Update app.py

app.py

@@ -1,81 +1,32 @@
-import os
-from flask import Flask
-from flask_cors import CORS
-from flask_limiter import Limiter
-from flask_limiter.util import get_remote_address
-from dotenv import load_dotenv
-import logging
-from utils.db import init_db
-from config.config import Config
-from flask import render_template
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-# Load environment variables
-load_dotenv()
-
-# Logging setup
-logging.basicConfig(level=logging.INFO, format='%(asctime)s %(levelname)s %(message)s')
-
-app = Flask(__name__)
-app.config.from_object(Config)
-CORS(app)
-
-# Rate limiter
-limiter = Limiter(
-    get_remote_address,
-    app=app,
-    default_limits=["5 per minute"]
-)
-
-# Initialize DB
-init_db()
-
-# Register blueprints
-from routes.chat import chat_bp
-from routes.feedback import feedback_bp
-app.register_blueprint(chat_bp)
-app.register_blueprint(feedback_bp)
-
-@app.route("/")
-def home():
-    api_key = Config.HF_API_TOKEN  # Get the API key from your config
-    return render_template("index.html", api_key=api_key)
-
-@app.errorhandler(429)
-def ratelimit_handler(e):
-    return {"error": "Rate limit exceeded. Please try again later."}, 429
-
-# Load model (will be cached on Hugging Face servers)
-tokenizer = AutoTokenizer.from_pretrained("bitext/Mistral-7B-Customer-Support")
-model = AutoModelForCausalLM.from_pretrained("bitext/Mistral-7B-Customer-Support")
+import requests
+import os
 
 def chat(message, history):
-    # Format conversation history
-    messages = []
-    for human, assistant in history:
-        messages.append({"role": "user", "content": human})
-        messages.append({"role": "assistant", "content": assistant})
-    messages.append({"role": "user", "content": message})
+    API_URL = "https://api-inference.huggingface.co/models/bitext/Mistral-7B-Customer-Support"
+    headers = {"Authorization": f"Bearer {os.getenv('HF_TOKEN')}"}
     
-    # Generate response
-    inputs = tokenizer.apply_chat_template(
-        messages,
-        add_generation_prompt=True,
-        tokenize=True,
-        return_dict=True,
-        return_tensors="pt",
-    )
+    # Format the message for the API
+    payload = {"inputs": message}
     
-    outputs = model.generate(**inputs, max_new_tokens=150, temperature=0.7)
-    response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)
-    return response.strip()
+    try:
+        response = requests.post(API_URL, headers=headers, json=payload, timeout=30)
+        if response.status_code == 200:
+            result = response.json()
+            if isinstance(result, list) and len(result) > 0:
+                return result[0]["generated_text"]
+            else:
+                return "Sorry, I couldn't generate a response."
+        else:
+            return f"API Error: {response.status_code}"
+    except Exception as e:
+        return f"Error: {str(e)}"
 
 # Create Gradio interface
 demo = gr.ChatInterface(
     fn=chat,
     title="AI Customer Service Chatbot",
-    description="Powered by Mistral-7B Customer Support model",
+    description="Powered by Mistral-7B Customer Support (via Hugging Face API)",
     examples=[
         ["How can I reset my password?"],
         ["What are your return policies?"],
@@ -84,7 +35,4 @@ demo = gr.ChatInterface(
     ]
 )
 
-demo.launch()
-
-if __name__ == "__main__":
-    app.run(debug=True)
+demo.launch()