app.py

from huggingface_hub import InferenceClient

import gradio as gr
import random
client=InferenceClient("Qwen/Qwen2.5-72B-Instruct")

def respond(message, history):
    #responses = ["Yes", "No"]
    #return random.choice(responses)

    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=100, temperature=1.3, top_p=0.2)
    # temperature and top_p control randomness
    
    return response["choices"][0]["message"]["content"].strip()

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