A delightful Ruby way to work with AI. RubyLLM provides one beautiful, Ruby-like interface to interact with modern AI models. Chat, generate images, create embeddings, and use tools – all with clean, expressive code that feels like Ruby, not like patching together multiple services.

🤺 Battle tested at 💬 Chat with Work

The problem with AI libraries

Every AI provider comes with its own client library, its own response format, its own conventions for streaming, and its own way of handling errors. Want to use multiple providers? Prepare to juggle incompatible APIs and bloated dependencies.

RubyLLM fixes all that. One beautiful API for everything. One consistent format. Minimal dependencies — just Faraday, Zeitwerk, and Marcel. Because working with AI should be a joy, not a chore.

What makes it great

# Just ask questionschat=RubyLLM.chatchat.ask"What's the best way to learn Ruby?"# Analyze images, audio, documents, and text fileschat.ask"What's in this image?",with: "ruby_conf.jpg"chat.ask"Describe this meeting",with: "meeting.wav"chat.ask"Summarize this document",with: "contract.pdf"chat.ask"Explain this code",with: "app.rb"# Multiple files at once - types automatically detectedchat.ask"Analyze these files",with: ["diagram.png","report.pdf","notes.txt"]# Stream responses in real-timechat.ask"Tell me a story about a Ruby programmer"do |chunk|
printchunk.contentend# Generate imagesRubyLLM.paint"a sunset over mountains in watercolor style"# Create vector embeddingsRubyLLM.embed"Ruby is elegant and expressive"# Let AI use your codeclassWeather < RubyLLM::Tooldescription"Gets current weather for a location"param:latitude,desc: "Latitude (e.g., 52.5200)"param:longitude,desc: "Longitude (e.g., 13.4050)"defexecute(latitude:,longitude:)url="https://api.open-meteo.com/v1/forecast?latitude=#{latitude}&longitude=#{longitude}&current=temperature_2m,wind_speed_10m"response=Faraday.get(url)data=JSON.parse(response.body)rescue=>e{error: e.message}endendchat.with_tool(Weather).ask"What's the weather in Berlin? (52.5200, 13.4050)"# Get structured output with JSON schemasclassProductSchema < RubyLLM::Schemastring:name,description: "Product name"number:price,description: "Price in USD"array:features,description: "Key features"dostringdescription: "Feature description"endendresponse=chat.with_schema(ProductSchema).ask"Analyze this product description",with: "product.txt"# response.content => { "name" => "...", "price" => 99.99, "features" => [...] }

Core Capabilities

• 💬 Unified Chat: Converse with models from OpenAI, Anthropic, Gemini, Bedrock, OpenRouter, DeepSeek, Perplexity, Mistral, Ollama, or any OpenAI-compatible API using RubyLLM.chat.
• 👁️ Vision: Analyze images within chats.
• 🔊 Audio: Transcribe and understand audio content.
• 📄 Document Analysis: Extract information from PDFs, text files, CSV, JSON, XML, Markdown, and code files.
• 🖼️ Image Generation: Create images with RubyLLM.paint.
• 📊 Embeddings: Generate text embeddings for vector search with RubyLLM.embed.
• 🔧 Tools (Function Calling): Let AI models call your Ruby code using RubyLLM::Tool.
• 📋 Structured Output: Guarantee responses conform to JSON schemas with RubyLLM::Schema.
• 🚂 Rails Integration: Easily persist chats, messages, and tool calls using acts_as_chat and acts_as_message.
• 🌊 Streaming: Process responses in real-time with idiomatic Ruby blocks.
• ⚡ Async Support: Built-in fiber-based concurrency for high-performance operations.
• 🎯 Smart Configuration: Global and scoped configs with automatic retries and proxy support.
• 📚 Model Registry: Access 500+ models with capability detection and pricing info.

Installation

Add to your Gemfile:

gem'ruby_llm'

Then bundle install.

Configure your API keys (using environment variables is recommended):

# config/initializers/ruby_llm.rb or similarRubyLLM.configuredo |config|
config.openai_api_key=ENV.fetch('OPENAI_API_KEY',nil)# Add keys ONLY for providers you intend to use# config.anthropic_api_key = ENV.fetch('ANTHROPIC_API_KEY', nil)# ... see Configuration guide for all options ...end

See the Installation Guide for full details.

Rails Integration

Add persistence to your chat models effortlessly:

# Generate models and migrations
rails generate ruby_llm:install

# Or add to existing modelsclassChat < ApplicationRecordacts_as_chat# Automatically saves messages & tool callsendclassMessage < ApplicationRecordacts_as_messageendclassToolCall < ApplicationRecordacts_as_tool_callend# Now chats persist automaticallychat=Chat.create!(model_id: "gpt-4.1-nano")chat.ask("What's in this file?",with: "report.pdf")

See the Rails Integration Guide for details.

Learn More

Dive deeper with the official documentation:

• Installation
• Configuration
• Guides:
  • Getting Started
  • Chatting with AI Models
  • Using Tools
  • Streaming Responses
  • Rails Integration
  • Image Generation
  • Embeddings
  • Working with Models
  • Error Handling
  • Available Models

Contributing

We welcome contributions! Please see CONTRIBUTING.md for details on setup, testing, and contribution guidelines.

License

Released under the MIT License.