import gradio as gr
from huggingface_hub import InferenceClient

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

def respond(message, history, 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() as demo:
    chatbot = gr.Chatbot(label="Chat", show_copy_button=True, type="messages")
    system_msg = gr.Textbox(value="You are a helpful assistant.", label="System Message")
    max_tokens = gr.Slider(1, 2048, value=512, label="Max Tokens")
    temperature = gr.Slider(0.1, 4.0, value=0.7, label="Temperature")
    top_p = gr.Slider(0.1, 1.0, value=0.95, label="Top-p")
    msg_input = gr.Textbox(label="Message", placeholder="Ask me anything...")

    def chat_fn(msg, history, system_msg, max_tokens, temperature, top_p):
        return respond(msg, history, system_msg, max_tokens, temperature, top_p)

    msg_input.submit(chat_fn, [msg_input, chatbot, system_msg, max_tokens, temperature, top_p], chatbot)

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