import gradio as gr
from llama_cpp import Llama

# Load the Mistral model
llm = Llama.from_pretrained(
    repo_id="bartowski/Mistral-Small-Instruct-2409-GGUF",
    filename="Mistral-Small-Instruct-2409-IQ2_M.gguf",
)

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    # Add history to messages
    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    # Add the current user message
    messages.append({"role": "user", "content": message})

    # Generate the response using the Mistral model
    response = llm.create_chat_completion(messages=messages)

    return response["choices"][0]["message"]["content"]  # Adjust based on your model's output format

# Set up Gradio Chat Interface
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)

if __name__ == "__main__":
    demo.launch()