app.py

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

# Response function for the chatbot
def respond(
    message: str,
    history: List[Dict[str, str]],
    system_message: str,
    max_tokens: int,
    temperature: float,
    top_p: float,
    hf_token: gr.OAuthToken,
):
    """
    Sends a user input to the summarization model using text-to-text interface.
    """
    client = InferenceClient(
        token=hf_token.token,
        model="Bocklitz-Lab/lit2vec-tldr-bart-model"
    )

    # You can prepend the system message if needed
    input_text = f"{system_message}\n\n{message}"

    response = client.text_to_text(
        input=input_text,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p
    )

    yield response


# Define the Gradio interface
chatbot = gr.ChatInterface(
    fn=respond,
    type="messages",
    additional_inputs=[
        gr.Textbox(
            value="You are a friendly chatbot.",
            label="System message",
            lines=1
        ),
        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)"
        ),
    ],
)

# Set up the full Gradio Blocks layout with login
with gr.Blocks() as demo:
    with gr.Row():
        with gr.Column(scale=1):
            gr.LoginButton()
    chatbot.render()

# Run the app
if __name__ == "__main__":
    demo.launch()