llm.rb 0.6.1 → 0.6.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a1f511ff8e5ea40a91c14f89d76a746e8ca96a866a7e99e2eb1c409d2cdebf74
-  data.tar.gz: 2d6b59d9fec4e9a38995571165b5aae96510f349d0011dd1de7e2c0776370279
+  metadata.gz: 0abd0e522f099e1e53a3b4d7d3e4648a7c42d2ce23e9c17b9e09f97803e1e31d
+  data.tar.gz: 2c7b8b38570b4cafb20c61e479f16bc9a7be3e81a651a189d6e15967da796fe3
 SHA512:
-  metadata.gz: fa1bedadae41e2c53fcbb0a8be37e158e5627a7e1f57aff0f34f49829a78386f342fc092222b50ab90e4b2e88603e5a5fd17912a99cccafb78f4cea23ac6b523
-  data.tar.gz: 8f78f02800ec4ecd829ebc2ecc459bdc7313bcae7c0d231a312e60a8f1b1c5aad7a912a0b7dafe6816180d7545edd5890d22c496fe53c556a326f93b3f0ce183
+  metadata.gz: b309e59522e4f80a78d6a34fdf5b7aa0f06ab14ad79e845b92f5ad87537aba07532bb5b6d24bbb6d13386b32a0235ee6fc0308c7fe27496bb95da2016a27dc02
+  data.tar.gz: 61e2ecd8a53d600977f8a97592b63ed978d2659ed49513508aea2e3ab66c7fe163790eec45dc2a58ccd8aa54fca6fcb89eeb58243861c3a3238e19d86a2a00c7

data/README.md

@@ -1,17 +1,17 @@
 ## About
 
-llm.rb is a zero-dependency Ruby toolkit for Large Language Models like
-OpenAI, Gemini, Anthropic, and more. It’s fast, clean, and composable –
-with full support for chat, tool calling, audio, images, files, and
-JSON Schema generation.
+llm.rb is a zero-dependency Ruby toolkit for Large Language Models that
+includes OpenAI, Gemini, Anthropic, Ollama, and LlamaCpp. It’s fast, simple
+and composable – with full support for chat, tool calling, audio, 
+images, files, and JSON Schema generation.
 
 ## Features
 
 #### General
-- ✅ Unified interface for OpenAI, Gemini, Anthropic, Ollama, and more
+- ✅ A single unified interface for multiple providers
 - 📦 Zero dependencies outside Ruby's standard library
-- 🔌 Model introspection and selection
 - 🚀 Optimized for performance and low memory usage
+- 🔌 Retrieve models dynamically for introspection and selection
 
 #### Chat, Agents
 - 🧠 Stateless and stateful chat via completions and responses API
@@ -46,6 +46,7 @@ llm = LLM.openai(key: "yourapikey")
 llm = LLM.gemini(key: "yourapikey")
 llm = LLM.anthropic(key: "yourapikey")
 llm = LLM.ollama(key: nil)
+llm = LLM.llamacpp(key: nil)
 llm = LLM.voyageai(key: "yourapikey")
 ```
 
@@ -144,9 +145,8 @@ composition of objects, the generation of a schema is delegated to another objec
 who is responsible for and an expert in the generation of JSON schemas. We will use
 the
 [llmrb/json-schema](https://github.com/llmrb/json-schema)
-library  for the sake of the examples - it is an optional dependency that is loaded
-on-demand. At least for the time being it is not necessary to install it separately.
-The interface is designed so you could drop in any other library in its place:
+library for the sake of the examples – the interface is designed so you 
+could drop in any other library in its place:
 
 ```ruby
 #!/usr/bin/env ruby
@@ -483,35 +483,9 @@ bot.chat "Hello #{model.id} :)"
 bot.messages.select(&:assistant?).each { print "[#{_1.role}] ", _1.content, "\n" }
 ```
 
-### Memory
+## Documentation
 
-#### Child process
-
-When it comes to the generation of audio, images, and video memory consumption
-can be a potential problem. There are a few strategies in place to deal with this,
-and one lesser known strategy is to let a child process handle the memory cost
-by delegating media generation to a child process.
-
-Once a child process exits, any memory it had used is freed immediately and
-the parent process can continue to have a small memory footprint. In a sense
-it is similar to being able to use malloc + free from Ruby. The following example
-demonstrates how that might look like in practice:
-
-```ruby
-#!/usr/bin/env ruby
-require "llm"
-
-llm = LLM.gemini(key: ENV["KEY"])
-fork do
-  %w[dog cat sheep goat capybara].each do |animal|
-    res = llm.images.create(prompt: "a #{animal} on a rocket to the moon")
-    IO.copy_stream res.images[0], "#{animal}.png"
-  end
-end
-Process.wait
-```
-
-## API reference
+### API
 
 The README tries to provide a high-level overview of the library. For everything
 else there's the API reference. It covers classes and methods that the README glances
@@ -519,31 +493,11 @@ over or doesn't cover at all. The API reference is available at
 [0x1eef.github.io/x/llm.rb](https://0x1eef.github.io/x/llm.rb).
 
 
-### See also
-
-#### Gemini
-
-* [LLM::Gemini](https://0x1eef.github.io/x/llm.rb/LLM/Gemini.html)
-* [LLM::Gemini::Images](https://0x1eef.github.io/x/llm.rb/LLM/Gemini/Images.html)
-* [LLM::Gemini::Audio](https://0x1eef.github.io/x/llm.rb/LLM/Gemini/Audio.html)
-
-#### OpenAI
+### Guides
 
-* [LLM::OpenAI](https://0x1eef.github.io/x/llm.rb/LLM/OpenAI.html)
-* [LLM::OpenAI::Images](https://0x1eef.github.io/x/llm.rb/LLM/OpenAI/Images.html)
-* [LLM::OpenAI::Audio](https://0x1eef.github.io/x/llm.rb/LLM/OpenAI/Audio.html)
-
-#### Anthropic
-* [LLM::Anthropic](https://0x1eef.github.io/x/llm.rb/LLM/Anthropic.html)
-
-#### Ollama
-* [LLM::Ollama](https://0x1eef.github.io/x/llm.rb/LLM/Ollama.html)
-
-## Install
-
-llm.rb can be installed via rubygems.org:
-
-	gem install llm.rb
+The [docs/](docs/) directory contains some additional documentation that
+didn't quite make it into the README. It covers the design guidelines that
+the library follows, and some strategies for memory management.
 
 ## See also
 
@@ -554,24 +508,11 @@ llm.rb and serves as a demonstration of the library's capabilities. The
 [demo](https://github.com/llmrb/llm-shell#demos) section has a number of GIF
 previews might be especially interesting!
 
+## Install
 
-## Philosophy
-
-llm.rb provides a clean, dependency-free interface to Large Language Models,
-treating Ruby itself — not Rails or any specific framework — as the primary platform.
-It avoids hidden magic, complex metaprogramming, and heavy DSLs. It is intentionally
-simple and won't compromise on being a simple library, even if that means saying no to
-certain features.
-
-Instead, it embraces a general-purpose, object-oriented design that prioritizes
-explicitness, composability, and clarity. Code should be easy to follow, test, and adapt.
-For that reason we favor small, cooperating objects over deeply nested blocks — a pattern
-that often emerges in DSL-heavy libraries.
+llm.rb can be installed via rubygems.org:
 
-Each part of llm.rb is designed to be conscious of memory, ready for production, and free
-from global state or non-standard dependencies. While inspired by ideas from other ecosystems
-(especially Python) it is not a port of any other library — it is a Ruby library written
-by Rubyists who value borrowing good ideas from other languages and ecosystems.
+	gem install llm.rb
 
 ## License
 

data/lib/json/schema/boolean.rb

@@ -5,7 +5,7 @@ class JSON::Schema
   # The {JSON::Schema::Boolean JSON::Schema::Boolean} class represents a
   # boolean value in a JSON schema. It is a subclass of
   # {JSON::Schema::Leaf JSON::Schema::Leaf}.
-  class Booelean < Leaf
+  class Boolean < Leaf
     def to_h
       super.merge!({type: "boolean"})
     end

data/lib/llm/function.rb

@@ -53,7 +53,6 @@ class LLM::Function
 
   ##
   # Call the function
-  # @param [Array] args The arguments to pass to the function
   # @return [Object] The result of the function call
   def call
     Return.new id, @runner.call(arguments)

data/lib/llm/providers/anthropic/format.rb

@@ -18,6 +18,9 @@ class LLM::Anthropic
 
     private
 
+    ##
+    # @param [Hash] params
+    # @return [Hash]
     def format_tools(params)
       return {} unless params and params[:tools]&.any?
       tools = params[:tools]

data/lib/llm/providers/gemini/format.rb

@@ -19,8 +19,7 @@ class LLM::Gemini
     private
 
     ##
-    # @param [JSON::Schema] schema
-    #  The schema to format
+    # @param [Hash] params
     # @return [Hash]
     def format_schema(params)
       return {} unless params and params[:schema]
@@ -29,8 +28,7 @@ class LLM::Gemini
     end
 
     ##
-    # @param [Array<LLM::Function>] tools
-    #  The tools to format
+    # @param [Hash] params
     # @return [Hash]
     def format_tools(params)
       return {} unless params and params[:tools]&.any?

data/lib/llm/providers/llamacpp.rb

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+module LLM
+  ##
+  # The LlamaCpp class implements a provider for
+  # [llama.cpp](https://github.com/ggml-org/llama.cpp)
+  # through the OpenAI-compatible API provided by the
+  # llama-server binary.
+  class LlamaCpp < OpenAI
+    ##
+    # @param (see LLM::Provider#initialize)
+    # @return [LLM::LlamaCpp]
+    def initialize(host: "localhost", port: 8080, ssl: false, **)
+      super
+    end
+
+    ##
+    # @raise [NotImplementedError]
+    def files
+      raise NotImplementedError
+    end
+
+    ##
+    # @raise [NotImplementedError]
+    def images
+      raise NotImplementedError
+    end
+
+    ##
+    # @raise [NotImplementedError]
+    def audio
+      raise NotImplementedError
+    end
+
+    ##
+    # Returns the default model for chat completions
+    # @see https://ollama.com/library llama3.2
+    # @return [String]
+    def default_model
+      "llama3.2"
+    end
+  end
+end

data/lib/llm/providers/ollama/format.rb

@@ -19,8 +19,7 @@ class LLM::Ollama
     private
 
     ##
-    # @param [Array<LLM::Function>] tools
-    #  The tools to format
+    # @param [Hash] params
     # @return [Hash]
     def format_tools(params)
       return {} unless params and params[:tools]&.any?

data/lib/llm/providers/openai/format.rb

@@ -26,8 +26,7 @@ class LLM::OpenAI
     private
 
     ##
-    # @param [JSON::Schema] schema
-    #  The schema to format
+    # @param [Hash] params
     # @return [Hash]
     def format_schema(params)
       return {} unless params and params[:schema]
@@ -41,8 +40,7 @@ class LLM::OpenAI
     end
 
     ##
-    # @param [Array<LLM::Function>] tools
-    #  The tools to format
+    # @param [Hash] params
     # @return [Hash]
     def format_tools(params)
       return {} unless params and params[:tools]&.any?

data/lib/llm/response/completion.rb

@@ -15,6 +15,7 @@ module LLM
     def choices
       parsed[:choices]
     end
+    alias_method :messages, :choices
 
     ##
     # @return [Integer]

data/lib/llm/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module LLM
-  VERSION = "0.6.1"
+  VERSION = "0.6.2"
 end

data/lib/llm.rb

@@ -21,7 +21,7 @@ module LLM
   module_function
 
   ##
-  # @param secret (see LLM::Anthropic#initialize)
+  # @param (see LLM::Provider#initialize)
   # @return (see LLM::Anthropic#initialize)
   def anthropic(**)
     require_relative "llm/providers/anthropic" unless defined?(LLM::Anthropic)
@@ -30,7 +30,7 @@ module LLM
   end
 
   ##
-  # @param secret (see LLM::VoyageAI#initialize)
+  # @param (see LLM::Provider#initialize)
   # @return (see LLM::VoyageAI#initialize)
   def voyageai(**)
     require_relative "llm/providers/voyageai" unless defined?(LLM::VoyageAI)
@@ -38,7 +38,7 @@ module LLM
   end
 
   ##
-  # @param secret (see LLM::Gemini#initialize)
+  # @param (see LLM::Provider#initialize)
   # @return (see LLM::Gemini#initialize)
   def gemini(**)
     require_relative "llm/providers/gemini" unless defined?(LLM::Gemini)
@@ -46,7 +46,7 @@ module LLM
   end
 
   ##
-  # @param host (see LLM::Ollama#initialize)
+  # @param (see LLM::Provider#initialize)
   # @return (see LLM::Ollama#initialize)
   def ollama(key: nil, **)
     require_relative "llm/providers/ollama" unless defined?(LLM::Ollama)
@@ -54,7 +54,16 @@ module LLM
   end
 
   ##
-  # @param secret (see LLM::OpenAI#initialize)
+  # @param key (see LLM::Provider#initialize)
+  # @return (see LLM::LlamaCpp#initialize)
+  def llamacpp(key: nil, **)
+    require_relative "llm/providers/openai" unless defined?(LLM::OpenAI)
+    require_relative "llm/providers/llamacpp" unless defined?(LLM::LlamaCpp)
+    LLM::LlamaCpp.new(key:, **)
+  end
+
+  ##
+  # @param key (see LLM::Provider#initialize)
   # @return (see LLM::OpenAI#initialize)
   def openai(**)
     require_relative "llm/providers/openai" unless defined?(LLM::OpenAI)
@@ -64,15 +73,15 @@ module LLM
   ##
   # Define a function
   # @example
-  # LLM.function(:system) do |fn|
-  #   fn.description "Run system command"
-  #   fn.params do |schema|
-  #     schema.object(command: schema.string.required)
-  #   end
-  #   fn.define do |params|
-  #     system(params.command)
+  #   LLM.function(:system) do |fn|
+  #     fn.description "Run system command"
+  #     fn.params do |schema|
+  #       schema.object(command: schema.string.required)
+  #     end
+  #     fn.define do |params|
+  #       system(params.command)
+  #     end
   #   end
-  # end
   # @param [Symbol] name The name of the function
   # @param [Proc] b The block to define the function
   # @return [LLM::Function] The function object

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: llm.rb
 version: !ruby/object:Gem::Version
-  version: 0.6.1
+  version: 0.6.2
 platform: ruby
 authors:
 - Antar Azri
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-05-06 00:00:00.000000000 Z
+date: 2025-05-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: webmock
@@ -202,6 +202,7 @@ files:
 - lib/llm/providers/gemini/models.rb
 - lib/llm/providers/gemini/response_parser.rb
 - lib/llm/providers/gemini/response_parser/completion_parser.rb
+- lib/llm/providers/llamacpp.rb
 - lib/llm/providers/ollama.rb
 - lib/llm/providers/ollama/error_handler.rb
 - lib/llm/providers/ollama/format.rb