app.py

import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")

def respond(message, history):
    messages = [{"role": "system", "content": "You are friend chatbot"}]

    if history:
        messages.extend(history)

    messages.append({"role": "user", "content": message})

    response = client.chat_completion(
        messages, 
        max_tokens = 100, 
        temperature = 0.2
    )
    return response['choices'][0]['message']['content'].strip()

chatbot = gr.ChatInterface(respond, type = 'messages')
chatbot.launch()