app.py

import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("davnas/Italian_Cousine_2.1")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Format the prompt in the way your working Colab example does
    prompt = f"User: {message}\nAssistant:"
    
    # If you want to include history
    for user_msg, assistant_msg in history:
        prompt = f"User: {user_msg}\nAssistant: {assistant_msg}\n" + prompt
    
    # If you want to include system message
    if system_message:
        prompt = f"{system_message}\n" + prompt

    response = ""
    
    # Use text_generation instead of chat_completion
    for token in client.text_generation(
        prompt,
        max_new_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        response += token
        yield response

demo = gr.ChatInterface(
    respond,
    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)",
        ),
    ],
)

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