app.py

import gradio as gr
from huggingface_hub import InferenceClient
import os

# Ensure the required library is installed
os.system("pip install minijinja gradio huggingface_hub")

# Initialize the client with the desired model
client = InferenceClient("meta-llama/Meta-Llama-3.1-8B")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [system_message]

    for val in history:
        if val[0]:
            messages.append(val[0])
        if val[1]:
            messages.append(val[1])

    messages.append(message)

    response = ""

    try:
        for message in client.chat_completion(
            messages,
            max_tokens=max_tokens,
            stream=True,
            temperature=temperature,
            top_p=top_p,
        ):
            token = message.choices[0].delta.content

            response += token
            yield response
    except Exception as e:
        yield f"Error: {str(e)}"

def autocomplete(prompt, max_tokens, temperature, top_p):
    messages = [prompt]
    response = ""

    try:
        for message in client.chat_completion(
            messages,
            max_tokens=max_tokens,
            stream=True,
            temperature=temperature,
            top_p=top_p,
        ):
            token = message.choices[0].delta.content

            response += token
            yield response
    except Exception as e:
        yield f"Error: {str(e)}"

# Create the Gradio interface
demo = gr.Blocks()

with demo:
    gr.Markdown("# Chat with Meta-Llama")

    with gr.Tab("Chat Interface"):
        chatbot = gr.ChatInterface(
            respond,
            additional_inputs=[
                gr.Textbox(value="", 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)",
                ),
            ],
        )

    with gr.Tab("Notebook Interface"):
        gr.Markdown("## Notebook Interface with Autocomplete")
        prompt = gr.Textbox(label="Enter your text")
        output = gr.Textbox(label="Autocompleted Text", interactive=False)
        max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
        temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
        top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")

        autocomplete_button = gr.Button("Autocomplete")

        autocomplete_button.click(
            autocomplete,
            inputs=[prompt, max_tokens, temperature, top_p],
            outputs=output
        )

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