ruby_llm 1.0.1 → 1.1.0rc1

data/.rubocop.yml

@@ -1,10 +0,0 @@
-plugins:
-  - rubocop-rake
-  - rubocop-rspec
-
-AllCops:
-  NewCops: enable
-  TargetRubyVersion: 3.1
-  Exclude:
-    - docs/**/*
-    - vendor/**/*

data/.yardopts

@@ -1,12 +0,0 @@
---markup markdown
---markup-provider redcarpet
---title "RubyLLM API Documentation"
---protected
---private
---embed-mixins
---output-dir doc/yard
---readme README.md
-lib/**/*.rb
--
-LICENSE
-

data/CONTRIBUTING.md

@@ -1,207 +0,0 @@
-# Contributing to RubyLLM
-
-First off, thank you for considering contributing to RubyLLM! It's people like you that make RubyLLM such a great tool.
-
-## Development Setup
-
-Here's how to get started:
-
-```bash
-# Clone the repository
-gh repo clone crmne/ruby_llm
-cd ruby_llm
-
-# Install dependencies
-bundle install
-
-# Set up git hooks
-overcommit --install
-
-# Run the tests (uses VCR cassettes)
-bundle exec rspec
-```
-
-## Development Workflow
-
-We recommend using GitHub CLI to simplify the workflow:
-
-```bash
-# Create a new branch for your feature
-gh repo fork crmne/ruby_llm --clone
-cd ruby_llm
-
-# Find or make an issue for the feature on GitHub and then:
-gh issue develop 123 --checkout  # Substitute 123 with the issue number
-
-# Make your changes and test them
-# ...
-
-# Commit your changes
-git commit
-
-# Create a PR
-gh pr create --web
-```
-
-## Model Naming Convention & Provider Strategy
-
-When adding new providers to RubyLLM, please follow these guidelines:
-
-### Normalized Model IDs
-
-We use a consistent approach separating **what** (model) from **where** (provider):
-
-```ruby
-# Default way (from the native provider)
-chat = RubyLLM.chat(model: "claude-3-5-sonnet")
-
-# Same model via different provider
-chat = RubyLLM.chat(model: "claude-3-5-sonnet", provider: :bedrock)
-```
-
-### Implementing a Provider
-
-If you're adding a new provider:
-
-1. **Use normalized model IDs** - Don't include provider prefixes in the model ID itself
-2. **Add provider mapping** - Map the normalized IDs to your provider's specific format internally
-3. **Preserve capabilities** - Ensure models accessed through your provider report the same capabilities as their native counterparts
-4. **Update models.json** - Include your provider's models in models.json
-5. **Update aliases.json** - Add entries to aliases.json for models accessible through your provider
-6. **Implement refresh mechanism** - Ensure your provider supports the `list_models` method for refreshing
-
-### Model Aliases
-
-For providers that use complex model identifiers (like Bedrock's `anthropic.claude-3-5-sonnet-20241022-v2:0:200k`), add mappings to the global aliases.json file:
-
-```json
-{
-  "claude-3-5-sonnet": {
-    "anthropic": "claude-3-5-sonnet-20241022",
-    "bedrock": "anthropic.claude-3-5-sonnet-20241022-v2:0:200k",
-    "openrouter": "anthropic/claude-3.5-sonnet"
-  },
-  "gpt-4o": {
-    "openai": "gpt-4o-2024-05-13",
-    "bedrock": "anthropic.gpt-4o-2024-05-13",
-    "openrouter": "openai/gpt-4o"
-  }
-}
-```
-
-If a model can't be found with the provided ID and provider, a `ModelNotFoundError` will be raised with an informative message. Your implementation should make this error helpful by suggesting available alternatives.
-
-When the same model has multiple versions and context windows e.g.
-
-```
-anthropic.claude-3-5-sonnet-20240620-v1:0
-anthropic.claude-3-5-sonnet-20240620-v1:0:18k
-anthropic.claude-3-5-sonnet-20240620-v1:0:200k
-anthropic.claude-3-5-sonnet-20240620-v1:0:51k
-anthropic.claude-3-5-sonnet-20241022-v2:0
-anthropic.claude-3-5-sonnet-20241022-v2:0:18k
-anthropic.claude-3-5-sonnet-20241022-v2:0:200k
-anthropic.claude-3-5-sonnet-20241022-v2:0:51k
-```
-
-We default all aliases to the biggest context window, and the main alias (without date) to the latest version:
-
-```json
-  "claude-3-5-sonnet": {
-    "anthropic": "claude-3-5-sonnet-20241022",
-    "bedrock": "anthropic.claude-3-5-sonnet-20241022-v2:0:200k",
-    "openrouter": "anthropic/claude-3.5-sonnet"
-  },
-  "claude-3-5-sonnet-20241022": {
-    "anthropic": "claude-3-5-sonnet-20241022",
-    "bedrock": "anthropic.claude-3-5-sonnet-20241022-v2:0:200k",
-    "openrouter": "anthropic/claude-3.5-sonnet"
-  },
-  "claude-3-5-sonnet-20240620": {
-    "anthropic": "claude-3-5-sonnet-20240620",
-    "bedrock": "anthropic.claude-3-5-sonnet-20240620-v1:0:200k"
-  },
-```
-
-## Running Tests
-
-Tests automatically use VCR to record and replay HTTP interactions, so you don't need real API keys for testing:
-
-```bash
-# Run all tests (using existing VCR cassettes)
-bundle exec rspec
-
-# Run a specific test file
-bundle exec rspec spec/ruby_llm/chat_spec.rb
-```
-
-### Recording VCR Cassettes
-
-When you make changes that affect API interactions, you can record new VCR cassettes.
-
-If you have keys for all providers:
-
-```bash
-# Re-record all cassettes
-bundle exec rake vcr:record[all]
-```
-
-If you only have keys for specific providers (e.g., just OpenAI):
-
-```bash
-# Set the API keys you have
-export OPENAI_API_KEY=your_openai_key
-
-# Find and remove only cassettes for OpenAI, then run tests to re-record them
-bundle exec rake vcr:record[openai]
-
-# You can also specify multiple providers
-bundle exec rake vcr:record[openai,anthropic]
-```
-
-Important: After recording new cassettes, please **manually check** them for any sensitive information that might have been missed by the automatic filters.
-
-## Adding New Tests
-
-Tests automatically create VCR cassettes based on their descriptions, so make sure your test descriptions are unique and descriptive.
-
-## Coding Style
-
-We follow the [Standard Ruby](https://github.com/testdouble/standard) style. Please ensure your contributions adhere to this style.
-
-```bash
-# Check your code style
-bundle exec rubocop
-
-# Auto-fix style issues where possible
-bundle exec rubocop -A
-```
-
-## Documentation
-
-When adding new features, please include documentation updates:
-
-- Update relevant guides in the `docs/guides/` directory
-- Add inline documentation using YARD comments
-- Keep the README clean and focused on helping new users get started quickly
-
-## Philosophy
-
-RubyLLM follows certain design philosophies and conventions. Please refer to our [Philosophy Guide](https://rubyllm.com/philosophy) to ensure your contributions align with the project's vision.
-
-## Discussions and Issues
-
-- For questions and discussions, please use [GitHub Discussions](https://github.com/crmne/ruby_llm/discussions)
-- For bugs and feature requests, please use [GitHub Issues](https://github.com/crmne/ruby_llm/issues)
-
-## Release Process
-
-Gem versioning follows [Semantic Versioning](https://semver.org/):
-
-1. MAJOR version for incompatible API changes
-2. MINOR version for backwards-compatible functionality
-3. PATCH version for backwards-compatible bug fixes
-
-Releases are handled by the maintainers through the CI/CD pipeline.
-
-Thanks for helping make RubyLLM better!

data/Gemfile

@@ -1,33 +0,0 @@
-# frozen_string_literal: true
-
-source 'https://rubygems.org'
-
-gemspec
-
-group :development do
-  # Rails integration dependencies
-  gem 'activerecord', '>= 6.0', '< 9.0'
-  gem 'activesupport', '>= 6.0', '< 9.0'
-
-  # Development dependencies
-  gem 'bundler', '>= 2.0'
-  gem 'codecov'
-  gem 'dotenv'
-  gem 'irb'
-  gem 'nokogiri'
-  gem 'overcommit', '>= 0.66'
-  gem 'pry', '>= 0.14'
-  gem 'rake', '>= 13.0'
-  gem 'rdoc'
-  gem 'reline'
-  gem 'rspec', '~> 3.12'
-  gem 'rubocop', '>= 1.0'
-  gem 'rubocop-rake', '>= 0.6'
-  gem 'rubocop-rspec'
-  gem 'simplecov', '>= 0.21'
-  gem 'simplecov-cobertura'
-  gem 'sqlite3'
-  gem 'vcr'
-  gem 'webmock', '~> 3.18'
-  gem 'yard', '>= 0.9'
-end

data/Rakefile

@@ -1,9 +0,0 @@
-# frozen_string_literal: true
-
-require 'bundler/setup'
-require 'bundler/gem_tasks'
-require 'rake/clean'
-
-Dir.glob('lib/tasks/**/*.rake').each { |r| load r }
-
-task default: %w[build]

data/bin/console

@@ -1,17 +0,0 @@
-#!/usr/bin/env ruby
-# frozen_string_literal: true
-
-require 'bundler/setup'
-require 'ruby_llm'
-require 'dotenv/load'
-
-require 'irb'
-
-RubyLLM.configure do |config|
-  config.openai_api_key = ENV.fetch('OPENAI_API_KEY', nil)
-  config.anthropic_api_key = ENV.fetch('ANTHROPIC_API_KEY', nil)
-  config.gemini_api_key = ENV.fetch('GEMINI_API_KEY', nil)
-  config.deepseek_api_key = ENV.fetch('DEEPSEEK_API_KEY', nil)
-end
-
-IRB.start(__FILE__)

data/bin/setup

@@ -1,6 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-IFS=$'\n\t'
-set -vx
-
-bundle install

data/ruby_llm.gemspec

@@ -1,44 +0,0 @@
-# frozen_string_literal: true
-
-require_relative 'lib/ruby_llm/version'
-
-Gem::Specification.new do |spec|
-  spec.name          = 'ruby_llm'
-  spec.version       = RubyLLM::VERSION
-  spec.authors       = ['Carmine Paolino']
-  spec.email         = ['carmine@paolino.me']
-
-  spec.summary       = 'Beautiful Ruby interface to modern AI'
-  spec.description   = 'A delightful Ruby way to work with AI. Chat in text, analyze and generate images, understand ' \
-                       'audio, and use tools through a unified interface to OpenAI, Anthropic, Google, and DeepSeek. ' \
-                       'Built for developer happiness with automatic token counting, proper streaming, and Rails ' \
-                       'integration. No wrapping your head around multiple APIs - just clean Ruby code that works.'
-  spec.homepage      = 'https://rubyllm.com'
-  spec.license       = 'MIT'
-  spec.required_ruby_version = Gem::Requirement.new('>= 3.1.0')
-
-  spec.metadata['homepage_uri'] = spec.homepage
-  spec.metadata['source_code_uri'] = 'https://github.com/crmne/ruby_llm'
-  spec.metadata['changelog_uri'] = "#{spec.metadata['source_code_uri']}/commits/main"
-  spec.metadata['documentation_uri'] = spec.homepage
-  spec.metadata['bug_tracker_uri'] = "#{spec.metadata['source_code_uri']}/issues"
-
-  spec.metadata['rubygems_mfa_required'] = 'true'
-
-  # Specify which files should be added to the gem when it is released.
-  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
-  spec.files = Dir.chdir(File.expand_path(__dir__)) do
-    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features|docs)/}) }
-  end
-  spec.bindir        = 'exe'
-  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
-  spec.require_paths = ['lib']
-
-  # Runtime dependencies
-  spec.add_dependency 'base64'
-  spec.add_dependency 'event_stream_parser', '~> 1'
-  spec.add_dependency 'faraday', '~> 2'
-  spec.add_dependency 'faraday-multipart', '~> 1'
-  spec.add_dependency 'faraday-retry', '~> 2'
-  spec.add_dependency 'zeitwerk', '~> 2'
-end