app.py

import gradio as gr
import random

from huggingface_hub import InferenceClient
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta",token=userdata.get('HF_TOKEN'))
def respond(message, history):
    messages = [{"role": "system", "content": "You are a friendly chatbot."}]
    if history:
        messages.extend(history)
    messages.append({"role": "user", "content": message})

#make the chat completion API call, sending the messages and other parameters to the model
    response = client.chat_completion(
        messages,
        max_tokens=100,
        temperature=0.2
    )
#extract and return the chatbot's response
    return response['choices'][0]['message']['content'].strip()

#def yorn(message,history):
    #responses=["yes","no"]
    #return random.choice(responses)

#def echo(message,history):
    #print("hello world")
    #return message

#def eightball(message,history):
    #responses=["Your luck has run out","It's your lucky day","You are so insightful"]
    #return random.choice(responses)

chatbot=gr.ChatInterface(respond, type='messages')
chatbot.launch()