app.py

import gradio as gr
from huggingface_hub import InferenceClient

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

def respond(
    message: str,
    history: list[tuple[str, str]],
    system_message: str,
    max_tokens: int,
    temperature: float,
    top_p: float,
) -> str:
    """
    Generate a response based on the user's message and chat history.

    Args:
        message (str): The user's message.
        history (list[tuple[str, str]]): The chat history.
        system_message (str): The system message.
        max_tokens (int): The maximum number of tokens in the response.
        temperature (float): The temperature for sampling.
        top_p (float): The top-p (nucleus) sampling value.

    Returns:
        str: The generated response.
    """
    messages = [{"role": "system", "content": system_message}]

    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})

    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

# Create the Gradio ChatInterface
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)",
        ),
    ],
    theme="default",  # Apply the default theme
    css=".gradio-container {background-color: #E0F7FA;}"  # Set a light blue background
)

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