app.py

from flask import Flask, request, jsonify, render_template
from llama_cpp import Llama
import os

app = Flask(__name__)

# Initialize the LLM
llm = Llama.from_pretrained(
    repo_id="unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF",
    filename="DeepSeek-R1-Distill-Qwen-1.5B-Q2_K.gguf",
)

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

@app.route('/chat', methods=['POST'])
def chat():
    data = request.json
    message = data.get('message', '')
    
    # Format the message for chat completion
    messages = [
        {"role": "user", "content": message}
    ]
    
    try:
        response = llm.create_chat_completion(messages=messages)
        return jsonify({
            "response": response['choices'][0]['message']['content']
        })
    except Exception as e:
        return jsonify({"error": str(e)}), 500

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