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,
):
    """
    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
    """
    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")

    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:
    gr.Markdown("#Pok.Bot")
    gr.Markdown("Задай вопрос ПОК.Боту! (Он отвечает с сарказмом 😎)")

    with gr.Row():
        prompt = gr.Textbox(
            label="Твой вопрос",
            placeholder="Спроси о...",
            lines=2
        )
        temperature = gr.Slider(
            label="Температура",
            minimum=0.1,
            maximum=1.5,
            value=0.9,
            step=0.1
        )

    with gr.Row():
        max_length = gr.Slider(
            label="Макс. длина ответа",
            minimum=10,
            maximum=100,
            value=50,
            step=10
        )
        submit_btn = gr.Button("Спросить ПОК.Бота")

    output = gr.Textbox(
        label="Ответ ПОК.Бота",
        lines=5,
        interactive=False
    )

    # Привязываем кнопку к функции
    submit_btn.click(
        fn=respond ,
        inputs=[prompt, temperature, max_length],
        outputs=output
    )

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

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