import gradio as gr
from huggingface_hub import InferenceClient


def respond(
    message,
    history,  
    system_message,
    max_tokens,
    temperature,
    top_p,
    hf_token: gr.OAuthToken,
):
    """
    Função de resposta usando Hugging Face Inference API.
    """
    # Use o token diretamente se estiver testando localmente
    client = InferenceClient(token=hf_token.token, model="apple/FastVLM-7B")


    messages = [{"role": "system", "content": system_message}]


    if history:
        for h in history:
   
            if isinstance(h, tuple) and len(h) == 2:
                user_msg, bot_msg = h
                messages.append({"role": "user", "content": user_msg})
                messages.append({"role": "assistant", "content": bot_msg})

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

    response = ""

    try:
        for message_chunk in client.chat_completion(
            messages,
            max_tokens=max_tokens,
            stream=True,
            temperature=temperature,
            top_p=top_p,
        ):
            if hasattr(message_chunk, "choices") and message_chunk.choices:
                delta = message_chunk.choices[0].delta
                if delta and hasattr(delta, "content"):
                    response += delta.content
                    yield response
    except Exception as e:
        yield f"Erro durante a execução: {str(e)}"


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)"),
    ],
)

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

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