app.py

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

# Create a custom function for the theme and interface
def create_interface():
    with gr.Blocks(theme='HaleyCH/HaleyCH_Theme') as demo:
        with gr.Row():
            with gr.Column():
                # Inputs for system message, max tokens, temperature, top_p
                system_message = gr.Textbox(value="You are a friendly 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 (nucleus sampling)")
                
                # Chat Interface
                chat = gr.ChatInterface(
                    fn=respond,
                    inputs=[system_message, max_tokens, temperature, top_p],
                    theme='HaleyCH/HaleyCH_Theme'
                )
                
    return demo

# Launch the Gradio app
if __name__ == "__main__":
    interface = create_interface()
    interface.launch()