app.py

import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") #change LLM

def respond(message, history):
    messages = [{"role": "system", "content": "You are a mean chatbot that hates humans."}]
    if history:
        messages.extend(history)
    messages.append({"role": "user", "content": message})
    
    response = ""
    for message in client.chat_completion(
        messages,
        max_tokens=100,
        stream=True,
    ):
        token = message.choices[0].delta.content
        response += token
        yield response

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