ruby_llm 1.6.1 → 1.6.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e1fd977cc46769d8d235fe13a31e030a133618a335c8cd012ab8de2b7d439297
-  data.tar.gz: ce8d22464541ac19246e6018fde5c7b414ba0022bc5995f8900052f3d0ac5b42
+  metadata.gz: 5e454eaf845f9c4b9a03f6e5a12567e59d5621d1ff6db3e866be50e836de65c2
+  data.tar.gz: 8e49e339287432cc9feee74ee9b0b49abffcc282bb6387fc9d2cdd6889f9c39c
 SHA512:
-  metadata.gz: aec038a65867c5fa13b93a11aa5356183b8f105bb7f48792e6300a9259a809206bc07da0b54c63a0a0de726cc3698ec2cd79c511be43e6fd8f47273adecc47a9
-  data.tar.gz: 5386da468b9f413d7fbf27192a693c2427a1e88a9082a7375f5641f01854a7cbd2235c1c8108ea870c97c97ea79c712bdd5d33e2ac09a22e25a74f9510a1599f
+  metadata.gz: 06e7fc0118d88631e1c41a9b4b0738b6f55b965ee4569643759489e81191317dfe4cba5e55dcf89d386ef68379b013a4a0a6c9b9b71f3dd3115f7f46186545f4
+  data.tar.gz: 047a575afaa0cf37934e395bd49460edab5a07e29a8c7f085139c331c94d44bdc226c9c2b8781183d05a7ce6b81b08af943b86c9c3ee76f19188a491585d971b

data/README.md

@@ -1,99 +1,114 @@
+<div align="center">
+
 <picture>
   <source media="(prefers-color-scheme: dark)" srcset="/docs/assets/images/logotype_dark.svg">
   <img src="/docs/assets/images/logotype.svg" alt="RubyLLM" height="120" width="250">
 </picture>
 
-**One *beautiful* Ruby API for GPT, Claude, Gemini, and more.** Easily build chatbots, AI agents, RAG applications, and content generators. Features chat (text, images, audio, PDFs), image generation, embeddings, tools (function calling), structured output, Rails integration, and streaming. Works with OpenAI, Anthropic, Google Gemini, AWS Bedrock, DeepSeek, Mistral, Ollama (local models), OpenRouter, Perplexity, GPUStack, and any OpenAI-compatible API.
+<strong>One *beautiful* Ruby API for GPT, Claude, Gemini, and more.</strong>
+
+Battle tested at [<picture><source media="(prefers-color-scheme: dark)" srcset="https://chatwithwork.com/logotype-dark.svg"><img src="https://chatwithwork.com/logotype.svg" alt="Chat with Work" height="30" align="absmiddle"></picture>](https://chatwithwork.com) — *Claude Code for your documents*
+
+[![Gem Version](https://badge.fury.io/rb/ruby_llm.svg?a=5)](https://badge.fury.io/rb/ruby_llm)
+[![Ruby Style Guide](https://img.shields.io/badge/code_style-standard-brightgreen.svg)](https://github.com/testdouble/standard)
+[![Gem Downloads](https://img.shields.io/gem/dt/ruby_llm)](https://rubygems.org/gems/ruby_llm)
+[![codecov](https://codecov.io/gh/crmne/ruby_llm/branch/main/graph/badge.svg)](https://codecov.io/gh/crmne/ruby_llm)
 
-<div class="badge-container">
-  <a href="https://badge.fury.io/rb/ruby_llm"><img src="https://badge.fury.io/rb/ruby_llm.svg?a=3" alt="Gem Version" /></a>
-  <a href="https://github.com/testdouble/standard"><img src="https://img.shields.io/badge/code_style-standard-brightgreen.svg" alt="Ruby Style Guide" /></a>
-  <a href="https://rubygems.org/gems/ruby_llm"><img alt="Gem Downloads" src="https://img.shields.io/gem/dt/ruby_llm"></a>
-  <a href="https://codecov.io/gh/crmne/ruby_llm"><img src="https://codecov.io/gh/crmne/ruby_llm/branch/main/graph/badge.svg" alt="codecov" /></a>
+<a href="https://trendshift.io/repositories/13640" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13640" alt="crmne%2Fruby_llm | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 </div>
 
-Battle tested at [<picture><source media="(prefers-color-scheme: dark)" srcset="https://chatwithwork.com/logotype-dark.svg"><img src="https://chatwithwork.com/logotype.svg" alt="Chat with Work" height="30" align="absmiddle"></picture>](https://chatwithwork.com) — *Claude Code for your documents*
+---
+
+Build chatbots, AI agents, RAG applications. Works with OpenAI, Anthropic, Google, AWS, local models, and any OpenAI-compatible API.
 
-## The problem with AI libraries
+## Why RubyLLM?
 
-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.
+Every AI provider ships their own bloated client. Different APIs. Different response formats. Different conventions. It's exhausting.
 
-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.
+RubyLLM gives you one beautiful API for all of them. Same interface whether you're using GPT, Claude, or your local Ollama. Just three dependencies: Faraday, Zeitwerk, and Marcel. That's it.
 
-## What makes it great
+## Show me the code
 
 ```ruby
 # Just ask questions
 chat = RubyLLM.chat
 chat.ask "What's the best way to learn Ruby?"
+```
 
-# Analyze images, audio, documents, and text files
+```ruby
+# Analyze any file type
 chat.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 detected
+```ruby
+# Multiple files at once
 chat.ask "Analyze these files", with: ["diagram.png", "report.pdf", "notes.txt"]
+```
 
-# Stream responses in real-time
-chat.ask "Tell me a story about a Ruby programmer" do |chunk|
+```ruby
+# Stream responses
+chat.ask "Tell me a story about Ruby" do |chunk|
   print chunk.content
 end
+```
 
+```ruby
 # Generate images
 RubyLLM.paint "a sunset over mountains in watercolor style"
+```
 
-# Create vector embeddings
+```ruby
+# Create embeddings
 RubyLLM.embed "Ruby is elegant and expressive"
+```
 
+```ruby
 # Let AI use your code
 class Weather < RubyLLM::Tool
-  description "Gets current weather for a location"
-  param :latitude, desc: "Latitude (e.g., 52.5200)"
-  param :longitude, desc: "Longitude (e.g., 13.4050)"
+  description "Get current weather"
+  param :latitude
+  param :longitude
 
   def execute(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 }
+    JSON.parse(Faraday.get(url).body)
   end
 end
 
-chat.with_tool(Weather).ask "What's the weather in Berlin? (52.5200, 13.4050)"
+chat.with_tool(Weather).ask "What's the weather in Berlin?"
+```
 
-# Get structured output with JSON schemas
+```ruby
+# Get structured output
 class ProductSchema < RubyLLM::Schema
-  string :name, description: "Product name"
-  number :price, description: "Price in USD"
-  array :features, description: "Key features" do
-    string description: "Feature description"
+  string :name
+  number :price
+  array :features do
+    string
   end
 end
 
-response = chat.with_schema(ProductSchema)
-               .ask "Analyze this product description", with: "product.txt"
-# response.content => { "name" => "...", "price" => 99.99, "features" => [...] }
+response = chat.with_schema(ProductSchema).ask "Analyze this product", with: "product.txt"
 ```
 
-## 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.
+## Features
+
+* **Chat:** Conversational AI with `RubyLLM.chat`
+* **Vision:** Analyze images and screenshots
+* **Audio:** Transcribe and understand speech
+* **Documents:** Extract from PDFs, CSVs, JSON, any file type
+* **Image generation:** Create images with `RubyLLM.paint`
+* **Embeddings:** Vector search with `RubyLLM.embed`
+* **Tools:** Let AI call your Ruby methods
+* **Structured output:** JSON schemas that just work
+* **Streaming:** Real-time responses with blocks
+* **Rails:** ActiveRecord integration with `acts_as_chat`
+* **Async:** Fiber-based concurrency
+* **Model registry:** 500+ models with capability detection and pricing
+* **Providers:** OpenAI, Anthropic, Gemini, Bedrock, DeepSeek, Mistral, Ollama, OpenRouter, Perplexity, GPUStack, and any OpenAI-compatible API
 
 ## Installation
 
@@ -103,69 +118,36 @@ gem 'ruby_llm'
 ```
 Then `bundle install`.
 
-Configure your API keys (using environment variables is recommended):
+Configure your API keys:
 ```ruby
-# config/initializers/ruby_llm.rb or similar
+# config/initializers/ruby_llm.rb
 RubyLLM.configure do |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 ...
+  config.openai_api_key = ENV['OPENAI_API_KEY']
 end
 ```
-See the [Installation Guide](https://rubyllm.com/installation) for full details.
 
-## Rails Integration
-
-Add persistence to your chat models effortlessly:
+## Rails
 
 ```bash
-# Generate models and migrations
 rails generate ruby_llm:install
 ```
 
 ```ruby
-# Or add to existing models
 class Chat < ApplicationRecord
-  acts_as_chat # Automatically saves messages & tool calls
-end
-
-class Message < ApplicationRecord
-  acts_as_message
+  acts_as_chat
 end
 
-class ToolCall < ApplicationRecord
-  acts_as_tool_call
-end
-
-# Now chats persist automatically
-chat = Chat.create!(model_id: "gpt-4.1-nano")
-chat.ask("What's in this file?", with: "report.pdf")
+chat = Chat.create! model_id: "claude-sonnet-4"
+chat.ask "What's in this file?", with: "report.pdf"
 ```
 
-See the [Rails Integration Guide](https://rubyllm.com/guides/rails) for details.
-
-## Learn More
-
-Dive deeper with the official documentation:
+## Documentation
 
--   [Installation](https://rubyllm.com/installation)
--   [Configuration](https://rubyllm.com/configuration)
--   **Guides:**
-    -   [Getting Started](https://rubyllm.com/guides/getting-started)
-    -   [Chatting with AI Models](https://rubyllm.com/guides/chat)
-    -   [Using Tools](https://rubyllm.com/guides/tools)
-    -   [Streaming Responses](https://rubyllm.com/guides/streaming)
-    -   [Rails Integration](https://rubyllm.com/guides/rails)
-    -   [Image Generation](https://rubyllm.com/guides/image-generation)
-    -   [Embeddings](https://rubyllm.com/guides/embeddings)
-    -   [Working with Models](https://rubyllm.com/guides/models)
-    -   [Error Handling](https://rubyllm.com/guides/error-handling)
-    -   [Available Models](https://rubyllm.com/guides/available-models)
+[rubyllm.com](https://rubyllm.com)
 
 ## Contributing
 
-We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for details on setup, testing, and contribution guidelines.
+See [CONTRIBUTING.md](CONTRIBUTING.md).
 
 ## License
 

data/lib/ruby_llm/active_record/acts_as.rb

@@ -3,8 +3,6 @@
 module RubyLLM
   module ActiveRecord
     # Adds chat and message persistence capabilities to ActiveRecord models.
-    # Provides a clean interface for storing chat history, message metadata,
-    # and attachments in your database.
     module ActsAs
       extend ActiveSupport::Concern
 
@@ -75,8 +73,7 @@ module RubyLLM
       end
     end
 
-    # Methods mixed into chat models to handle message persistence and
-    # provide a conversation interface.
+    # Methods mixed into chat models.
     module ChatMethods
       extend ActiveSupport::Concern
 
@@ -222,10 +219,8 @@ module RubyLLM
       end
 
       def setup_persistence_callbacks
-        # Only set up once per chat instance
         return @chat if @chat.instance_variable_get(:@_persistence_callbacks_setup)
 
-        # Set up persistence callbacks (user callbacks will be chained via on_new_message/on_end_message methods)
         @chat.on_new_message { persist_new_message }
         @chat.on_end_message { |msg| persist_message_completion(msg) }
 
@@ -234,7 +229,7 @@ module RubyLLM
       end
 
       def persist_new_message
-        @message = messages.create!(role: :assistant, content: String.new)
+        @message = messages.create!(role: :assistant, content: '')
       end
 
       def persist_message_completion(message)
@@ -243,7 +238,6 @@ module RubyLLM
         tool_call_id = find_tool_call_id(message.tool_call_id) if message.tool_call_id
 
         transaction do
-          # Convert parsed JSON back to JSON string for storage
           content = message.content
           content = content.to_json if content.is_a?(Hash) || content.is_a?(Array)
 
@@ -297,7 +291,6 @@ module RubyLLM
       def convert_to_active_storage_format(source)
         return if source.blank?
 
-        # Let RubyLLM::Attachment handle the heavy lifting
         attachment = RubyLLM::Attachment.new(source)
 
         {
@@ -311,8 +304,7 @@ module RubyLLM
       end
     end
 
-    # Methods mixed into message models to handle serialization and
-    # provide a clean interface to the underlying message data.
+    # Methods mixed into message models.
     module MessageMethods
       extend ActiveSupport::Concern
 

data/lib/ruby_llm/aliases.json

@@ -182,6 +182,10 @@
     "openai": "gpt-oss-120b",
     "openrouter": "openai/gpt-oss-120b"
   },
+  "gpt-oss-20b": {
+    "openai": "gpt-oss-20b",
+    "openrouter": "openai/gpt-oss-20b"
+  },
   "o1": {
     "openai": "o1",
     "openrouter": "openai/o1"

data/lib/ruby_llm/aliases.rb

@@ -1,53 +1,35 @@
 # frozen_string_literal: true
 
 module RubyLLM
-  # Manages model aliases, allowing users to reference models by simpler names
-  # that map to specific model versions across different providers.
-  #
-  # Aliases are defined in aliases.json and follow the format:
-  #   {
-  #     "simple-name": {
-  #       "provider1": "specific-version-for-provider1",
-  #       "provider2": "specific-version-for-provider2"
-  #     }
-  #   }
+  # Manages model aliases for provider-specific versions
   class Aliases
     class << self
-      # Resolves a model ID to its provider-specific version
-      #
-      # @param model_id [String] the model identifier or alias
-      # @param provider_slug [String, Symbol, nil] optional provider to resolve for
-      # @return [String] the resolved model ID or the original if no alias exists
       def resolve(model_id, provider = nil)
         return model_id unless aliases[model_id]
 
         if provider
           aliases[model_id][provider.to_s] || model_id
         else
-          # Get native provider's version
           aliases[model_id].values.first || model_id
         end
       end
 
-      # Returns the loaded aliases mapping
-      # @return [Hash] the aliases mapping
       def aliases
         @aliases ||= load_aliases
       end
 
-      # Loads aliases from the JSON file
-      # @return [Hash] the loaded aliases
+      def aliases_file
+        File.expand_path('aliases.json', __dir__)
+      end
+
       def load_aliases
-        file_path = File.expand_path('aliases.json', __dir__)
-        if File.exist?(file_path)
-          JSON.parse(File.read(file_path))
+        if File.exist?(aliases_file)
+          JSON.parse(File.read(aliases_file))
         else
           {}
         end
       end
 
-      # Reloads aliases from disk
-      # @return [Hash] the reloaded aliases
       def reload!
         @aliases = load_aliases
       end

data/lib/ruby_llm/chat.rb

@@ -1,13 +1,7 @@
 # frozen_string_literal: true
 
 module RubyLLM
-  # Represents a conversation with an AI model. Handles message history,
-  # streaming responses, and tool integration with a simple, conversational API.
-  #
-  # Example:
-  #   chat = RubyLLM.chat
-  #   chat.ask "What's the best way to learn Ruby?"
-  #   chat.ask "Can you elaborate on that?"
+  # Represents a conversation with an AI model
   class Chat
     include Enumerable
 
@@ -22,7 +16,7 @@ module RubyLLM
       @config = context&.config || RubyLLM.config
       model_id = model || @config.default_model
       with_model(model_id, provider: provider, assume_exists: assume_model_exists)
-      @temperature = 0.7
+      @temperature = nil
       @messages = []
       @tools = {}
       @params = {}
@@ -51,10 +45,6 @@ module RubyLLM
     end
 
     def with_tool(tool)
-      unless @model.supports_functions?
-        raise UnsupportedFunctionsError, "Model #{@model.id} doesn't support function calling"
-      end
-
       tool_instance = tool.is_a?(Class) ? tool.new : tool
       @tools[tool_instance.name.to_sym] = tool_instance
       self
@@ -94,11 +84,7 @@ module RubyLLM
       self
     end
 
-    def with_schema(schema, force: false)
-      unless force || @model.structured_output?
-        raise UnsupportedStructuredOutputError, "Model #{@model.id} doesn't support structured output"
-      end
-
+    def with_schema(schema)
       schema_instance = schema.is_a?(Class) ? schema.new : schema
 
       # Accept both RubyLLM::Schema instances and plain JSON schemas
@@ -149,7 +135,6 @@ module RubyLLM
 
       @on[:new_message]&.call unless block_given?
 
-      # Parse JSON if schema was set
       if @schema && response.content.is_a?(String)
         begin
           response.content = JSON.parse(response.content)
@@ -192,7 +177,6 @@ module RubyLLM
           @on[:new_message]&.call
         end
 
-        # Pass chunk to user's block
         block.call chunk
       end
     end

data/lib/ruby_llm/configuration.rb

@@ -1,16 +1,8 @@
 # frozen_string_literal: true
 
 module RubyLLM
-  # Global configuration for RubyLLM. Manages API keys, default models,
-  # and provider-specific settings.
-  #
-  # Configure via:
-  #   RubyLLM.configure do |config|
-  #     config.openai_api_key = ENV['OPENAI_API_KEY']
-  #     config.anthropic_api_key = ENV['ANTHROPIC_API_KEY']
-  #   end
+  # Global configuration for RubyLLM
   class Configuration
-    # Provider-specific configuration
     attr_accessor :openai_api_key,
                   :openai_api_base,
                   :openai_organization_id,
@@ -44,11 +36,9 @@ module RubyLLM
                   :logger,
                   :log_file,
                   :log_level,
-                  :log_assume_model_exists,
                   :log_stream_debug
 
     def initialize
-      # Connection configuration
       @request_timeout = 120
       @max_retries = 3
       @retry_interval = 0.1
@@ -56,15 +46,12 @@ module RubyLLM
       @retry_interval_randomness = 0.5
       @http_proxy = nil
 
-      # Default models
       @default_model = 'gpt-4.1-nano'
       @default_embedding_model = 'text-embedding-3-small'
       @default_image_model = 'gpt-image-1'
 
-      # Logging configuration
       @log_file = $stdout
       @log_level = ENV['RUBYLLM_DEBUG'] ? Logger::DEBUG : Logger::INFO
-      @log_assume_model_exists = true
       @log_stream_debug = ENV['RUBYLLM_STREAM_DEBUG'] == 'true'
     end
 

data/lib/ruby_llm/content.rb

@@ -2,7 +2,6 @@
 
 module RubyLLM
   # Represents the content sent to or received from an LLM.
-  # Selects the appropriate attachment class based on the content type.
   class Content
     attr_reader :text, :attachments
 
@@ -42,8 +41,7 @@ module RubyLLM
 
     def process_attachments(attachments)
       if attachments.is_a?(Hash)
-        # Ignores types (like :image, :audio, :text, :pdf) since we have robust MIME type detection
-        attachments.each_value(&method(:process_attachments_array_or_string))
+        attachments.each_value { |attachment| process_attachments_array_or_string(attachment) }
       else
         process_attachments_array_or_string attachments
       end

data/lib/ruby_llm/embedding.rb

@@ -1,8 +1,7 @@
 # frozen_string_literal: true
 
 module RubyLLM
-  # Core embedding interface. Provides a clean way to generate embeddings
-  # from text using various provider models.
+  # Core embedding interface.
   class Embedding
     attr_reader :vectors, :model, :input_tokens
 

data/lib/ruby_llm/error.rb

@@ -3,13 +3,6 @@
 module RubyLLM
   # Custom error class that wraps API errors from different providers
   # into a consistent format with helpful error messages.
-  #
-  # Example:
-  #   begin
-  #     chat.ask "What's 2+2?"
-  #   rescue RubyLLM::Error => e
-  #     puts "Couldn't chat with AI: #{e.message}"
-  #   end
   class Error < StandardError
     attr_reader :response
 
@@ -23,9 +16,7 @@ module RubyLLM
   class ConfigurationError < StandardError; end
   class InvalidRoleError < StandardError; end
   class ModelNotFoundError < StandardError; end
-  class UnsupportedFunctionsError < StandardError; end
   class UnsupportedAttachmentError < StandardError; end
-  class UnsupportedStructuredOutputError < StandardError; end
 
   # Error classes for different HTTP status codes
   class BadRequestError < Error; end
@@ -38,7 +29,6 @@ module RubyLLM
   class UnauthorizedError < Error; end
 
   # Faraday middleware that maps provider-specific API errors to RubyLLM errors.
-  # Uses provider's parse_error method to extract meaningful error messages.
   class ErrorMiddleware < Faraday::Middleware
     def initialize(app, options = {})
       super(app)

data/lib/ruby_llm/image.rb

@@ -2,8 +2,6 @@
 
 module RubyLLM
   # Represents a generated image from an AI model.
-  # Provides an interface to image generation capabilities
-  # from providers like DALL-E and Gemini's Imagen.
   class Image
     attr_reader :url, :data, :mime_type, :revised_prompt, :model_id
 
@@ -19,7 +17,6 @@ module RubyLLM
       !@data.nil?
     end
 
-    # Returns the raw binary image data regardless of source
     def to_blob
       if base64?
         Base64.decode64 @data
@@ -29,7 +26,6 @@ module RubyLLM
       end
     end
 
-    # Saves the image to a file path
     def save(path)
       File.binwrite(File.expand_path(path), to_blob)
       path

data/lib/ruby_llm/message.rb

@@ -1,9 +1,7 @@
 # frozen_string_literal: true
 
 module RubyLLM
-  # A single message in a chat conversation. Can represent user input,
-  # AI responses, or tool interactions. Tracks token usage and handles
-  # the complexities of tool calls and responses.
+  # A single message in a chat conversation.
   class Message
     ROLES = %i[system user assistant tool].freeze
 
@@ -65,7 +63,7 @@ module RubyLLM
       case content
       when String then Content.new(content)
       when Hash then Content.new(content[:text], content)
-      else content # Pass through nil, Content, or other types
+      else content
       end
     end
 

data/lib/ruby_llm/model/info.rb

@@ -3,14 +3,6 @@
 module RubyLLM
   module Model
     # Information about an AI model's capabilities, pricing, and metadata.
-    # Used by the Models registry to help developers choose the right model
-    # for their needs.
-    #
-    # Example:
-    #   model = RubyLLM.models.find('gpt-4')
-    #   model.supports_vision?          # => true
-    #   model.supports_functions?       # => true
-    #   model.input_price_per_million   # => 30.0
     class Info
       attr_reader :id, :name, :provider, :family, :created_at, :context_window, :max_output_tokens, :knowledge_cutoff,
                   :modalities, :capabilities, :pricing, :metadata
@@ -30,7 +22,6 @@ module RubyLLM
         @metadata = data[:metadata] || {}
       end
 
-      # Capability methods
       def supports?(capability)
         capabilities.include?(capability.to_s)
       end
@@ -41,7 +32,6 @@ module RubyLLM
         end
       end
 
-      # Backward compatibility methods
       def display_name
         name
       end

data/lib/ruby_llm/model/pricing.rb

@@ -3,12 +3,10 @@
 module RubyLLM
   module Model
     # A collection that manages and provides access to different categories of pricing information
-    # (text tokens, images, audio tokens, embeddings)
     class Pricing
       def initialize(data)
         @data = {}
 
-        # Initialize pricing categories
         %i[text_tokens images audio_tokens embeddings].each do |category|
           @data[category] = PricingCategory.new(data[category]) if data[category] && !empty_pricing?(data[category])
         end
@@ -33,7 +31,6 @@ module RubyLLM
       private
 
       def empty_pricing?(data)
-        # Check if all pricing values in this category are zero or nil
         return true unless data
 
         %i[standard batch].each do |tier|