app.py

import gradio as gr
from huggingface_hub import InferenceClient

def respond(
    message,
    history: list[list[str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    hf_token: gr.OAuthToken,
):
    client = InferenceClient(
        token=hf_token.token,
        model="DeepHat/DeepHat-V1-7B"
    )

    # Construção correta do histórico
    messages = [{"role": "system", "content": system_message}]

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

    # Adiciona a nova mensagem do usuário
    messages.append({"role": "user", "content": message})

    response = ""

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

        response += token
        yield response