app.py

from huggingface_hub import InferenceClient 

import gradio as gr
import random


# Making requests to the model to generate responses:
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=1.7, top_p=.3)
    # Temp and top_p control randomness
    
    return response['choices'][0]['message']['content'].strip()


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