Added classify car part URL

app.py

@@ -16,6 +16,10 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 from torchvision import transforms 
+from PIL import Image
+import torchvision.transforms as transforms
+
+import io
 
 all_letters = string.ascii_letters + " .,;'"
 n_letters = len(all_letters)
@@ -167,22 +171,28 @@ def classify_img(img):
     return model_output 
 
     
-@app.post("/upload")
+@app.post("/classifycarpart")
 async def upload_image(file: UploadFile = File(...)):
-    # Read the file into memory
-    image_bytes = await file.read()
-
-    # Convert to a PIL Image (or format expected by your ML model)
     try:
-        image = Image.open(io.BytesIO(image_bytes))
-    except Exception as e:
-        return JSONResponse(content={"error": "Invalid image format"}, status_code=400)
+        # Read and convert the image to a PIL Image
+        contents = await file.read()
+        image = Image.open(io.BytesIO(contents)).convert("RGB")
 
-    # Preprocess and run classification (example: dummy label here)
-    # Replace this with your actual model inference
-    #prediction = classify_img(image)  # 👈 Define this function to use your ML model
+        # Optional: Transform the image into a tensor for PyTorch
+        transform = transforms.Compose([
+            transforms.Resize((224, 224)),  # Resize to your model's expected input
+            transforms.ToTensor(),          # Convert to tensor
+        ])
+        tensor = transform(image).unsqueeze(0)  # Add batch dimension
 
-    return JSONResponse(content=classify_img(image), status_code=201)
+        # Dummy model prediction
+        # Replace this with your actual PyTorch model
+        prediction = torch.rand(1).item()
+
+        return JSONResponse(content={"message": "Image received", "prediction": prediction})
+
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=500)
 
 @app.get("/")
 def api_home():