RubyLLM 1.3.0.rc1: Isolation, Configuration & Model Expansion 🚀

We're excited to introduce RubyLLM 1.3.0.rc1 with isolated configuration contexts, expanded provider support, and major improvements to attachments and Rails integration.

🔄 Isolation with Contexts

Introducing scoped configuration with Contexts - perfect for multi-tenant applications, environment targeting, and testing:

# Create an isolated configuration context
context = RubyLLM.context do |config|
  config.openai_api_key = ENV['TENANT_A_OPENAI_KEY']
  config.anthropic_api_key = ENV['TENANT_A_ANTHROPIC_KEY']
  config.request_timeout = 180 # Longer timeout just for this context
end

# Use the isolated context for specific operations
embedding = context.embed("Text for tenant A")
response = context.chat.ask("Question from tenant A")

# Global configuration remains untouched
RubyLLM.embed("This uses the default configuration")

📎 Smart Attachments with Auto Type Detection

The new attachment system works everywhere - not just Rails! RubyLLM automatically detects file types and handles the appropriate API formatting:

# Send a single file - auto detects if it's an image, PDF, or audio
chat.ask("What's in this file?", with: "diagram.png")

# Send multiple files - all types are automatically detected
chat.ask("Analyze these files", with: [
  "report.pdf",
  "chart.jpg", 
  "recording.mp3"
])

# Still works with manual categorization if you prefer
chat.ask("What's in this?", with: {
  image: "diagram.png",
  audio: "recording.mp3"
})

🚂 Enhanced Rails Integration

The Rails integration now supports attachments with ActiveStorage, making it easy to work with uploaded files:

# After setting up ActiveStorage
class Message < ApplicationRecord
  acts_as_message
  has_many_attached :attachments # Add this for attachment support
end

# Works seamlessly with Rails uploads
chat_record.ask("Analyze this", with: params[:uploaded_file])

# Works with existing ActiveStorage attachments
chat_record.ask("What's in my document?", with: user.profile_document)

# Send multiple files from a form
chat_record.ask("Review these documents", with: params[:files])

The persistence flow has also been enhanced with better error handling and support for validation-focused approaches.

💻 Ollama Integration

Local LLMs are now first-class citizens with Ollama support:

RubyLLM.configure do |config|
  config.ollama_api_base = 'http://localhost:11434/api'
end

# Use local models
chat = RubyLLM.chat(model: 'mistral')

🔀 OpenRouter Support

Access hundreds of models through a single API:

RubyLLM.configure do |config|
  config.openrouter_api_key = ENV['OPENROUTER_API_KEY']
end

# Access models from various providers through OpenRouter
chat = RubyLLM.chat(model: 'anthropic/claude-3.5-sonnet', provider: 'openrouter')

🏢 OpenAI Organization Support

Support for OpenAI organization and project IDs:

RubyLLM.configure do |config|
  config.openai_api_key = ENV['OPENAI_API_KEY']
  config.openai_organization_id = ENV['OPENAI_ORG_ID']
  config.openai_project_id = ENV['OPENAI_PROJECT_ID']
end

🌐 Better Model Information via Parsera API

We now use the Parsera API for getting accurate, up-to-date model information when you run RubyLLM.models.refresh!. This provides scraped data directly from provider websites, ensuring the most current model details, pricing, and capabilities.

Check out the model browser built by Parsera for more information.

🔢 Custom Embedding Dimensions

Control the dimensionality of your embeddings:

# Generate compact embeddings for specific use cases
embedding = RubyLLM.embed(
  "Ruby is a programmer's best friend",
  model: "text-embedding-3-small",
  dimensions: 512
)

🪵 Configurable Logging

Control where and how RubyLLM logs:

RubyLLM.configure do |config|
  config.log_file = '/path/to/ruby_llm.log'
  config.log_level = :debug
end

🔧 Core Improvements

Completely refactored Content implementation for simplified provider integration
Fixed duplicate messages when calling chat.to_llm multiple times
Enhanced media handling across providers (including PDF support)
Fixed embedding when using default model
Configuration.inspect now properly filters sensitive data
Rails-style foreign keys for custom class names in ActiveRecord integration
Fixed empty message cleanup on API failures
Enhanced test coverage for streaming vs non-streaming consistency

This is a release candidate. Please test thoroughly, especially the new context and provider features!

gem 'ruby_llm', '1.3.0.rc1'

PRs Merged

Support Embedding Dimensions by @papgmez in #73
Updated acts_as_* helpers to use canonical 'rails-style' foreign keys by @timaro in #151
Add support for logging to file via configuration by @rhys117 in #148
Use foreign_key instead of to_s for acts_as methods by @bborn in #157
Fix inflector by @bborn in #159
Handle OpenAI organization and project IDs by @xymbol in #162
Don't call blob on a blob by @bborn in #164

New Contributors

@papgmez made their first contribution in #73
@timaro made their first contribution in #151
@rhys117 made their first contribution in #148
@bborn made their first contribution in #157
@xymbol made their first contribution in #162

Full Changelog: 1.2.0...1.3.0rc1

crmne/ruby_llm 1.3.0rc1 on GitHub