Update app.py

app.py

@@ -1,59 +1,28 @@
-from fastapi import FastAPI, Request, HTTPException
-from fastapi.middleware.cors import CORSMiddleware
-from tensorflow.keras.models import load_model
+# app.py
+from fastapi import FastAPI, UploadFile, File
+from keras.models import load_model
+from PIL import Image
 import numpy as np
-import tensorflow as tf
 from huggingface_hub import hf_hub_download
 
-# 🔹 Download model file from your Hugging Face repo
-MODEL_PATH = hf_hub_download(
-    repo_id="aadityaramrame/blood-cell-cancer-detector",  # 👈 your repo
-    filename="cancer_classifier.h5"
-)
+# 🔹 Download your model from Hugging Face Hub
+MODEL_PATH = hf_hub_download(repo_id="aadityaramrame/blood-cell-cancer-detector",
+                              filename="cancer_classifier.h5")
 
-# 🔹 Load model
+# 🔹 Load the model
 model = load_model(MODEL_PATH)
 
-# ---------- Initialize FastAPI ----------
-app = FastAPI(title="GenAI Health Insight API", version="2.0")
+# 🔹 Initialize FastAPI app
+app = FastAPI(title="Blood Cell Cancer Detection API")
 
-# ---------- Enable CORS (so your friend’s frontend can call it) ----------
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],  # Or set ["https://yourfrontend.vercel.app"] for extra safety
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-# ---------- Root Endpoint ----------
 @app.get("/")
-def home():
-    return {"message": "Welcome to GenAI Health Insight API 🚀"}
+def root():
+    return {"message": "API is running successfully 🚀"}
 
-# ---------- Prediction Endpoint ----------
 @app.post("/predict")
-async def predict(request: Request):
-    """
-    Input example (JSON):
-    {
-        "features": [value1, value2, ..., valueN]
-    }
-    """
-    data = await request.json()
-    input_data = data.get("features")
-
-    if input_data is None:
-        raise HTTPException(status_code=400, detail="Missing 'features' in request body")
-    
-    # Prepare and predict
-    input_array = np.array(input_data).reshape(1, -1)
-    prediction = model.predict(input_array)
-    result = float(prediction[0][0])
-
-    return {"prediction": result, "status": "success"}
-
-# ---------- Health Check Endpoint ----------
-@app.get("/health")
-def health():
-    return {"status": "healthy"}
+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}