This guide will walk you through adding a ChatGPT-like messaging stream to your Ruby on Rails 7 app using ruby-openai, Rails 7, Hotwire, Turbostream, Sidekiq and Tailwind. All code included below!
- Follow me on Twitter for more Ruby AI at https://twitter.com/alexrudall
- Released under the MIT License - use as you wish :)
First, add the ruby-openai gem! Needs to be at least version 4. Add Sidekiq too.
One way to do this is to use bundler to scaffold our gem:
bundler gem my_gem
I prefer to put tasks meant to manage the gem itself in lib/tasks
, and tasks the gem is meant to provide to gem users in lib/my_gem/tasks
.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Background: | |
# The following code works but I have intentionally introduced issues to make it inefficient. | |
# UserEvents are created for every interaction a user has in the system. It stores what employer, partner and | |
# controller they were on. When there were 10 users and only a little bit of traffic, this would run quickly. | |
# But now with 10,000 users and months of traffic - (millions of user events), this code would be very inefficient. | |
# Instructions: | |
# 1. Please make this code more efficient through refactoring so that it can run at a greater scale, | |
# along with adding some comments to improve the readability. | |
# 2. Please explain what the variable 'distinct_groups' will contain by the end of the execution and what |
OlderNewer