app.py

import os
import gradio as gr
from huggingface_hub import InferenceClient

# Lấy token từ biến môi trường (đã tạo trong Secrets với tên HF_TOKEN)
HF_TOKEN = os.getenv("HF_TOKEN")

# Khởi tạo client với model GPT-OSS-120B
client = InferenceClient(
    model="openai/gpt-oss-120b",
    token=HF_TOKEN,
)

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for user_msg, bot_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if bot_msg:
            messages.append({"role": "assistant", "content": bot_msg})

    messages.append({"role": "user", "content": message})

    response = ""

    for response_chunk in client.chat_completion(
        messages=messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        delta = response_chunk.choices[0].delta.content
        if delta:
            response += delta
            yield response

# UI với Gradio
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a helpful assistant.", 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"),
    ],
    title="Chat with GPT-OSS-120B",
    description="Inference via Hugging Face Hub – powered by openai/gpt-oss-120b"
)

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