ruby_llm_community 1.1.0 → 1.2.0

data/lib/ruby_llm/providers/red_candle/models.rb

@@ -0,0 +1,121 @@
+# frozen_string_literal: true
+
+module RubyLLM
+  module Providers
+    class RedCandle
+      # Models methods of the RedCandle integration
+      module Models
+        # TODO: red-candle supports more models, but let's start with some well tested ones.
+        SUPPORTED_MODELS = [
+          {
+            id: 'google/gemma-3-4b-it-qat-q4_0-gguf',
+            name: 'Gemma 3 4B Instruct (Quantized)',
+            gguf_file: 'gemma-3-4b-it-q4_0.gguf',
+            tokenizer: 'google/gemma-3-4b-it', # Tokenizer from base model
+            context_window: 8192,
+            family: 'gemma',
+            architecture: 'gemma2',
+            supports_chat: true,
+            supports_structured: true
+          },
+          {
+            id: 'TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF',
+            name: 'TinyLlama 1.1B Chat (Quantized)',
+            gguf_file: 'tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf',
+            context_window: 2048,
+            family: 'llama',
+            architecture: 'llama',
+            supports_chat: true,
+            supports_structured: true
+          },
+          {
+            id: 'TheBloke/Mistral-7B-Instruct-v0.2-GGUF',
+            name: 'Mistral 7B Instruct v0.2 (Quantized)',
+            gguf_file: 'mistral-7b-instruct-v0.2.Q4_K_M.gguf',
+            tokenizer: 'mistralai/Mistral-7B-Instruct-v0.2',
+            context_window: 32_768,
+            family: 'mistral',
+            architecture: 'mistral',
+            supports_chat: true,
+            supports_structured: true
+          },
+          {
+            id: 'Qwen/Qwen2.5-1.5B-Instruct-GGUF',
+            name: 'Qwen 2.1.5B Instruct (Quantized)',
+            gguf_file: 'qwen2.5-1.5b-instruct-q4_k_m.gguf',
+            context_window: 32_768,
+            family: 'qwen2',
+            architecture: 'qwen2',
+            supports_chat: true,
+            supports_structured: true
+          },
+          {
+            id: 'microsoft/Phi-3-mini-4k-instruct',
+            name: 'Phi 3',
+            context_window: 4096,
+            family: 'phi',
+            architecture: 'phi',
+            supports_chat: true,
+            supports_structured: true
+          }
+        ].freeze
+
+        def list_models
+          SUPPORTED_MODELS.map do |model_data|
+            Model::Info.new(
+              id: model_data[:id],
+              name: model_data[:name],
+              provider: slug,
+              family: model_data[:family],
+              context_window: model_data[:context_window],
+              capabilities: %w[streaming structured_output],
+              modalities: { input: %w[text], output: %w[text] }
+            )
+          end
+        end
+
+        def models
+          @models ||= list_models
+        end
+
+        def model(id)
+          models.find { |m| m.id == id } ||
+            raise(Error.new(nil,
+                            "Model #{id} not found in Red Candle provider. Available models: #{model_ids.join(', ')}"))
+        end
+
+        def model_available?(id)
+          SUPPORTED_MODELS.any? { |m| m[:id] == id }
+        end
+
+        def model_ids
+          SUPPORTED_MODELS.map { |m| m[:id] }
+        end
+
+        def model_info(id)
+          SUPPORTED_MODELS.find { |m| m[:id] == id }
+        end
+
+        def supports_chat?(model_id)
+          info = model_info(model_id)
+          info ? info[:supports_chat] : false
+        end
+
+        def supports_structured?(model_id)
+          info = model_info(model_id)
+          info ? info[:supports_structured] : false
+        end
+
+        def gguf_file_for(model_id)
+          info = model_info(model_id)
+          info ? info[:gguf_file] : nil
+        end
+
+        def tokenizer_for(model_id)
+          info = model_info(model_id)
+          info ? info[:tokenizer] : nil
+        end
+      end
+    end
+  end
+end

data/lib/ruby_llm/providers/red_candle/streaming.rb

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+
+module RubyLLM
+  module Providers
+    class RedCandle
+      # Streaming methods of the RedCandle integration
+      module Streaming
+        def stream(payload, &block)
+          if payload[:stream]
+            perform_streaming_completion!(payload, &block)
+          else
+            # Non-streaming fallback
+            result = perform_completion!(payload)
+            # Yield the complete result as a single chunk
+            chunk = {
+              content: result[:content],
+              role: result[:role],
+              finish_reason: result[:finish_reason]
+            }
+            block.call(chunk)
+          end
+        end
+
+        private
+
+        def stream_processor
+          # Red Candle handles streaming internally through blocks
+          # This method is here for compatibility with the base streaming interface
+          nil
+        end
+
+        def process_stream_response(response)
+          # Red Candle doesn't use HTTP responses
+          # Streaming is handled directly in perform_streaming_completion!
+          response
+        end
+      end
+    end
+  end
+end

data/lib/ruby_llm/providers/red_candle.rb

@@ -0,0 +1,90 @@
+# frozen_string_literal: true
+
+module RubyLLM
+  module Providers
+    # Red Candle provider for local LLM execution using the Candle Rust crate.
+    class RedCandle < Provider
+      include RedCandle::Chat
+      include RedCandle::Models
+      include RedCandle::Capabilities
+      include RedCandle::Streaming
+
+      def initialize(config)
+        ensure_red_candle_available!
+        super
+        @loaded_models = {} # Cache for loaded models
+        @device = determine_device(config)
+      end
+
+      def api_base
+        nil # Local execution, no API base needed
+      end
+
+      def headers
+        {} # No HTTP headers needed
+      end
+
+      class << self
+        def capabilities
+          RedCandle::Capabilities
+        end
+
+        def configuration_requirements
+          [] # No required config, device is optional
+        end
+
+        def local?
+          true
+        end
+
+        def supports_functions?(model_id = nil)
+          RedCandle::Capabilities.supports_functions?(model_id)
+        end
+
+        def models
+          # Return Red Candle models for registration
+          RedCandle::Models::SUPPORTED_MODELS.map do |model_data|
+            Model::Info.new(
+              id: model_data[:id],
+              name: model_data[:name],
+              provider: 'red_candle',
+              type: 'chat',
+              family: model_data[:family],
+              context_window: model_data[:context_window],
+              capabilities: %w[streaming structured_output],
+              modalities: { input: %w[text], output: %w[text] }
+            )
+          end
+        end
+      end
+
+      private
+
+      def ensure_red_candle_available!
+        require 'candle'
+      rescue LoadError
+        raise Error.new(nil, "Red Candle gem is not installed. Add 'gem \"red-candle\", \"~> 1.2.3\"' to your Gemfile.")
+      end
+
+      def determine_device(config)
+        if config.red_candle_device
+          case config.red_candle_device.to_s.downcase
+          when 'cpu'
+            ::Candle::Device.cpu
+          when 'cuda', 'gpu'
+            ::Candle::Device.cuda
+          when 'metal'
+            ::Candle::Device.metal
+          else
+            ::Candle::Device.best
+          end
+        else
+          ::Candle::Device.best
+        end
+      rescue StandardError => e
+        RubyLLM.logger.warn "Failed to initialize device: #{e.message}. Falling back to CPU."
+        ::Candle::Device.cpu
+      end
+    end
+  end
+end

data/lib/ruby_llm/railtie.rb

@@ -5,7 +5,7 @@ module RubyLLM
   class Railtie < Rails::Railtie
     initializer 'ruby_llm.inflections' do
       ActiveSupport::Inflector.inflections(:en) do |inflect|
-        inflect.acronym 'LLM'
+        inflect.acronym 'RubyLLM'
       end
     end
 

data/lib/ruby_llm/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RubyLLM
-  VERSION = '1.1.0'
+  VERSION = '1.2.0'
 end

data/lib/ruby_llm_community.rb

@@ -58,6 +58,10 @@ module RubyLLM
       Embedding.embed(...)
     end
 
+    def moderate(...)
+      Moderation.moderate(...)
+    end
+
     def paint(...)
       Image.paint(...)
     end
@@ -101,6 +105,34 @@ RubyLLM::Provider.register :perplexity, RubyLLM::Providers::Perplexity
 RubyLLM::Provider.register :vertexai, RubyLLM::Providers::VertexAI
 RubyLLM::Provider.register :xai, RubyLLM::Providers::XAI
 
+# Optional Red Candle provider - only available if gem is installed
+begin
+  require 'candle'
+  require 'ruby_llm/providers/red_candle'
+  RubyLLM::Provider.register :red_candle, RubyLLM::Providers::RedCandle
+
+  # Register Red Candle models with the global registry
+  RubyLLM::Providers::RedCandle.models.each do |model|
+    RubyLLM.models.instance_variable_get(:@models) << model
+  end
+rescue LoadError
+  # Red Candle is optional - provider won't be available if gem isn't installed
+end
+
+# Optional Red Candle provider - only available if gem is installed
+begin
+  require 'candle'
+  require 'ruby_llm/providers/red_candle'
+  RubyLLM::Provider.register :red_candle, RubyLLM::Providers::RedCandle
+
+  # Register Red Candle models with the global registry
+  RubyLLM::Providers::RedCandle.models.each do |model|
+    RubyLLM.models.instance_variable_get(:@models) << model
+  end
+rescue LoadError
+  # Red Candle is optional - provider won't be available if gem isn't installed
+end
+
 if defined?(Rails::Railtie)
   require 'ruby_llm/railtie'
   require 'ruby_llm/active_record/acts_as'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ruby_llm_community
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.2.0
 platform: ruby
 authors:
 - Paul Shippy
@@ -152,7 +152,9 @@ files:
 - lib/generators/ruby_llm/chat_ui/templates/views/models/_model.html.erb.tt
 - lib/generators/ruby_llm/chat_ui/templates/views/models/index.html.erb.tt
 - lib/generators/ruby_llm/chat_ui/templates/views/models/show.html.erb.tt
+- lib/generators/ruby_llm/generator_helpers.rb
 - lib/generators/ruby_llm/install/install_generator.rb
+- lib/generators/ruby_llm/install/templates/add_references_to_chats_tool_calls_and_messages_migration.rb.tt
 - lib/generators/ruby_llm/install/templates/chat_model.rb.tt
 - lib/generators/ruby_llm/install/templates/create_chats_migration.rb.tt
 - lib/generators/ruby_llm/install/templates/create_messages_migration.rb.tt
@@ -194,6 +196,7 @@ files:
 - lib/ruby_llm/models.json
 - lib/ruby_llm/models.rb
 - lib/ruby_llm/models_schema.json
+- lib/ruby_llm/moderation.rb
 - lib/ruby_llm/provider.rb
 - lib/ruby_llm/providers/anthropic.rb
 - lib/ruby_llm/providers/anthropic/capabilities.rb
@@ -247,6 +250,7 @@ files:
 - lib/ruby_llm/providers/openai/images.rb
 - lib/ruby_llm/providers/openai/media.rb
 - lib/ruby_llm/providers/openai/models.rb
+- lib/ruby_llm/providers/openai/moderation.rb
 - lib/ruby_llm/providers/openai/response.rb
 - lib/ruby_llm/providers/openai/response_media.rb
 - lib/ruby_llm/providers/openai/streaming.rb
@@ -258,6 +262,11 @@ files:
 - lib/ruby_llm/providers/perplexity/capabilities.rb
 - lib/ruby_llm/providers/perplexity/chat.rb
 - lib/ruby_llm/providers/perplexity/models.rb
+- lib/ruby_llm/providers/red_candle.rb
+- lib/ruby_llm/providers/red_candle/capabilities.rb
+- lib/ruby_llm/providers/red_candle/chat.rb
+- lib/ruby_llm/providers/red_candle/models.rb
+- lib/ruby_llm/providers/red_candle/streaming.rb
 - lib/ruby_llm/providers/vertexai.rb
 - lib/ruby_llm/providers/vertexai/chat.rb
 - lib/ruby_llm/providers/vertexai/embeddings.rb