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":messages})

    response = client.chat_completion(
        mesages,
        max_token=100)
    return response ['choices'][0]['message']['content'].strip()




chatbot = gr.ChatInterface(repsond, type = "messages")

chatbot.launch()