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 friend chatbot"}]
    
    if history:
        messages.extend(history)

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

    response = client.chat_completion(
        messages,
        max_tokens=100
        temperature=0.2
    )

    return response['choices'][0]['message']['content'].strip()

chatbot = gr.ChatInterface(eightball, type='messages')

chatbot.launch()