app.py

import gradio as gr
import random
import os 

from huggingface_hub import InferenceClient

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

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")

chatbot.launch()