app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Public inference (no token required for many free models)
client = InferenceClient()

def chatbot(message, history):
    messages = []

    for user, assistant in history:
        messages.append({"role": "user", "content": user})
        messages.append({"role": "assistant", "content": assistant})

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

    try:
        response = client.chat.completions.create(
            model="microsoft/Phi-3-mini-4k-instruct",
            messages=messages,
            max_tokens=100,
        )
        return response.choices[0].message.content
    except Exception as e:
        return f"Error: {e}"

demo = gr.ChatInterface(
    fn=chatbot,
    title="Simple Hugging Face Chatbot"
)

demo.launch()