Files
leadchat/lib/tasks/ruby_llm.rake
Aakash Bakhle 97dae52841 fix: use committed model registry for RubyLLM (#14067)
RubyLLM bundles a static models.json that doesn't know about models
released after the gem was published. Self-hosted users configuring
newer models hit ModelNotFoundError.

Added a rake task that refreshes the registry from models.dev and saves
to disk. ~~Called during Docker image build so every deploy gets fresh
model data. Falls back silently to the bundled registry if models.dev is
unreachable.~~

Commit the models.json file to code so it is available across
deployments.

---------

Co-authored-by: Sojan Jose <sojan@pepalo.com>
2026-04-16 10:28:38 +05:30

18 lines
724 B
Ruby

# Refresh the RubyLLM model registry from models.dev and configured providers.
# Updates config/llm_models.json so new models are available without a gem upgrade.
#
# Usage:
# bundle exec rake ruby_llm:refresh_models
#
# Run this when new models are released, commit the updated config/llm_models.json.
namespace :ruby_llm do
desc 'Refresh RubyLLM model registry from models.dev'
task refresh_models: :environment do
registry_path = Rails.root.join('config/llm_models.json').to_s
puts 'Refreshing RubyLLM model registry...'
RubyLLM.models.refresh!
RubyLLM.models.save_to_json(registry_path)
puts "RubyLLM model registry updated with #{RubyLLM.models.all.size} models at #{registry_path}"
end
end