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("meta-llama/Meta-Llama-3.1-405B")

## None type 
def respond(
    message: str,
    history: list[tuple[str, str]],  # This will not be used
    system_message: str,
    max_tokens: int,
    temperature: float,
    top_p: float,
):
    messages = [{"role": "system", "content": system_message}]
    
    # Append only the latest user message
    messages.append({"role": "user", "content": message})

    response = ""

    try:
        # Generate response from the model
        for message in client.chat_completion(
            messages,
            max_tokens=max_tokens,
            stream=True,
            temperature=temperature,
            top_p=top_p,
        ):
            if message.choices[0].delta.content is not None:
                token = message.choices[0].delta.content
                response += token
            yield response
    except Exception as e:
        yield f"An error occurred: {e}"

"""
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="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()