ruby_llm 0.1.0.pre37 → 0.1.0.pre39

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8befc508f1a0bdbaf7b113f3a2f8584f78fbe756ac07b22344af9ea90bc47f31
-  data.tar.gz: 389cb1518cacfa6448f30891d45e573536c768aa8092f8d1fbac156ff4c2d4c5
+  metadata.gz: 0c887462ad2c35c5e831991b8b6cd78095c3f286861fd4913afddd5887833f3b
+  data.tar.gz: 382a2dd05532510ed5ac8ae5deb7a81febb831e3bbd8a11376eba0ad266451c3
 SHA512:
-  metadata.gz: 67493fd05b3c9f0765b8d7bd72d295756e615ad6ab8b133181c8a472d28a64ce83e8aaedf48f556de8e9ddc1d39c59fdd4e7cdf4f0521eff9b9d34726a6b6bcd
-  data.tar.gz: e4569279dc890b62881c3d8da2cd03370fd8a87f6c20f112fe0bbce2d61aec0acba726d9d89252b724f4f4a2cc97ce383f229bddc8ea9d6c204fbcc66e71f6de
+  metadata.gz: b8c372a54f0bb94ecf6b22ead70f34a324974f4f61ad4610ba15ffee64ed8ec226fac24a74b73667bc07ea73a14fb5ee5d813759ab60f86c54c7d00cfc3905aa
+  data.tar.gz: 868fadbdaf583aa911a98cce36b6b61208a2065d92f32c31f1a2ea0908a37aa91f2047d2ea7aa77911093a7fcbb4ae10ace87f7ddafa2d39856e67a54d5bf846

data/.github/workflows/cicd.yml

@@ -3,6 +3,12 @@ name: CI
 on:
   push:
     branches: [ "main" ]
+    paths:
+      - 'lib/**'
+      - 'spec/**'
+      - 'Gemfile'
+      - 'Rakefile'
+      - 'ruby_llm.gemspec'
   pull_request:
     branches: [ "main" ]
   workflow_call:

data/.rspec_status

@@ -1,7 +1,38 @@
-example_id                                  | status | run_time     |
-------------------------------------------- | ------ | ------------ |
-./spec/ruby_llm/chat_content_spec.rb[1:1:1] | passed | 3.59 seconds |
-./spec/ruby_llm/chat_content_spec.rb[1:1:2] | passed | 1.51 seconds |
-./spec/ruby_llm/chat_content_spec.rb[1:1:3] | passed | 2.29 seconds |
-./spec/ruby_llm/chat_content_spec.rb[1:2:1] | passed | 2.06 seconds |
-./spec/ruby_llm/chat_content_spec.rb[1:2:2] | passed | 2.04 seconds |
+example_id                                         | status | run_time        |
+-------------------------------------------------- | ------ | --------------- |
+./spec/ruby_llm/active_record/acts_as_spec.rb[1:1] | passed | 3.38 seconds    |
+./spec/ruby_llm/active_record/acts_as_spec.rb[1:2] | passed | 2.48 seconds    |
+./spec/ruby_llm/chat_content_spec.rb[1:1:1]        | passed | 2.74 seconds    |
+./spec/ruby_llm/chat_content_spec.rb[1:1:2]        | passed | 1.29 seconds    |
+./spec/ruby_llm/chat_content_spec.rb[1:1:3]        | passed | 2.54 seconds    |
+./spec/ruby_llm/chat_content_spec.rb[1:2:1]        | passed | 2.77 seconds    |
+./spec/ruby_llm/chat_content_spec.rb[1:2:2]        | passed | 2.1 seconds     |
+./spec/ruby_llm/chat_spec.rb[1:1:1:1]              | passed | 1.02 seconds    |
+./spec/ruby_llm/chat_spec.rb[1:1:1:2]              | passed | 3.95 seconds    |
+./spec/ruby_llm/chat_spec.rb[1:1:2:1]              | passed | 0.4854 seconds  |
+./spec/ruby_llm/chat_spec.rb[1:1:2:2]              | passed | 1.37 seconds    |
+./spec/ruby_llm/chat_spec.rb[1:1:3:1]              | passed | 7.34 seconds    |
+./spec/ruby_llm/chat_spec.rb[1:1:3:2]              | passed | 19.22 seconds   |
+./spec/ruby_llm/chat_spec.rb[1:1:4:1]              | passed | 3.15 seconds    |
+./spec/ruby_llm/chat_spec.rb[1:1:4:2]              | passed | 2.51 seconds    |
+./spec/ruby_llm/chat_streaming_spec.rb[1:1:1:1]    | passed | 0.91374 seconds |
+./spec/ruby_llm/chat_streaming_spec.rb[1:1:2:1]    | passed | 0.50088 seconds |
+./spec/ruby_llm/chat_streaming_spec.rb[1:1:3:1]    | passed | 5.69 seconds    |
+./spec/ruby_llm/chat_streaming_spec.rb[1:1:4:1]    | passed | 1.22 seconds    |
+./spec/ruby_llm/chat_tools_spec.rb[1:1:1:1]        | passed | 3.75 seconds    |
+./spec/ruby_llm/chat_tools_spec.rb[1:1:1:2]        | passed | 6.1 seconds     |
+./spec/ruby_llm/chat_tools_spec.rb[1:1:1:3]        | passed | 5.32 seconds    |
+./spec/ruby_llm/chat_tools_spec.rb[1:1:2:1]        | passed | 1.21 seconds    |
+./spec/ruby_llm/chat_tools_spec.rb[1:1:2:2]        | passed | 2.36 seconds    |
+./spec/ruby_llm/chat_tools_spec.rb[1:1:2:3]        | passed | 2.78 seconds    |
+./spec/ruby_llm/chat_tools_spec.rb[1:1:3:1]        | passed | 1.87 seconds    |
+./spec/ruby_llm/chat_tools_spec.rb[1:1:3:2]        | passed | 3.12 seconds    |
+./spec/ruby_llm/chat_tools_spec.rb[1:1:3:3]        | passed | 3.83 seconds    |
+./spec/ruby_llm/embeddings_spec.rb[1:1:1:1]        | passed | 0.33357 seconds |
+./spec/ruby_llm/embeddings_spec.rb[1:1:1:2]        | passed | 0.43632 seconds |
+./spec/ruby_llm/embeddings_spec.rb[1:1:2:1]        | passed | 0.65614 seconds |
+./spec/ruby_llm/embeddings_spec.rb[1:1:2:2]        | passed | 2.16 seconds    |
+./spec/ruby_llm/error_handling_spec.rb[1:1]        | passed | 0.19586 seconds |
+./spec/ruby_llm/image_generation_spec.rb[1:1:1]    | passed | 12.77 seconds   |
+./spec/ruby_llm/image_generation_spec.rb[1:1:2]    | passed | 18.13 seconds   |
+./spec/ruby_llm/image_generation_spec.rb[1:1:3]    | passed | 0.00035 seconds |

data/README.md

@@ -20,6 +20,8 @@ A delightful Ruby way to work with AI. Chat in text, analyze and generate images
   <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>
 </p>
 
+🤺 Battle tested at [💬  Chat with Work](https://chatwithwork.com)
+
 ## Features
 
 - 💬 **Beautiful Chat Interface** - Converse with AI models as easily as `RubyLLM.chat.ask "teach me Ruby"`

data/lib/ruby_llm/models.json

@@ -23,7 +23,7 @@
     "created_at": "2023-08-21T18:16:55+02:00",
     "display_name": "Babbage 002",
     "provider": "openai",
-    "context_window": 16384,
+    "context_window": 16385,
     "max_tokens": 16384,
     "type": "chat",
     "family": "babbage",
@@ -262,7 +262,7 @@
     "created_at": "2023-08-21T18:11:41+02:00",
     "display_name": "Davinci 002",
     "provider": "openai",
-    "context_window": 16384,
+    "context_window": 16385,
     "max_tokens": 16384,
     "type": "chat",
     "family": "davinci",
@@ -287,7 +287,7 @@
     "family": "chat",
     "supports_vision": false,
     "supports_functions": true,
-    "supports_json_mode": true,
+    "supports_json_mode": false,
     "input_price_per_million": 0.27,
     "output_price_per_million": 1.1,
     "metadata": {
@@ -371,63 +371,6 @@
       "owned_by": "google"
     }
   },
-  {
-    "id": "gemini-1.0-pro",
-    "created_at": null,
-    "display_name": "Gemini 1.0 Pro",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "gemini10_pro",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.5,
-    "output_price_per_million": 1.5,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-1.0-pro-001",
-    "created_at": null,
-    "display_name": "Gemini 1.0 Pro 001",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "gemini10_pro",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.5,
-    "output_price_per_million": 1.5,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-1.0-pro-latest",
-    "created_at": null,
-    "display_name": "Gemini 1.0 Pro Latest",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "gemini10_pro",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.5,
-    "output_price_per_million": 1.5,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
   {
     "id": "gemini-1.0-pro-vision-latest",
     "created_at": null,
@@ -884,44 +827,6 @@
       "owned_by": "google"
     }
   },
-  {
-    "id": "gemini-2.0-flash-lite-preview",
-    "created_at": null,
-    "display_name": "Gemini 2.0 Flash Lite Preview",
-    "provider": "gemini",
-    "context_window": 1048576,
-    "max_tokens": 8192,
-    "type": "chat",
-    "family": "gemini20_flash_lite",
-    "supports_vision": true,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-2.0-flash-lite-preview-02-05",
-    "created_at": null,
-    "display_name": "Gemini 2.0 Flash Lite Preview 02 05",
-    "provider": "gemini",
-    "context_window": 1048576,
-    "max_tokens": 8192,
-    "type": "chat",
-    "family": "gemini20_flash_lite",
-    "supports_vision": true,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
   {
     "id": "gemini-2.0-flash-mmgen-rev17",
     "created_at": null,
@@ -1093,25 +998,6 @@
       "owned_by": "google"
     }
   },
-  {
-    "id": "gemini-pro",
-    "created_at": null,
-    "display_name": "Gemini Pro",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
   {
     "id": "gemini-pro-vision",
     "created_at": null,
@@ -1212,7 +1098,7 @@
     "created_at": "2024-01-23T23:19:18+01:00",
     "display_name": "GPT-3.5-Turbo 0125",
     "provider": "openai",
-    "context_window": 16385,
+    "context_window": 4096,
     "max_tokens": 4096,
     "type": "chat",
     "family": "gpt35",
@@ -1231,7 +1117,7 @@
     "created_at": "2023-11-02T22:15:48+01:00",
     "display_name": "GPT-3.5-Turbo 1106",
     "provider": "openai",
-    "context_window": 16385,
+    "context_window": 4096,
     "max_tokens": 4096,
     "type": "chat",
     "family": "gpt35",
@@ -1460,7 +1346,7 @@
     "display_name": "GPT-4o 20240513",
     "provider": "openai",
     "context_window": 128000,
-    "max_tokens": 4096,
+    "max_tokens": 16384,
     "type": "chat",
     "family": "gpt4o",
     "supports_vision": true,
@@ -1650,7 +1536,7 @@
     "display_name": "GPT-4o-Mini Realtime Preview",
     "provider": "openai",
     "context_window": 128000,
-    "max_tokens": 4096,
+    "max_tokens": 16384,
     "type": "chat",
     "family": "gpt4o_mini_realtime",
     "supports_vision": true,
@@ -1669,7 +1555,7 @@
     "display_name": "GPT-4o-Mini Realtime Preview 20241217",
     "provider": "openai",
     "context_window": 128000,
-    "max_tokens": 4096,
+    "max_tokens": 16384,
     "type": "chat",
     "family": "gpt4o_mini_realtime",
     "supports_vision": true,
@@ -1688,7 +1574,7 @@
     "display_name": "GPT-4o-Realtime Preview",
     "provider": "openai",
     "context_window": 128000,
-    "max_tokens": 4096,
+    "max_tokens": 16384,
     "type": "chat",
     "family": "gpt4o_realtime",
     "supports_vision": true,
@@ -1707,7 +1593,7 @@
     "display_name": "GPT-4o-Realtime Preview 20241001",
     "provider": "openai",
     "context_window": 128000,
-    "max_tokens": 4096,
+    "max_tokens": 16384,
     "type": "chat",
     "family": "gpt4o_realtime",
     "supports_vision": true,
@@ -1726,7 +1612,7 @@
     "display_name": "GPT-4o-Realtime Preview 20241217",
     "provider": "openai",
     "context_window": 128000,
-    "max_tokens": 4096,
+    "max_tokens": 16384,
     "type": "chat",
     "family": "gpt4o_realtime",
     "supports_vision": true,

data/lib/ruby_llm/providers/deepseek/capabilities.rb

@@ -65,8 +65,8 @@ module RubyLLM
         # Determines if the model supports JSON mode
         # @param model_id [String] the model identifier
         # @return [Boolean] true if the model supports JSON mode
-        def supports_json_mode?(model_id)
-          model_id.match?(/deepseek-chat/) # Only deepseek-chat supports JSON mode
+        def supports_json_mode?(_model_id)
+          false # DeepSeek function calling is unstable
         end
 
         # Returns a formatted display name for the model

data/lib/ruby_llm/providers/openai/capabilities.rb

@@ -15,8 +15,7 @@ module RubyLLM
           when /o1-2024/, /o3-mini/, /o3-mini-2025/ then 200_000
           when /gpt-4o/, /gpt-4o-mini/, /gpt-4-turbo/, /o1-mini/ then 128_000
           when /gpt-4-0[0-9]{3}/ then 8_192
-          when /gpt-3.5/ then 16_385
-          when /babbage-002/, /davinci-002/ then 16_384
+          when /gpt-3.5-turbo$/, /babbage-002/, /davinci-002/, /16k/ then 16_385
           else 4_096
           end
         end

data/lib/ruby_llm/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RubyLLM
-  VERSION = '0.1.0.pre37'
+  VERSION = '0.1.0.pre39'
 end

data/ruby_llm.gemspec

@@ -28,7 +28,7 @@ Gem::Specification.new do |spec|
   # 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)/}) }
+    `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) }

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ruby_llm
 version: !ruby/object:Gem::Version
-  version: 0.1.0.pre37
+  version: 0.1.0.pre39
 platform: ruby
 authors:
 - Carmine Paolino
@@ -111,21 +111,6 @@ files:
 - Rakefile
 - bin/console
 - bin/setup
-- docs/.gitignore
-- docs/Gemfile
-- docs/_config.yml
-- docs/_data/navigation.yml
-- docs/guides/chat.md
-- docs/guides/embeddings.md
-- docs/guides/error-handling.md
-- docs/guides/getting-started.md
-- docs/guides/image-generation.md
-- docs/guides/index.md
-- docs/guides/rails.md
-- docs/guides/streaming.md
-- docs/guides/tools.md
-- docs/index.md
-- docs/installation.md
 - lib/ruby_llm.rb
 - lib/ruby_llm/active_record/acts_as.rb
 - lib/ruby_llm/chat.rb

data/docs/.gitignore

@@ -1,7 +0,0 @@
-_site/
-.sass-cache/
-.jekyll-cache/
-.jekyll-metadata
-# Ignore folders generated by Bundler
-.bundle/
-vendor/

data/docs/Gemfile

@@ -1,11 +0,0 @@
-source 'https://rubygems.org'
-
-gem 'jekyll', '~> 4.3'
-gem 'just-the-docs', '~> 0.7.0'
-gem 'webrick', '~> 1.8'
-
-# GitHub Pages plugins
-group :jekyll_plugins do
-  gem 'jekyll-remote-theme'
-  gem 'jekyll-seo-tag'
-end

data/docs/_config.yml

@@ -1,43 +0,0 @@
-title: RubyLLM
-description: A delightful Ruby way to work with AI
-url: https://crmne.github.io/ruby_llm
-baseurl: /ruby_llm
-remote_theme: just-the-docs/just-the-docs
-
-# Enable search
-search_enabled: true
-search:
-  heading_level: 2
-  previews: 3
-  preview_words_before: 5
-  preview_words_after: 10
-  tokenizer_separator: /[\s/]+/
-  rel_url: true
-  button: false
-
-# Navigation structure
-nav_external_links:
-  - title: RubyLLM on GitHub
-    url: https://github.com/crmne/ruby_llm
-    hide_icon: false
-
-# Footer content
-footer_content: "Copyright &copy; 2025 <a href='https://paolino.me'>Carmine Paolino</a>. Distributed under an <a href=\"https://github.com/crmne/ruby_llm/tree/main/LICENSE\">MIT license.</a>"
-
-# Enable copy button on code blocks
-enable_copy_code_button: true
-
-# Make Anchor links show on hover
-heading_anchors: true
-
-# Color scheme
-color_scheme: light
-
-# Google Analytics
-ga_tracking:
-ga_tracking_anonymize_ip: true
-
-# Custom plugins (GitHub Pages allows these)
-plugins:
-  - jekyll-remote-theme
-  - jekyll-seo-tag

data/docs/_data/navigation.yml

@@ -1,25 +0,0 @@
-- title: Home
-  url: /
-- title: Installation
-  url: /installation
-- title: Guides
-  url: /guides/
-  subfolderitems:
-    - title: Getting Started
-      url: /guides/getting-started
-    - title: Chat
-      url: /guides/chat
-    - title: Tools
-      url: /guides/tools
-    - title: Streaming
-      url: /guides/streaming
-    - title: Rails Integration
-      url: /guides/rails
-    - title: Image Generation
-      url: /guides/image-generation
-    - title: Embeddings
-      url: /guides/embeddings
-    - title: Error Handling
-      url: /guides/error-handling
-- title: GitHub
-  url: https://github.com/crmne/ruby_llm

data/docs/guides/chat.md

@@ -1,206 +0,0 @@
----
-layout: default
-title: Chat
-parent: Guides
-nav_order: 2
-permalink: /guides/chat
----
-
-# Chatting with AI Models
-
-RubyLLM's chat interface provides a natural way to interact with various AI models. This guide covers everything from basic chatting to advanced features like multimodal inputs and streaming responses.
-
-## Basic Chat
-
-Creating a chat and asking questions is straightforward:
-
-```ruby
-# Create a chat with the default model
-chat = RubyLLM.chat
-
-# Ask a question
-response = chat.ask "What's the best way to learn Ruby?"
-
-# The response is a Message object
-puts response.content
-puts "Role: #{response.role}"
-puts "Model: #{response.model_id}"
-puts "Tokens: #{response.input_tokens} input, #{response.output_tokens} output"
-```
-
-## Choosing Models
-
-You can specify which model to use when creating a chat:
-
-```ruby
-# Create a chat with a specific model
-chat = RubyLLM.chat(model: 'gpt-4o-mini')
-
-# Use Claude instead
-claude_chat = RubyLLM.chat(model: 'claude-3-5-sonnet-20241022')
-
-# Or change the model for an existing chat
-chat.with_model('gemini-2.0-flash')
-```
-
-## Multi-turn Conversations
-
-Chats maintain conversation history automatically:
-
-```ruby
-chat = RubyLLM.chat
-
-# Start a conversation
-chat.ask "What's your favorite programming language?"
-
-# Follow up
-chat.ask "Why do you like that language?"
-
-# Continue the conversation
-chat.ask "What are its weaknesses?"
-
-# Access the conversation history
-chat.messages.each do |message|
-  puts "#{message.role}: #{message.content[0..50]}..."
-end
-```
-
-## Working with Images
-
-Vision-capable models can understand images:
-
-```ruby
-chat = RubyLLM.chat
-
-# Ask about an image (local file)
-chat.ask "What's in this image?", with: { image: "path/to/image.jpg" }
-
-# Or use an image URL
-chat.ask "Describe this picture", with: { image: "https://example.com/image.jpg" }
-
-# Include multiple images
-chat.ask "Compare these two charts", with: {
-  image: ["chart1.png", "chart2.png"]
-}
-
-# Combine text and image
-chat.ask "Is this the Ruby logo?", with: { image: "logo.png" }
-```
-
-## Working with Audio
-
-Models with audio capabilities can process spoken content:
-
-```ruby
-chat = RubyLLM.chat(model: 'gpt-4o-audio-preview')
-
-# Analyze audio content
-chat.ask "What's being said in this recording?", with: {
-  audio: "meeting.wav"
-}
-
-# Ask follow-up questions about the audio
-chat.ask "Summarize the key points mentioned"
-```
-
-## Streaming Responses
-
-For a more interactive experience, you can stream responses as they're generated:
-
-```ruby
-chat = RubyLLM.chat
-
-# Stream the response with a block
-chat.ask "Tell me a story about a Ruby programmer" do |chunk|
-  # Each chunk is a partial response
-  print chunk.content
-  $stdout.flush # Ensure output is displayed immediately
-end
-
-# Useful for long responses or real-time displays
-chat.ask "Write a detailed essay about programming paradigms" do |chunk|
-  add_to_ui(chunk.content) # Your method to update UI
-end
-```
-
-## Temperature Control
-
-Control the creativity and randomness of AI responses:
-
-```ruby
-# Higher temperature (more creative)
-creative_chat = RubyLLM.chat.with_temperature(0.9)
-creative_chat.ask "Write a poem about Ruby programming"
-
-# Lower temperature (more deterministic)
-precise_chat = RubyLLM.chat.with_temperature(0.1)
-precise_chat.ask "Explain how Ruby's garbage collector works"
-```
-
-## Access Token Usage
-
-RubyLLM automatically tracks token usage for billing and quota management:
-
-```ruby
-chat = RubyLLM.chat
-response = chat.ask "Explain quantum computing"
-
-# Check token usage
-puts "Input tokens: #{response.input_tokens}"
-puts "Output tokens: #{response.output_tokens}"
-puts "Total tokens: #{response.input_tokens + response.output_tokens}"
-
-# Estimate cost (varies by model)
-model = RubyLLM.models.find(response.model_id)
-input_cost = response.input_tokens * model.input_price_per_million / 1_000_000
-output_cost = response.output_tokens * model.output_price_per_million / 1_000_000
-puts "Estimated cost: $#{(input_cost + output_cost).round(6)}"
-```
-
-## Registering Event Handlers
-
-You can register callbacks for chat events:
-
-```ruby
-chat = RubyLLM.chat
-
-# Called when a new assistant message starts
-chat.on_new_message do
-  puts "Assistant is typing..."
-end
-
-# Called when a message is complete
-chat.on_end_message do |message|
-  puts "Response complete!"
-  puts "Used #{message.input_tokens + message.output_tokens} tokens"
-end
-
-# These callbacks work with both streaming and non-streaming responses
-chat.ask "Tell me about Ruby's history"
-```
-
-## Multiple Parallel Chats
-
-You can maintain multiple separate chat instances:
-
-```ruby
-# Create multiple chat instances
-ruby_chat = RubyLLM.chat
-python_chat = RubyLLM.chat
-
-# Each has its own conversation history
-ruby_chat.ask "What's great about Ruby?"
-python_chat.ask "What's great about Python?"
-
-# Continue separate conversations
-ruby_chat.ask "How does Ruby handle metaprogramming?"
-python_chat.ask "How does Python handle decorators?"
-```
-
-## Next Steps
-
-Now that you understand chat basics, you might want to explore:
-
-- [Using Tools]({% link guides/tools.md %}) to let AI use your Ruby code
-- [Streaming Responses]({% link guides/streaming.md %}) for real-time interactions
-- [Rails Integration]({% link guides/rails.md %}) to persist conversations in your apps