app.py

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

app = Flask(__name__)

# Load the Llama model (Ensure the GGUF file is in the same directory)
llm = Llama.from_pretrained(
    repo_id="bartowski/google_gemma-3-1b-it-GGUF",
    filename="google_gemma-3-1b-it-IQ4_XS.gguf",
)

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

@app.route("/chat", methods=["POST"])
def chat():
    user_input = request.json.get("message", "")
    if not user_input:
        return jsonify({"error": "Empty input"}), 400

    response = llm.create_chat_completion(
        messages=[{"role": "user", "content": user_input}]
    )
    
    bot_reply = response["choices"][0]["message"]["content"]
    
    return jsonify({"response": bot_reply})

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