app.py

import gradio as gr
from huggingface_hub import InferenceClient

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

# Background effect from CodePen
background_html = """
<p class="codepen" data-height="300" data-theme-id="dark" data-default-tab="html,result" data-slug-hash="LYwLqVv" data-pen-title="WebGL Eye Pattern" data-user="bxck75" style="height: 300px; box-sizing: border-box; display: flex; align-items: center; justify-content: center; border: 2px solid; margin: 1em 0; padding: 1em;">
  <span>See the Pen <a href="https://codepen.io/bxck75/pen/LYwLqVv">
  WebGL Eye Pattern</a> by boudewijn (<a href="https://codepen.io/bxck75">@bxck75</a>)
  on <a href="https://codepen.io">CodePen</a>.</span>
</p>
<script async src="https://cpwebassets.codepen.io/assets/embed/ei.js"></script>
"""

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


with gr.Blocks() as demo:
    gr.HTML(background_html)  # Insert the background effect
    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)",
            ),
        ],
    )

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