app.py

import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")

def respond (message, history):
    messages = [{"role": "system", "content": "You are a friendly chatbot."}]
    if history:
        messages.extend(history)
        
    messages.append({"role": "user", "content": message})

    response = client.chat_completion(
        messages,
        max_tokens=120,
        temperature=1.2
    )

    return response['choices'][0]['message']['content'].strip()

chatbot = gr.ChatInterface(respond)

chatbot.launch()