AWS S3 has been a reliable service over the years and for a long time it was the only option. However, in the past few years, there has been more cloud storage options that have popped up with compatible S3 APIs. These services can sometimes offer better pricing and speeds.

In this episode, we look at running a self hosted Large Language Model (LLM) and consuming it with a Rails application. We will use a background to make API requests to the LLM and then stream the responses in real-time to the browser.

With strong params replacing attr_accessible, a difficulty has arisen with referencing to the structure of your models. With annotate, we can generate the structure of our models in the comments of our models.

ActionController::Renderer allows you to render arbitrary templates without requirement of being in controller actions.

Developing a Ruby on Rails application on Windows can be difficult, but doesn't have to be with Docker. Learn how to use Docker to create isolated containers and get them to talk with the Rails app and passed through to the local computer.