def generate_response(prompt):
    response = llm.create_chat_completion(
        messages=[
            {
                "role": "user",
                "content": prompt
            }
        ]
    )
    return response["choices"][0]["message"]["content"]

iface = gr.Interface(
    fn=generate_response,
    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your prompt here..."),
    outputs=gr.outputs.Textbox(),
    title="Llama Model",
    description="A Gradio interface to interact with the Llama model.",
)

iface.launch()