Project

rbs_goose

0.0
The project is in a healthy, maintained state
RBS type inferrer with LLM
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
 Dependencies

Runtime

>= 0.8.2, < 1.0.0
>= 6.1.0, < 7.0.0
 Project Readme

RuboCop Logo

en-US README ja-JP README

CI Gem Version Test Coverage Maintainability

RBS Goose is a tool that uses large language models such as ChatGPT to infer RBS signatures for Ruby code.

Caution

Currently in the process of technical verification, there is a possibility that appropriate types may not be output at all or may not be output at all. Also, when making inferences, it may be expensive to use the ChatGPT API, depending on the size of the code.

Installation

$ gem install rbs_goose
# Install the corresponding gem according to the LangChain LLM you want to use
$ gem install ruby-openai

If you are using bundler, add the following to your Gemfile instead.

gem 'rbs_goose'
# Install the corresponding gem according to the LangChain LLM you want to use
gem 'ruby-openai'

Usage

Currently, the command-line tool is not fully developed, so please call RbsGoose.run directly from a file like Rakefile.

To use the OpenAI API, do the following:

require 'rbs_goose'
require 'openai'

desc 'refine RBS files in sig directory'
task :refine do
  RbsGoose.configure do |c|
    c.use_open_ai(ENV.fetch('OPENAI_ACCESS_TOKEN'))
  end
  RbsGoose.run
end

When you run this task, it will reference the Ruby code in the lib directory and the RBS signatures in the sig directory, and overwrite the inferred signatures.

If you want to change the target directory, specify the arguments for RbsGoose.run as follows:

RbsGoose.run(code_dir: 'app', sig_dir: 'types', base_path: Rails.root)

The call to the large language model uses Langchain.rb.

If you want to use another large language model, set llm directly as follows:

RbsGoose.configure do |c|
  c.llm = Langchain::LLM::GooglePalm.new(api_key: ENV["GOOGLE_PALM_API_KEY"])
end

Development

After checking out the repository, run bin/setup to install dependencies. Then, run rake spec to run the tests. You can also run bin/console for an interactive prompt.

To install this gem onto your local machine, run bundle exec rake install. To release a new version, update the version number in version.rb, and then run bundle exec rake release. This will create a git tag for the version, push git commits and tags, and push the .gem file to rubygems.org.

Contributing

Bug reports and pull requests are welcome on GitHub at https://github.com/kokuyouwind/rbs_goose. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the code of conduct.

License

This gem is available as open source under the terms of the MIT License.

Code of Conduct

Everyone interacting in the RbsGoose project's codebases, issue trackers, chat rooms, and mailing lists is expected to follow the code of conduct.