Update app.py

app.py

@@ -1,28 +1,41 @@
 # app.py
 from fastapi import FastAPI, UploadFile, File
+from fastapi.responses import JSONResponse
 from keras.models import load_model
+from huggingface_hub import hf_hub_download
 from PIL import Image
 import numpy as np
-from huggingface_hub import hf_hub_download
+import uvicorn
 
-# 🔹 Download your model from Hugging Face Hub
-MODEL_PATH = hf_hub_download(repo_id="aadityaramrame/blood-cell-cancer-detector",
-                              filename="cancer_classifier.h5")
+# 🔹 Download model from Hugging Face Hub
+MODEL_PATH = hf_hub_download(
+    repo_id="aadityaramrame/blood-cell-cancer-detector",
+    filename="cancer_classifier.h5"
+)
 
-# 🔹 Load the model
+# 🔹 Load the trained model
 model = load_model(MODEL_PATH)
 
 # 🔹 Initialize FastAPI app
-app = FastAPI(title="Blood Cell Cancer Detection API")
+app = FastAPI(title="Cancer Detection API")
 
 @app.get("/")
-def root():
-    return {"message": "API is running successfully 🚀"}
+async def root():
+    return {"message": "🚀 Cancer Detection API is live!"}
 
 @app.post("/predict")
 async def predict(file: UploadFile = File(...)):
-    image = Image.open(file.file).resize((64, 64))  # adjust size as per training
-    img_array = np.expand_dims(np.array(image) / 255.0, axis=0)
-    prediction = model.predict(img_array)
-    result = int(np.argmax(prediction))
-    return {"prediction": result}
+    try:
+        image = Image.open(file.file).convert("RGB").resize((64, 64))  # use training size
+        img_array = np.expand_dims(np.array(image) / 255.0, axis=0)
+        prediction = model.predict(img_array)
+        result = int(np.argmax(prediction))
+        return JSONResponse(content={"prediction": result})
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=500)
+
+
+# 🔹 This line is CRUCIAL for Hugging Face Spaces
+# It ensures the FastAPI app is visible when the Space starts
+if __name__ == "__main__":
+    uvicorn.run("app:app", host="0.0.0.0", port=7860)