rz_tiktoken_ruby 0.0.6-aarch64-linux

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 419e4958da9b1c3c6156ffd4cd355e5949ec0faa2844483ee2262546757cb6f2
+  data.tar.gz: 8a76618eef051f71d682e6cc6c505ca148df898438380f216e8697c902038f39
+SHA512:
+  metadata.gz: 1ec9045bdd82e403987954303973f5ab07edbd3c3f55dd283596587bf77e27e84928043ace13fdead621caf40b8c25cd6d11f77e35be0410829319aad22998bd
+  data.tar.gz: 4fa079a17ddb9244fd232c0b9b394d223f308cf872c6c4457767bf0a6cb11b1ba614e2a429966ebf9f6fe2ad5fa638fbf3cb5eb6d2372e09fe18377c10e7c12f

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.standard.yml

@@ -0,0 +1,3 @@
+# For available configuration options, see:
+#   https://github.com/testdouble/standard
+ruby_version: 2.6

data/Gemfile

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in tiktoken_ruby.gemspec
+gemspec
+
+gem "rake", "~> 13.0"
+
+gem "rake-compiler"
+
+gem "rspec", "~> 3.0"
+
+gem "standard", "~> 1.3"
+
+gem "yard-doctest", "~> 0.1.17"

data/Gemfile.lock

@@ -0,0 +1,93 @@
+PATH
+  remote: .
+  specs:
+    rz_tiktoken_ruby (0.0.6)
+      rb_sys (~> 0.9.81)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    ast (2.4.2)
+    base64 (0.1.1)
+    diff-lcs (1.5.0)
+    json (2.6.3)
+    language_server-protocol (3.17.0.3)
+    lint_roller (1.1.0)
+    minitest (5.19.0)
+    parallel (1.23.0)
+    parser (3.2.2.3)
+      ast (~> 2.4.1)
+      racc
+    racc (1.7.1)
+    rainbow (3.1.1)
+    rake (13.0.6)
+    rake-compiler (1.2.5)
+      rake
+    rb_sys (0.9.81)
+    regexp_parser (2.8.1)
+    rexml (3.2.6)
+    rspec (3.12.0)
+      rspec-core (~> 3.12.0)
+      rspec-expectations (~> 3.12.0)
+      rspec-mocks (~> 3.12.0)
+    rspec-core (3.12.2)
+      rspec-support (~> 3.12.0)
+    rspec-expectations (3.12.3)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.12.0)
+    rspec-mocks (3.12.6)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.12.0)
+    rspec-support (3.12.1)
+    rubocop (1.56.1)
+      base64 (~> 0.1.1)
+      json (~> 2.3)
+      language_server-protocol (>= 3.17.0)
+      parallel (~> 1.10)
+      parser (>= 3.2.2.3)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 1.8, < 3.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.28.1, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 3.0)
+    rubocop-ast (1.29.0)
+      parser (>= 3.2.1.0)
+    rubocop-performance (1.19.0)
+      rubocop (>= 1.7.0, < 2.0)
+      rubocop-ast (>= 0.4.0)
+    ruby-progressbar (1.13.0)
+    standard (1.31.0)
+      language_server-protocol (~> 3.17.0.2)
+      lint_roller (~> 1.0)
+      rubocop (~> 1.56.0)
+      standard-custom (~> 1.0.0)
+      standard-performance (~> 1.2)
+    standard-custom (1.0.2)
+      lint_roller (~> 1.0)
+      rubocop (~> 1.50)
+    standard-performance (1.2.0)
+      lint_roller (~> 1.1)
+      rubocop-performance (~> 1.19.0)
+    unicode-display_width (2.4.2)
+    yard (0.9.34)
+    yard-doctest (0.1.17)
+      minitest
+      yard
+
+PLATFORMS
+  arm64-darwin-22
+  ruby
+  x86_64-darwin-22
+  x86_64-linux
+
+DEPENDENCIES
+  rake (~> 13.0)
+  rake-compiler
+  rspec (~> 3.0)
+  rz_tiktoken_ruby!
+  standard (~> 1.3)
+  yard-doctest (~> 0.1.17)
+
+BUNDLED WITH
+   2.4.6

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2023 IAPark
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,59 @@
+[![Gem Version](https://badge.fury.io/rb/tiktoken_ruby.svg)](https://badge.fury.io/rb/tiktoken_ruby)
+# tiktoken_ruby
+
+[Tiktoken](https://github.com/openai/tiktoken) is BPE tokenizer from OpenAI used with their GPT models.
+This is a wrapper around it aimed primarily at enabling accurate counts of GPT model tokens used. 
+
+## Installation
+
+Install the gem and add to the application's Gemfile by executing:
+
+    $ bundle add tiktoken_ruby
+
+If bundler is not being used to manage dependencies, install the gem by executing:
+
+    $ gem install tiktoken_ruby
+
+## Usage
+Usage should be very similar to the python library. Here's a simple example
+
+Encode and decode text
+```ruby
+require 'tiktoken_ruby'
+
+enc = Tiktoken.get_encoding("cl100k_base")
+enc.decode(enc.encode("hello world")) #=> "hello world"
+```
+
+Encoders can also be retrieved by model name
+```ruby
+require 'tiktoken_ruby'
+
+enc = Tiktoken.encoding_for_model("gpt-4")
+enc.encode("hello world").length #=> 2
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/iapark/tiktoken_ruby.
+
+To get started with development:
+
+```sh
+git clone https://github.com/IAPark/tiktoken_ruby.git
+cd tiktoken_ruby
+bundle install
+bundle exec rake compile
+bundle exec rake spec
+```
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+require "standard/rake"
+require "rake/extensiontask"
+require "rb_sys/extensiontask"
+
+GEMSPEC = Gem::Specification.load("tiktoken_ruby.gemspec")
+
+RbSys::ExtensionTask.new("tiktoken_ruby", GEMSPEC) do |ext|
+  ext.lib_dir = "lib/tiktoken_ruby"
+end
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :native, [:platform] do |_t, platform:|
+  sh "bundle", "exec", "rb-sys-dock", "--platform", platform, "--build"
+end
+
+task build: :compile
+
+task default: %i[compile spec standard]

data/doctest_helper.rb

@@ -0,0 +1 @@
+require "lib/tiktoken_ruby"

data/lib/tiktoken_ruby/encoding.rb

@@ -0,0 +1,52 @@
+# frozen_string_literal: true
+
+class Tiktoken::Encoding
+  attr_reader :name
+
+  # This returns a new Tiktoken::Encoding instance for the requested encoding
+  # @param encoding [Symbol] The name of the encoding to load
+  # @return [Tiktoken::Encoding] The encoding instance
+  def self.for_name(encoding)
+    Tiktoken::Encoding.new(Tiktoken::BpeFactory.send(encoding.to_sym), encoding.to_sym)
+  end
+
+  # This returns a Tiktoken::Encoding instance for the requested encoding
+  # It will reuse an existing encoding if it's already been loaded
+  # @param encoding [Symbol] The name of the encoding to load
+  # @return [Tiktoken::Encoding] The encoding instance
+  def self.for_name_cached(encoding)
+    @encodings ||= {}
+    @encodings[encoding.to_sym] ||= Tiktoken::Encoding.for_name(encoding)
+  end
+
+  # Encodes the text as a list of integer tokens. This encoding will encode special non text tokens
+  # basically it's unescaped
+  # @param text [String] The text to encode
+  # @return [Array<Integer>] The encoded tokens
+  def encode_ordinary(text)
+    @ext_base_bpe.encode_ordinary(text)
+  end
+
+  # Encodes the text as a list of integer tokens. This encoding will treat special non text tokens
+  # as text unless they're in the allowed_special array. It's basically like the text was escaped
+  # @param text [String] The text to encode
+  # @param allowed_special [Array<String>] An array of special tokens to allow
+  # @return [Array<Integer>] The encoded tokens
+  def encode(text, allowed_special: [])
+    @ext_base_bpe.encode(text, allowed_special)
+  end
+
+  # Decodes the tokens back into text
+  # @param tokens [Array<Integer>] The tokens to decode
+  # @return [String] The decoded text
+  def decode(tokens)
+    @ext_base_bpe.decode(tokens)
+  end
+
+  private
+
+  def initialize(ext_base_bpe, name)
+    @ext_base_bpe = ext_base_bpe
+    @name = name
+  end
+end

data/lib/tiktoken_ruby/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module Tiktoken
+  VERSION = "0.0.6"
+end

data/lib/tiktoken_ruby.rb

@@ -0,0 +1,114 @@
+# frozen_string_literal: true
+
+require_relative "tiktoken_ruby/version"
+require_relative "tiktoken_ruby/encoding"
+
+begin
+  RUBY_VERSION =~ /(\d+\.\d+)/
+  require_relative "tiktoken_ruby/#{$1}/tiktoken_ruby"
+rescue LoadError
+  require_relative "tiktoken_ruby/tiktoken_ruby"
+end
+
+module Tiktoken
+  class << self
+    # Returns an encoding by name. If the encoding is not already loaded it will be loaded, but otherwise
+    # it will reuse the instance of that type that was previous loaded
+    # @param name [Symbol|String] The name of the encoding to load
+    # @return [Tiktoken::Encoding] The encoding instance
+    # @example Encode and decode text
+    #   enc = Tiktoken.get_encoding("cl100k_base")
+    #   enc.decode(enc.encode("hello world")) #=> "hello world"
+    def get_encoding(name)
+      name = name.to_sym
+      return nil unless SUPPORTED_ENCODINGS.include?(name)
+
+      Tiktoken::Encoding.for_name_cached(name)
+    end
+
+    # Gets the encoding for an OpenAI model
+    # @param model_name [Symbol|String] The name of the model to get the encoding for
+    # @return [Tiktoken::Encoding] The encoding instance
+    # @example Count tokens for text
+    #   enc = Tiktoken.encoding_for_model("gpt-4")
+    #   enc.encode("hello world").length #=> 2
+    def encoding_for_model(model_name)
+      PREFIX_MODELS.each do |prefix|
+        if model_name.to_s.start_with?("#{prefix}-")
+          model_name = prefix
+          break
+        end
+      end
+
+      encoding_name = MODEL_TO_ENCODING_NAME[model_name.to_sym]
+      return nil unless encoding_name
+
+      get_encoding(encoding_name)
+    end
+
+    # Lists all the encodings that are supported
+    # @return [Array<Symbol>] The list of supported encodings
+    def list_encoding_names
+      SUPPORTED_ENCODINGS
+    end
+
+    # Lists all the models that are supported
+    # @return [Array<Symbol>] The list of supported models
+    def list_model_names
+      MODEL_TO_ENCODING_NAME.keys
+    end
+
+    private
+
+    SUPPORTED_ENCODINGS = [
+      :r50k_base,
+      :p50k_base,
+      :p50k_edit,
+      :cl100k_base
+    ]
+
+    # taken from the python library here https://github.com/openai/tiktoken/blob/main/tiktoken/model.py#L13-L53
+    # that is also MIT licensed but by OpenAI
+    MODEL_TO_ENCODING_NAME = {
+      "gpt-4": "cl100k_base",
+      "gpt-3.5-turbo": "cl100k_base",
+      # text
+      "text-davinci-003": "p50k_base",
+      "text-davinci-002": "p50k_base",
+      "text-davinci-001": "r50k_base",
+      "text-curie-001": "r50k_base",
+      "text-babbage-001": "r50k_base",
+      "text-ada-001": "r50k_base",
+      davinci: "r50k_base",
+      curie: "r50k_base",
+      babbage: "r50k_base",
+      ada: "r50k_base",
+      # code
+      "code-davinci-002": "p50k_base",
+      "code-davinci-001": "p50k_base",
+      "code-cushman-002": "p50k_base",
+      "code-cushman-001": "p50k_base",
+      "davinci-codex": "p50k_base",
+      "cushman-codex": "p50k_base",
+      # edit
+      "text-davinci-edit-001": "p50k_edit",
+      "code-davinci-edit-001": "p50k_edit",
+      # embeddings
+      "text-embedding-ada-002": "cl100k_base",
+      # old embeddings
+      "text-similarity-davinci-001": "r50k_base",
+      "text-similarity-curie-001": "r50k_base",
+      "text-similarity-babbage-001": "r50k_base",
+      "text-similarity-ada-001": "r50k_base",
+      "text-search-davinci-doc-001": "r50k_base",
+      "text-search-curie-doc-001": "r50k_base",
+      "text-search-babbage-doc-001": "r50k_base",
+      "text-search-ada-doc-001": "r50k_base",
+      "code-search-babbage-code-001": "r50k_base",
+      "code-search-ada-code-001": "r50k_base"
+    }
+
+    # these are models that have a versioned models that are otherwise identical
+    PREFIX_MODELS = ["gpt-4", "gpt-3.5-turbo"]
+  end
+end

data/sig/tiktoken_ruby.rbs

@@ -0,0 +1,4 @@
+module TiktokenRuby
+  VERSION: String
+  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+end

metadata

@@ -0,0 +1,71 @@
+--- !ruby/object:Gem::Specification
+name: rz_tiktoken_ruby
+version: !ruby/object:Gem::Version
+  version: 0.0.6
+platform: aarch64-linux
+authors:
+- IAPark
+- judy
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2023-08-24 00:00:00.000000000 Z
+dependencies: []
+description: |
+  An unofficial Ruby wrapper for Tiktoken, a BPE tokenizer written by and used by OpenAI. It
+  can be used to count the number of tokens in text before sending it to OpenAI APIs. This
+  is a fork of tiktoken_ruby by IAPark, which has been cross-compiled for multiple platforms.
+  This way compilation with Rust extensions doesn't need to happen wherever you are deploying it.
+email:
+- isaac.a.park@gmail.com
+- clinton@judy.io
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rspec"
+- ".standard.yml"
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- doctest_helper.rb
+- lib/tiktoken_ruby.rb
+- lib/tiktoken_ruby/3.0/tiktoken_ruby.so
+- lib/tiktoken_ruby/3.1/tiktoken_ruby.so
+- lib/tiktoken_ruby/3.2/tiktoken_ruby.so
+- lib/tiktoken_ruby/encoding.rb
+- lib/tiktoken_ruby/version.rb
+- sig/tiktoken_ruby.rbs
+homepage: https://github.com/retailzipline/tiktoken_ruby
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/retailzipline/tiktoken_ruby
+  source_code_uri: https://github.com/retailzipline/tiktoken_ruby
+  documentation_uri: https://rubydoc.info/github/IAPark/tiktoken_ruby/main
+  allowed_push_host: https://rubygems.org
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '3.0'
+  - - "<"
+    - !ruby/object:Gem::Version
+      version: 3.3.dev
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.1.0
+requirements: []
+rubygems_version: 3.4.4
+signing_key: 
+specification_version: 4
+summary: Ruby wrapper for Tiktoken
+test_files: []