Update app.py

app.py

@@ -1,25 +1,53 @@
-import streamlit as st
-import requests
 import os
+import requests
+import yaml
+from flask import Flask, request, jsonify
 from dotenv import load_dotenv
+from PIL import Image
+import io
+from transformers import pipeline
 
+# Load environment variables
 load_dotenv()
 api_key = os.getenv('HF_API_KEY')
 model_path = os.getenv('MODEL_PATH')
 
+app = Flask(__name__)
+
+# Load configuration
+with open('config.yaml', 'r') as file:
+    config = yaml.safe_load(file)
+
 def get_model_predictions(text):
     headers = {"Authorization": f"Bearer {api_key}"}
     payload = {"inputs": text}
-    response = requests.post(f"https://api.huggingface.co/models/{model_path}", headers=headers, json=payload)
+    response = requests.post(f"https://api-inference.huggingface.co/models/{model_path}", headers=headers, json=payload)
     return response.json()
 
-st.title("My AI Prediction App")
+def process_image(image_file):
+    image = Image.open(image_file)
+    # Implement image processing here
+    return "Image processed"
 
-text = st.text_area("Enter text to predict")
-
-if st.button("Predict"):
+@app.route('/predict', methods=['POST'])
+def predict():
+    data = request.get_json()
+    text = data.get('text')
+    image_file = data.get('image')
+    
     if text:
-        result = get_model_predictions(text)
-        st.write("Prediction:", result)
+        prediction = get_model_predictions(text)
+        return jsonify(prediction)
+    elif image_file:
+        image = io.BytesIO(image_file)
+        result = process_image(image)
+        return jsonify({"result": result})
     else:
-        st.write("Please enter some text.")
+        return jsonify({"error": "No input provided"})
+
+@app.route('/', methods=['GET'])
+def index():
+    return "Welcome to My AI! Use /predict to interact."
+
+if __name__ == '__main__':
+    app.run(debug=True, use_reloader=False)