app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Using Zephyr-7B Beta
MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
client = InferenceClient(MODEL_NAME)


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 = ""

    try:
        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 if message.choices[0].delta else ""
            response += token
            yield response
    except Exception as e:
        yield f"Error: {str(e)}"


# Gradio UI with adjustable settings
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 Tokens"),
        gr.Slider(minimum=0.1, maximum=2.0, 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"),
    ],
)

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