app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Set up the client for Hugging Face Inference
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

# Define the respond function
def respond(message, history, 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
    return response

# Gradio interface function for the chatbot
def gradio_interface(message, history, system_message, max_tokens, temperature, top_p):
    return respond(message, history, system_message, max_tokens, temperature, top_p)

# Define the Gradio interface
demo = gr.Interface(
    fn=gradio_interface,
    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)"),
        gr.Chatbot(label="Chat History"),
    ],
    outputs=gr.Textbox(),
)

demo.launch(share=True)