Update main.py

main.py

@@ -7,6 +7,7 @@ from fastapi.middleware.cors import CORSMiddleware
 from sentence_transformers import SentenceTransformer
 from PIL import Image
 import io
+import requests
 
 # Fix caching permissions for Hugging Face
 os.environ["HF_HOME"] = "./cache"
@@ -15,19 +16,21 @@ os.environ["SENTENCE_TRANSFORMERS_HOME"] = "./cache"
 
 app = FastAPI()
 
-# Enable CORS (so frontend on Netlify can call backend on HF)
+# Enable CORS (for frontend)
 app.add_middleware(
     CORSMiddleware,
-    allow_origins=["*"],  # for now allow all, can restrict to Netlify domain
+    allow_origins=["*"],  # you can restrict to your Netlify domain later
     allow_credentials=True,
     allow_methods=["*"],
     allow_headers=["*"],
 )
 
-# Load product metadata
-with open("id_mapping.json", "r", encoding="utf-8") as f:
+# Load products directly from products.json
+with open("products.json", "r", encoding="utf-8") as f:
     products = json.load(f)
 
+print(f"📦 Loaded {len(products)} products")
+
 # Load FAISS index
 index = faiss.read_index("products.index")
 
@@ -50,17 +53,23 @@ def search_text(query: str = Form(...), top_k: int = 5, min_score: float = 0.0):
     distances, indices = index.search(query_emb, top_k)
 
     results = []
-    for score, idx in zip(distances[0], indices[0]):
-        if score >= min_score:  # filter by threshold
-            item = products[idx]
-            item["score"] = float(score)
+    for dist, idx in zip(distances[0], indices[0]):
+        score = float(1 - dist)  # convert distance to similarity (optional)
+        if score >= min_score:
+            item = products[idx].copy()
+            item["score"] = score
             results.append(item)
 
     return {"matches": results}
 
 
-@app.post("/match")  # 👈 Renamed to match frontend
-async def search_image(file: UploadFile = File(None), image_url: str = Form(None), top_k: int = 5, min_score: float = 0.0):
+@app.post("/match")  # image search
+async def search_image(
+    file: UploadFile = File(None),
+    image_url: str = Form(None),
+    top_k: int = 5,
+    min_score: float = 0.0
+):
     """
     Search products using image query (upload or URL).
     """
@@ -68,7 +77,6 @@ async def search_image(file: UploadFile = File(None), image_url: str = Form(None
         image_bytes = await file.read()
         image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
     elif image_url:
-        import requests
         response = requests.get(image_url)
         image = Image.open(io.BytesIO(response.content)).convert("RGB")
     else:
@@ -78,10 +86,11 @@ async def search_image(file: UploadFile = File(None), image_url: str = Form(None
     distances, indices = index.search(image_emb, top_k)
 
     results = []
-    for score, idx in zip(distances[0], indices[0]):
+    for dist, idx in zip(distances[0], indices[0]):
+        score = float(1 - dist)  # convert distance to similarity
         if score >= min_score:
-            item = products[idx]
-            item["score"] = float(score)
+            item = products[idx].copy()
+            item["score"] = score
             results.append(item)
 
     return {"matches": results}