app.py

import gradio as gr
from huggingface_hub import InferenceClient

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

def respond(message, history):
    
    system_message = "you are a color theory chatbot that helps people evaluate color schemes"
    
    messages = [{"role": "system", "content": system_message}]

    if history:
        message.extend(history)

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

    response = "" 
    for message in client.chat_completion(
        messages, 
        max_tokens=150,
        temperature = .8,
        top_p = .5,
        stream=True
    ):
        token = message.choices[0].delta.content
        response += token
        yield response
    
    

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

chatbot.launch(debug=True)