RubyLLM 1.8.1: Efficient Chat Streaming 🚀💬

Small release bringing production-ready streaming for Rails chat UIs and minor fixes.

💬 Production-Ready Chat Streaming

Improved the chat UI generator with efficient chunk streaming that reduces bandwidth usage:

• Bandwidth optimized: New broadcast_append_chunk method appends individual chunks without re-transmitting entire messages
• Single subscription: Maintains one Turbo Stream subscription at chat level (not per message)
• Reduced overhead: Jobs now append chunks instead of updating entire messages, reducing database writes

🔧 Improvements & Fixes

• Cleaner injection: Refined message model class injection for chat UI generator
• GPT-5 capabilities: Fixed missing capability declarations for parsera compatibility
• Funding support: Added funding URI to gemspec metadata
• Documentation updates: Enhanced README and moderation guides
• Model registry: Latest model updates across all providers
• Dependency updates: Updated Appraisal gemfiles

Installation

gem 'ruby_llm', '1.8.1'

Upgrading from 1.8.0

bundle update ruby_llm

All changes are backward compatible. To benefit from the streaming improvements, regenerate your chat UI with rails generate ruby_llm:chat_ui.

Merged PRs

• Update gpt-5 capabilities by @mnort9 in #345

New Contributors

• @mnort9 made their first contribution in #345

Full Changelog: 1.8.0...1.8.1