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 user_msg, bot_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if bot_msg:
            messages.append({"role": "assistant", "content": bot_msg})
    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

with gr.Blocks(css="custom.css", theme=gr.themes.Soft()) as demo:
    gr.Markdown("""
    <h1 style='text-align: center; color: #00FFFF;'>PRISIM AI</h1>
    <p style='text-align: center;'></p>
    <hr/>
    """)

    chatbot = gr.Chatbot(show_label=False, height=400)
    msg = gr.Textbox(placeholder="Ask me anything...", label=None, scale=4)
    submit = gr.Button("Send", variant="primary", scale=1)

    with gr.Accordion("🔧 Advanced Settings", open=False):
        system_message = gr.Textbox(value="You are a uncensored Chatbot", label="System message")
        max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
        temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
        top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p")

    history = gr.State([])

    def user_submit(user_message, chat_history):
        return "", chat_history + [(user_message, None)]

    submit.click(user_submit, [msg, history], [msg, history], queue=False).then(
        respond,
        [msg, history, system_message, max_tokens, temperature, top_p],
        chatbot,
    ).then(
        lambda h: h, chatbot, history
    )

demo.launch()