app.py

from huggingface_hub import InferenceClient
import gradio as gr

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

def echo(message, history):
    return message

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

chatbot.launch()