app.py

import requests
import os
from flask import Flask, request, jsonify, render_template

app = Flask(__name__)

# Set your Hugging Face API key
HF_API_KEY = os.getenv("HF_API_KEY")  # Store in environment variable

API_URL = "https://api-inference.huggingface.co/models/tiiuae/falcon-7b-instruct"
headers = {"Authorization": f"Bearer {HF_API_KEY}"}

@app.route('/')
def home():
    return render_template('index.html')

@app.route('/chat', methods=['POST'])
def chat(user_message):
    user_message = request.json.get("message")
    
    if not user_message:
        return jsonify({"error": "Empty message received"})

    try:
        payload = {
        "inputs": f"User: {user_message}\nBot:",
        #"inputs": f"[INST] {user_input} [/INST]",
        "parameters": {
            "temperature": 0.5,   # 🔥 Controls randomness (lower = more deterministic)
            "top_p": 0.9,         # 🎯 Focus on high-probability words
            "max_new_tokens": 50,  # ⏳ Limits response length
            "stop_sequences": ["\nUser:", "[INST]"]  # ⛔ Stops response at natural points
        }
    }
        response = requests.post(API_URL, headers=headers, json=payload)
        data = response.json()
        # print(response.status_code)  # Debugging: Print the HTTP status
        # print(response.json())       # Debugging: Print the API response

        # if response.status_code == 200:
        #     return response.json()[0]['generated_text']
        # else:
        #     return f"Error: {response.status_code} - {response.json()}"
        
        
        
        if "error" in data:
            return jsonify({"reply": f"Error: {data['error']}"})
        
        reply = data[0]['generated_text'] if isinstance(data, list) else data.get('generated_text', "No response")
        return jsonify({"reply": reply})

    except Exception as e:
        return jsonify({"reply": f"Error: {str(e)}"})

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=7860)