import gradio as gr
from ctransformers import AutoModelForCausalLM

# Use ctransformers for GGUF models
client = AutoModelForCausalLM.from_pretrained(
    "michailroussos/model-mistral_CP1250", 
    model_type='mistral',
    gpu_layers=0  # Set to 0 for CPU, or appropriate number for GPU
)

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Combine system message and current message
    full_prompt = f"{system_message}\n{message}"
    
    # Generate response
    response = client(
        full_prompt, 
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p
    )
    
    return response

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()