app.py

import gradio as gr
from huggingface_hub import InferenceClient

def respond(
    message,
    history: list[dict[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    hf_token: gr.OAuthToken,
):
    """
    Chat response generation using Hugging Face InferenceClient.
    """
    client = InferenceClient(token=hf_token.token, model="algorythmtechnologies/zenith_coder_v1.1")

    messages = [{"role": "system", "content": system_message}]
    messages.extend(history)
    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,
    ):
        choices = message.choices
        token = ""
        if len(choices) and choices[0].delta.content:
            token = choices[0].delta.content

        response += token
        yield response

with gr.Blocks() as demo:
    with gr.Sidebar():
        login = gr.LoginButton()
        login.render()

    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)")

    chatbot = gr.ChatInterface(
        fn=respond,
        type="messages",
        additional_inputs=[system_message, max_tokens, temperature, top_p, login],
    )
    chatbot.render()

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