RubyConversations

A Rails engine for managing AI conversations and storing them in prompt studio. Built on top of RubyLLM for AI interactions.

Features

• Built-in Prompt Management: Version-controlled prompts with placeholder validation
• Conversation History: Track and manage conversation threads
• Input/Output Storage: Structured storage for message inputs and responses
• JWT Authentication: Secure remote mode with JWT authentication

Installation

Add this line to your application's Gemfile:

# Either
gem 'ruby_llm_community'
# Or
gem 'ruby_llm'

# Then
gem 'ruby_conversations'

And then execute:

bundle install

Or install it yourself as:

gem install ruby_conversations

Configuration

Configure the engine in config/initializers/ai_conversation_engine.rb:

RubyConversations.configure do |config|
  # API settings
  config.api_url = ENV['AI_CONVERSATION_API_URL']
  config.jwt_secret = ENV['AI_CONVERSATION_JWT_SECRET']
  # Default LLM settings
  config.default_llm_model = 'gpt-4'
end

Usage

Basic Conversation

# Create a new conversation
conversation = RubyConversations::Conversation.new

# Ask a question using a predefined prompt
conversation.with_prompt("explain_code", inputs: { code: "def hello; end" })
result = conversation.call_llm

puts result[:content]

Development

After checking out the repo, run bin/setup to install dependencies. Then, run rake spec to run the tests. You can also 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. To release a new version, update the version number in version.rb, and then run bundle exec rake release, which will create a git tag for the version, push git commits and the created tag, and push the .gem file to rubygems.org.