_Nutrition_Intelligence\\RAG_Model_Full_Implement\\backend\\app\\api\\routers\\user_products.py",
+  "total_products": 1,
+  "total_images": 2,
+  "products": [
+    {
+      "image_id": "naga_naga_maida_2kg",
+      "product_name": "Naga Maida 2kg",
+      "title": "Naga Maida 2kg",
+      "brand": "Naga",
+      "brand_name": "Naga",
+      "category": "Flour & Grains",
+      "description": "High grade refined wheat flour maida",
+      "price_range": "₹90-110",
+      "size_variants": [
+        "2kg"
+      ],
+      "providers": [
+        "Amazon",
+        "Flipkart",
+        "BigBasket",
+        "Jiomart",
+        "Blinkit",
+        "Zepto"
+      ],
+      "highlights": [
+        "Naga Brand - Trusted Quality",
+        "Atta & Staples Category",
+        "Affordable at ₹41-49",
+        "Available in 250g",
+        "Premium Quality",
+        "Available on 6 platforms"
+      ],
+      "nutrients": [
+        "Carbohydrates - Sustained energy",
+        "Dietary Fiber - Digestive health",
+        "Vitamin B1 (Thiamine) - Energy metabolism",
+        "Iron - Blood health",
+        "Folic Acid - Cell growth"
+      ],
+      "fssai_license": "10012042000192",
+      "product_sku": "NAGA-NAGA_M-001",
+      "sku_source": "User Upload",
+      "hsn_code": "1101",
+      "final_selling_price": 98.0,
+      "selling_price": 98.0,
+      "barcode": "8906012345001",
+      "barcode_type": "GTIN-13",
+      "image_url": "https://nearle.sgp1.digitaloceanspaces.com/daily/brands/naga/naga_naga_maida_250g/image_000.jpg",
+      "image_urls": [
+        "https://nearle.sgp1.digitaloceanspaces.com/daily/brands/naga/naga_naga_maida_250g/image_000.jpg",
+        "https://nearle.sgp1.digitaloceanspaces.com/daily/brands/naga/naga_naga_maida_250g/image_001.png"
+      ],
+      "search_query": "Naga Naga Maida 2kg Flour & Grains High grade refined wheat flour maida ₹90-110"
+    }
+  ]
+}

backend/scripts/backfill_barcodes.py

@@ -0,0 +1,93 @@
+#!/usr/bin/env python3
+"""
+Backfill PostgreSQL brand tables with `barcode` and `barcode_type` from seed catalogs.
+This ensures existing products with barcode details in seed files or DB rows are populated and served to the API and UI.
+"""
+from __future__ import annotations
+
+import json
+import logging
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
+
+from app.services.vector_store import _connect, list_available_brands, _sanitize_name, resolve_parent_brand, ensure_brand_schema
+
+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 backfill_barcodes() -> None:
+    conn = _connect()
+    if not conn:
+        logger.error("Could not connect to PostgreSQL database.")
+        return
+
+    brands = list_available_brands()
+    logger.info("Ensuring schema for %d brand(s)...", len(brands))
+    for brand in brands:
+        ensure_brand_schema(brand)
+
+    seed_files = sorted(SEED_DIR.glob("*.json")) if SEED_DIR.exists() else []
+    logger.info("Found %d seed file(s) in %s", len(seed_files), SEED_DIR)
+
+    updated_count = 0
+    with conn.cursor() as cur:
+        for seed_file in seed_files:
+            try:
+                data = json.loads(seed_file.read_text(encoding="utf-8-sig"))
+            except Exception as e:
+                logger.warning("Could not read seed file %s: %s", seed_file.name, e)
+                continue
+
+            products = data.get("products", [])
+            brand = data.get("brand") or (products[0].get("brand_name") if products else None)
+            if not brand or not products:
+                continue
+
+            table_name = f"brand_{_sanitize_name(resolve_parent_brand(brand))}"
+
+            for p in products:
+                image_id = p.get("image_id") or p.get("sku") or ""
+                product_name = p.get("product_name") or p.get("title") or ""
+                barcode = str(p.get("barcode") or p.get("Barcode") or "").strip() or None
+                barcode_type = str(p.get("barcode_type") or p.get("Barcode_Type") or "").strip() or None
+
+                if not barcode and not barcode_type:
+                    continue
+
+                if image_id:
+                    cur.execute(
+                        f"""
+                        UPDATE {table_name}
+                        SET barcode = COALESCE(%s, barcode),
+                            barcode_type = COALESCE(%s, barcode_type)
+                        WHERE image_id = %s
+                        """,
+                        (barcode, barcode_type, image_id)
+                    )
+                    if cur.rowcount > 0:
+                        updated_count += cur.rowcount
+                elif product_name:
+                    cur.execute(
+                        f"""
+                        UPDATE {table_name}
+                        SET barcode = COALESCE(%s, barcode),
+                            barcode_type = COALESCE(%s, barcode_type)
+                        WHERE product_name = %s
+                        """,
+                        (barcode, barcode_type, product_name)
+                    )
+                    if cur.rowcount > 0:
+                        updated_count += cur.rowcount
+
+        conn.commit()
+    conn.close()
+    logger.info("🎉 Barcode backfill complete! Updated %d product row(s).", updated_count)
+
+
+if __name__ == "__main__":
+    backfill_barcodes()

backend/scripts/backfill_hsn_prices.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python3
+"""
+Backfill PostgreSQL brand tables with `hsn_code`, `final_selling_price`, and `selling_price` from seed catalogs.
+This ensures existing products with these details in seed files or DB rows are populated and served to the API and UI.
+"""
+from __future__ import annotations
+
+import json
+import logging
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
+
+from app.services.vector_store import _connect, list_available_brands, _sanitize_name, resolve_parent_brand, ensure_brand_schema
+
+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 backfill_hsn_prices() -> None:
+    conn = _connect()
+    if not conn:
+        logger.error("Could not connect to PostgreSQL database.")
+        return
+
+    brands = list_available_brands()
+    logger.info("Ensuring schema for %d brand(s)...", len(brands))
+    for brand in brands:
+        ensure_brand_schema(brand)
+
+    seed_files = sorted(SEED_DIR.glob("*.json")) if SEED_DIR.exists() else []
+    logger.info("Found %d seed file(s) in %s", len(seed_files), SEED_DIR)
+
+    updated_count = 0
+    with conn.cursor() as cur:
+        for seed_file in seed_files:
+            try:
+                data = json.loads(seed_file.read_text(encoding="utf-8-sig"))
+            except Exception as e:
+                logger.warning("Could not read seed file %s: %s", seed_file.name, e)
+                continue
+
+            products = data.get("products", [])
+            brand = data.get("brand") or (products[0].get("brand_name") if products else None)
+            if not brand or not products:
+                continue
+
+            table_name = f"brand_{_sanitize_name(resolve_parent_brand(brand))}"
+
+            for p in products:
+                image_id = p.get("image_id") or p.get("sku") or ""
+                product_name = p.get("product_name") or p.get("title") or ""
+                hsn = str(p.get("hsn_code") or p.get("HSN_Code") or p.get("hsn") or "").strip() or None
+
+                raw_fsp = p.get("final_selling_price") if "final_selling_price" in p else p.get("Final_Selling_Price")
+                if raw_fsp is None:
+                    raw_fsp = p.get("final_price")
+                try:
+                    fsp = float(raw_fsp) if raw_fsp is not None and str(raw_fsp).strip() != "" else None
+                except (ValueError, TypeError):
+                    fsp = None
+
+                raw_sp = p.get("selling_price") if "selling_price" in p else p.get("Selling_Price")
+                try:
+                    sp = float(raw_sp) if raw_sp is not None and str(raw_sp).strip() != "" else None
+                except (ValueError, TypeError):
+                    sp = None
+
+                if fsp is None and sp is not None:
+                    fsp = sp
+
+                if not hsn and fsp is None and sp is None:
+                    continue
+
+                if image_id:
+                    cur.execute(
+                        f"""
+                        UPDATE {table_name}
+                        SET hsn_code = COALESCE(%s, hsn_code),
+                            final_selling_price = COALESCE(%s, final_selling_price),
+                            selling_price = COALESCE(%s, selling_price)
+                        WHERE image_id = %s
+                        """,
+                        (hsn, fsp, sp, image_id)
+                    )
+                    if cur.rowcount > 0:
+                        updated_count += cur.rowcount
+                elif product_name:
+                    cur.execute(
+                        f"""
+                        UPDATE {table_name}
+                        SET hsn_code = COALESCE(%s, hsn_code),
+                            final_selling_price = COALESCE(%s, final_selling_price),
+                            selling_price = COALESCE(%s, selling_price)
+                        WHERE product_name = %s
+                        """,
+                        (hsn, fsp, sp, product_name)
+                    )
+                    if cur.rowcount > 0:
+                        updated_count += cur.rowcount
+
+        conn.commit()
+    conn.close()
+    logger.info("🎉 HSN and Price backfill complete! Updated %d product row(s).", updated_count)
+
+
+if __name__ == "__main__":
+    backfill_hsn_prices()

backend/scripts/backfill_s3_urls.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+"""
+Backfill PostgreSQL product rows that have `image_id` set but empty/null `image_url` or `image_urls`.
+This updates products in-place in pgvector so that API requests and RAG queries serve image URLs directly from DB
+without making S3 list_objects_v2 network calls.
+"""
+from __future__ import annotations
+
+import logging
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
+
+from app.services.vector_store import _connect, list_available_brands, _sanitize_name, resolve_parent_brand, ensure_brand_schema
+from app.services.s3_service import s3_service
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
+logger = logger = logging.getLogger(__name__)
+
+
+def backfill_brand_images() -> None:
+    if not s3_service.enabled:
+        logger.warning("S3 service is not enabled. Skipping backfill.")
+        return
+
+    brands = list_available_brands()
+    logger.info("Found %d brands in PostgreSQL database", len(brands))
+
+    for brand in brands:
+        ensure_brand_schema(brand)
+
+    conn = _connect()
+    if not conn:
+        logger.error("Could not connect to PostgreSQL database.")
+        return
+
+    brands = list_available_brands()
+    logger.info("Found %d brands in PostgreSQL database", len(brands))
+
+    updated_total = 0
+    with conn.cursor() as cur:
+        for brand in brands:
+            table_name = f"brand_{_sanitize_name(resolve_parent_brand(brand))}"
+            try:
+                cur.execute(f"SELECT id, image_id, image_url, image_urls FROM {table_name}")
+                rows = cur.fetchall()
+            except Exception as e:
+                logger.warning("Could not read table %s: %s", table_name, e)
+                conn.rollback()
+                continue
+
+            for row in rows:
+                row_id, image_id, image_url, image_urls = row
+                if not image_id:
+                    continue
+
+                db_has_images = bool(image_url or (image_urls and any(image_urls)))
+                if not db_has_images:
+                    # Fetch from S3 (or construct primary S3 URL)
+                    s3_urls = s3_service.get_product_image_urls(brand, image_id)
+                    primary_url = s3_urls[0] if s3_urls else s3_service.get_product_image_url(brand, image_id)
+                    if not s3_urls and primary_url:
+                        s3_urls = [primary_url]
+
+                    if primary_url or s3_urls:
+                        cur.execute(
+                            f"UPDATE {table_name} SET image_url = %s, image_urls = %s WHERE id = %s",
+                            (primary_url, s3_urls, row_id)
+                        )
+                        updated_total += 1
+                        logger.info("Updated product ID %s in %s (image_id=%s) with %d image(s)", row_id, table_name, image_id, len(s3_urls))
+
+        conn.commit()
+    conn.close()
+    logger.info("🎉 Backfill complete! Updated %d product(s) in database.", updated_total)
+
+
+if __name__ == "__main__":
+    backfill_brand_images()

backend/tests/test_api.py

@@ -38,7 +38,10 @@ client = TestClient(app)
 def test_root() -> None:
     resp = client.get("/")
     assert resp.status_code == 200
-    assert "service" in resp.json()
+    if "text/html" in resp.headers.get("content-type", ""):
+        assert "<html" in resp.text.lower()
+    else:
+        assert "service" in resp.json()
 
 
 def test_health_degrades_gracefully_without_dependencies() -> None: