app.py

import gradio as gr
from huggingface_hub import InferenceClient
from typing import List, Dict

def respond(
    message: str,
    history: List[Dict[str, str]],
    system_message: str,
    max_tokens: int,
    temperature: float,
    top_p: float,
    hf_token: gr.OAuthToken,
):
    """
    Para mais informações sobre o Inference API:
    https://huggingface.co/docs/huggingface_hub/guides/inference
    """
    # Inicializa cliente de inferência
    client = InferenceClient(
        token=hf_token.token,
        model="apple/FastVLM-7B"
    )

    # Prepara mensagens
    messages = [{"role": "system", "content": system_message}]
    messages.extend(history)
    messages.append({"role": "user", "content": message})

    response = ""

    # Stream de tokens
    for chunk in client.chat_completion(
        messages=messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        choices = chunk.choices
        token = ""
        if len(choices) and choices[0].delta and choices[0].delta.content:
            token = choices[0].delta.content

        response += token
        yield response


# Interface do chatbot
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 (nucleus sampling)"),
    ],
)

# Monta layout com Sidebar
with gr.Blocks() as demo:
    with gr.Sidebar():
        gr.LoginButton()
    chatbot.render()

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