Generate text with ChatGPT (Generative Pre-trained Transformer)

Add this line to your application's Gemfile:

gem "rubyai"

And then execute:

$ bundle install

Or install with:

$ gem install rubyai

and require with:

require "rubyai"

• Get your API key from https://beta.openai.com/account/api-keys

• If you belong to multiple organizations, you can get your Organization ID from https://beta.openai.com/account/org-settings

For a quick test you can pass your token directly to a new client:

result = RubyAI::Client.new(access_token, messages).call

ChatGPT is a conversational-style text generation model. You can use it to generate a response to a sequence of messages:

api_key = "YOUR API KEY"
messages = "Who is the best chess player in history?"

result = RubyAI::Client.new(api_key, messages, model: "gpt-4").call
puts result.dig("choices", 0, "message", "content")

# => As an AI language model, I do not have personal opinions, but according to historical records, Garry Kasparov is often considered as one of the best chess players in history. Other notable players include Magnus Carlsen, Bobby Fischer, and Jose Capablanca.

You can also pass client variables using the configuration file. Create configruation file like on example:

configuration = RubyAI::Configuration.new("YOUR API KEY", "Who is the best chess player in history?")
client = RubyAI::Client.new(configuration)
result = client.call
puts result.dig("choices", 0, "message", "content")

Also (mostly) if you are using Rails you can use configure method:

RubyAI.configure do |config|
  config.api_key = "YOUR API KEY"
  config.messages = "Who is the best chess player in history?"
  config.model = "gpt-3.5-turbo"
end

After checking out the repo, run bin/setup to install dependencies. You can run bin/console for an interactive prompt that will allow you to experiment.

To install this gem onto your local machine, run bundle exec rake install.

Bug reports and pull requests are welcome on GitHub at https://github.com/alexshapalov/rubyai. This project is intended to be a safe, welcoming space for collaboration, and contributors.

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