app.py

import gradio as gr 
from huggingface_hub import InferenceClient
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
def respond(message,history):

    messages = [{'role': "system", "content":"your are a friend chatbot"}]    
    if history:
        messages.extend(history)
    messages.append({"role": "User", "content": message} )
    response = client.chat_completion( 
        messages, 
        max_tokens=200,
        temperature = 1.2,
        top_p = 0.8
    )
    return response['choices'][0]['message']['content'].strip()

chatbot = gr.ChatInterface(respond, type='message')
chatbot.launch(debug=True)