app.py

import gradio as gr
import os
from huggingface_hub import InferenceClient

client = InferenceClient(
    model="Qwen/Qwen2.5-7B-Instruct",
    token=os.getenv("hf_token")
)

def respond(message, history):
    messages = [{"role": "system", "content": "You're a friendly chatbot!"}]
    
    if history:
        messages.extend(history)
    
    messages.append({"role": "user", "content": message})
    
    response = client.chat_completion(
        messages,
        max_tokens=100
    )
    return response.choices[0].message.content.strip()

chatbot = gr.ChatInterface(respond,title="Capstone Chatbot")
chatbot.launch()