import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

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

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

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

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


# Add a title to the UI
title = "Corenet"

# Modify the pre-prompt to be editable but greyed out
pre_prompt = gr.Textbox(
    value="You are a friendly Chatbot, and you are a finetuned version of Llama-3 8B made possible by HX",
    label="Pre-prompt",
    interactive=True,
    placeholder="Type here...",
)

demo = gr.ChatInterface(
    respond,
    title=title,
    additional_inputs=[
        pre_prompt,
        gr.Slider(minimum=256, maximum=8192, value=512, step=1, label="Max Gen tokens"),
        gr.Slider(minimum=0.3, maximum=2.5, value=0.8, step=0.1, label="Creativity"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


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