app.py

import os
import gradio as gr
from huggingface_hub import InferenceClient

HF_TOKEN = os.getenv("HF_TOKEN")
SF = os.getenv("SF")
def respond(
    message,
    history: list[dict[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    quem_faz,
):
    client = InferenceClient(token=HF_TOKEN, model="openai/gpt-oss-20b")

        
    
    if quem_faz != SF:
        yield "Acesso negado para"
        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,
        ):
            if message.choices and message.choices[0].delta.content:
                response += message.choices[0].delta.content
            yield response


chatbot = gr.ChatInterface(
    respond,
    type="messages",
    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"),
        gr.Textbox(value="", label="Quem faz"),
    ],
)

with gr.Blocks() as demo:
    chatbot.render()

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