import gradio as gr
from huggingface_hub import InferenceClient

# Initialize the InferenceClient with your model name
client = InferenceClient("Aksh1t/mistral-7b-oig-unsloth-merged")

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

    # Add user and assistant messages from history
    for user_msg, assistant_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if assistant_msg:
            messages.append({"role": "assistant", "content": assistant_msg})

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

    # Call the InferenceClient for chat completion
    response = client.chat_completion(
        messages,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
    )

    # Extract and yield the assistant's response
    for message in response:
        token = message.get("choices")[0].get("delta").get("content")
        yield token

# Create a Gradio interface for the chatbot
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()