app.py

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

app = Flask(__name__)

llm = Llama.from_pretrained(
    repo_id="yukiarimo/yuna-ai-v3",
    filename="yuna-ai-v3-q3_k_m.gguf",
    verbose=False
)

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

@app.route('/api/generate', methods=['POST'])
def generate():
    user_message = request.json['message']
    output = llm(
        f"Q: {user_message}\nA:",
        max_tokens=32,
        stop=["Q:", "\n"],
        echo=False
    )
    return jsonify({'response': output})

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5000)