app.py

import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("microsoft/phi-4")

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 = 100
    )
    return response['choices'][0]['message']['content'].strip()
    
chatbot = gr.ChatInterface(respond, type = "messages", title = "Yes or No")

chatbot.launch()