app.py

import gradio as gr
from huggingface_hub import InferenceClient

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("mlx-community/Hermes-3-Llama-3.1-70B-8bit")  # Garantir que o modelo seja compatível com `text-generation`


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

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

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

    # Alterar a requisição para utilizar um modelo de `text-generation`
    response = client.text_generation(
        inputs=messages[-1]['content'],
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p
    )

    # Assumindo que o modelo de texto retorna a resposta como uma string diretamente
    response_text = response['generated_text']  # Adapte de acordo com a estrutura da resposta

    return response_text


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="Você se chama Esquizofrenia, você é irônico e tímido", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=256, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.6, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


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