How to deploy RAG Chatbot

Hi,
I can create a chatbot using LangChain or other tools in a Jupyter notebook, and thus can create a *.py file to define and create the RAG Chatbot. I am having difficulty in figuring out how to deploy the Chatbot, which would have an API interface, and then making it available on my WIX website. Any ideas on how to deploy? For some reason I keep thinking about Docker and Kubernetes, or NVidia, or AWS… What are your thoughts? Thanks.