Project

llm_orchestrator

0.0
The project is in a healthy, maintained state
llm_orchestratoraquaflamingo/llm_orchestratorHomepageDocumentationSource CodeBug TrackerWiki
A simple and flexible framework for managing prompts and LLM interactions with OpenAI and Anthropic Claude
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
 Popularity
Downloads
478
Stars
4
Forks
0
Watchers
1
 Releases
Current version
0.2.0
Total releases
2
First release
2025-01-15
Latest release
2025-01-24
 Pull Requests
Open Pull Requests
0
Closed Pull Requests
0
Merged Pull Requests
2
Pull Request Acceptance Rate
100%
 Development
Primary Language
Ruby
Licenses
MIT
Average date of last 50 commits
2025-01-18
Reverse Dependencies
0

 Dependencies

Development

rspec
~> 3.12
vcr
~> 6.1
webmock
~> 3.18

Runtime

anthropic
~> 0.3.2
ruby-openai
~> 6.0
 Project Readme

LlmOrchestrator

A lightweight Ruby framework for orchestrating LLM operations with OpenAI and Anthropic Claude. This gem provides a simple way to:

  • Manage prompt templates
  • Chain LLM operations
  • Maintain conversation context
  • Switch between OpenAI and Claude providers

Installation

Add this line to your application's Gemfile:

gem 'llm_orchestrator'

And then execute:

$ bundle install

Configuration

Configure your API keys:

LlmOrchestrator.configure do |config|
  config.openai_api_key = ENV['OPENAI_API_KEY']
  config.claude_api_key = ENV['CLAUDE_API_KEY']
  config.default_llm_provider = :claude  # or :openai
end

Basic Usage

Prompt Templates

# Create and use a prompt template
prompt = LlmOrchestrator::Prompt.new("Answer this {type} question: {question}")
formatted = prompt.format(
  type: "math",
  question: "What is 2+2?"
)

LLM Providers

# Using OpenAI
openai = LlmOrchestrator::OpenAI.new
response = openai.generate("What is 2+2?", model: "gpt-3.5-turbo")

# Using Claude
claude = LlmOrchestrator::Anthropic.new
response = claude.generate("What is 2+2?", model: "claude-3-opus-20240229")

Chains with Memory

# Create a chain with memory
memory = LlmOrchestrator::Memory.new
chain = LlmOrchestrator::Chain.new(memory: memory)

# Add processing steps
chain.add_step do |input, memory|
  llm = LlmOrchestrator::Anthropic.new
  llm.generate(input, context: memory.context_string)
end

# Run multiple interactions with context
result1 = chain.run("What is the capital of France?")
result2 = chain.run("What is its population?") # Uses previous context

# Clear memory when needed
chain.clear_memory

Development

After checking out the repo, run:

$ bundle install
$ bundle exec rspec

The tests use VCR to record HTTP interactions. To run the tests with real API calls:

  1. Set up your environment variables:
export OPENAI_API_KEY="your-key-here"
export CLAUDE_API_KEY="your-key-here"
  1. Delete the VCR cassettes (if they exist):
rm -rf spec/fixtures/vcr_cassettes
  1. Run the tests:
bundle exec rspec

Contributing

Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/llm_orchestrator.

License

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