tiktoken_ruby 0.0.6 → 0.0.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e011f7a82a6ee3d09405cd2c817d2ba9fe06e5a3bdde3ee622c9aefd9b1e8dd8
-  data.tar.gz: 892539805e10e5e10456956aa65b72e7ab4ececae56db2c49ccd11848cd0d2c2
+  metadata.gz: 347a10d045e27fca4cdfec03c4d2eac0150448b8f2125d5bcbcd1b92db83499a
+  data.tar.gz: de048e8320daa15b27ffa7ccdd9f7ec618cb2a3ad96fe2bedf71e6f780fc8b6f
 SHA512:
-  metadata.gz: 5accbfe97904fb1e9b6c5fa793a9e326bb25befaca6dbf5a2f8e6cfcad5f3c80c7dd1d0f66aaa95bed732943a2c0999654ffa2cf40891b2c9443f8909efb1dc6
-  data.tar.gz: 5e95a59d2876fb54e8a76e7d855c42d4e314be211f495dae5ef0bf4004cc44eeb0ea433a620e037232349a10d107ed25afafa704e1fffcddb4ce29219a199e87
+  metadata.gz: 7c587d4b18e777a0f7692aab857fec1fc3b3bcceceab158439197123786475c65d51f5356351bcf0c9c327b94e2ff15a83b2144c2db329aedea0456c1d763ff9
+  data.tar.gz: abfdeb836d81555effa5ef6647a77b360dae2b975bb3dc23a22c779f6dd82256630942ddfef01a837ff5195896fa4251925e87dec0d245dce1c8e83719a488f1

data/Cargo.lock

@@ -31,16 +31,16 @@ checksum = "a4a4ddaa51a5bc52a6948f74c06d20aaaddb71924eab79b8c97a8c556e942d6a"
 
 [[package]]
 name = "bindgen"
-version = "0.66.1"
+version = "0.69.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f2b84e06fc203107bfbad243f4aba2af864eb7db3b1cf46ea0a023b0b433d2a7"
+checksum = "a00dc851838a2120612785d195287475a3ac45514741da670b735818822129a0"
 dependencies = [
  "bitflags 2.4.0",
  "cexpr",
  "clang-sys",
+ "itertools",
  "lazy_static",
  "lazycell",
- "peeking_take_while",
  "proc-macro2",
  "quote",
  "regex",
@@ -114,6 +114,12 @@ dependencies = [
  "libloading",
 ]
 
+[[package]]
+name = "either"
+version = "1.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "11157ac094ffbdde99aa67b23417ebdd801842852b500e395a45a9c0aac03e4a"
+
 [[package]]
 name = "fancy-regex"
 version = "0.11.0"
@@ -130,6 +136,15 @@ version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
 
+[[package]]
+name = "itertools"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+dependencies = [
+ "either",
+]
+
 [[package]]
 name = "lazy_static"
 version = "1.4.0"
@@ -242,12 +257,6 @@ dependencies = [
  "windows-sys",
 ]
 
-[[package]]
-name = "peeking_take_while"
-version = "0.1.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "19b17cddbe7ec3f8bc800887bab5e717348c95ea2ca0b1bf0837fb964dc67099"
-
 [[package]]
 name = "proc-macro2"
 version = "1.0.66"
@@ -268,18 +277,18 @@ dependencies = [
 
 [[package]]
 name = "rb-sys"
-version = "0.9.81"
+version = "0.9.87"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a57240b308b155b09dce81e32829966a99f52d1088b45957e4283e526c5317a1"
+checksum = "225103e3d69bbfe8831f9fd0d2461335f3a9dd06aa6e88bcb6d6970383494d06"
 dependencies = [
  "rb-sys-build",
 ]
 
 [[package]]
 name = "rb-sys-build"
-version = "0.9.81"
+version = "0.9.87"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f24ce877a4c5d07f06f6aa6fec3ac95e4b357b9f73b0f5445d8cbb7266d410e8"
+checksum = "bacce8095a5167d5ede618bbd9353e9d9e2f32ddaf54be911106f0ee6baacf09"
 dependencies = [
  "bindgen",
  "lazy_static",

data/Gemfile

@@ -2,15 +2,11 @@
 
 source "https://rubygems.org"
 
-# Specify your gem's dependencies in tiktoken_ruby.gemspec
 gemspec
 
-gem "rake", "~> 13.0"
-
+gem "rake"
 gem "rake-compiler"
-
-gem "rspec", "~> 3.0"
-
-gem "standard", "~> 1.3"
-
-gem "yard-doctest", "~> 0.1.17"
+gem "rspec"
+gem "standard"
+gem "yard-doctest"
+gem "racc"

data/Gemfile.lock

@@ -1,64 +1,74 @@
 PATH
   remote: .
   specs:
-    tiktoken_ruby (0.0.6)
-      rb_sys (~> 0.9.68)
+    tiktoken_ruby (0.0.8)
+      rb_sys (>= 0.9.86)
 
 GEM
   remote: https://rubygems.org/
   specs:
     ast (2.4.2)
     diff-lcs (1.5.0)
-    json (2.6.3)
+    json (2.7.1)
     language_server-protocol (3.17.0.3)
-    minitest (5.18.0)
-    parallel (1.22.1)
-    parser (3.2.1.1)
+    lint_roller (1.1.0)
+    minitest (5.21.2)
+    parallel (1.24.0)
+    parser (3.3.0.4)
       ast (~> 2.4.1)
+      racc
+    racc (1.7.3)
     rainbow (3.1.1)
-    rake (13.0.6)
-    rake-compiler (1.2.1)
+    rake (13.1.0)
+    rake-compiler (1.2.5)
       rake
-    rb_sys (0.9.68)
-    regexp_parser (2.7.0)
-    rexml (3.2.5)
+    rb_sys (0.9.86)
+    regexp_parser (2.9.0)
+    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 (3.12.1)
+    rspec-core (3.12.2)
       rspec-support (~> 3.12.0)
-    rspec-expectations (3.12.2)
+    rspec-expectations (3.12.3)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.12.0)
-    rspec-mocks (3.12.4)
+    rspec-mocks (3.12.6)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.12.0)
-    rspec-support (3.12.0)
-    rubocop (1.48.1)
+    rspec-support (3.12.1)
+    rubocop (1.59.0)
       json (~> 2.3)
+      language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
-      parser (>= 3.2.0.0)
+      parser (>= 3.2.2.4)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
       rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.26.0, < 2.0)
+      rubocop-ast (>= 1.30.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.27.0)
+    rubocop-ast (1.30.0)
       parser (>= 3.2.1.0)
-    rubocop-performance (1.16.0)
-      rubocop (>= 1.7.0, < 2.0)
-      rubocop-ast (>= 0.4.0)
+    rubocop-performance (1.20.2)
+      rubocop (>= 1.48.1, < 2.0)
+      rubocop-ast (>= 1.30.0, < 2.0)
     ruby-progressbar (1.13.0)
-    standard (1.25.1)
+    standard (1.33.0)
       language_server-protocol (~> 3.17.0.2)
-      rubocop (= 1.48.1)
-      rubocop-performance (= 1.16.0)
-    unicode-display_width (2.4.2)
-    webrick (1.7.0)
-    yard (0.9.28)
-      webrick (~> 1.7.0)
+      lint_roller (~> 1.0)
+      rubocop (~> 1.59.0)
+      standard-custom (~> 1.0.0)
+      standard-performance (~> 1.3)
+    standard-custom (1.0.2)
+      lint_roller (~> 1.0)
+      rubocop (~> 1.50)
+    standard-performance (1.3.1)
+      lint_roller (~> 1.1)
+      rubocop-performance (~> 1.20.2)
+    unicode-display_width (2.5.0)
+    yard (0.9.34)
     yard-doctest (0.1.17)
       minitest
       yard
@@ -70,12 +80,13 @@ PLATFORMS
   x86_64-linux
 
 DEPENDENCIES
-  rake (~> 13.0)
+  racc
+  rake
   rake-compiler
-  rspec (~> 3.0)
-  standard (~> 1.3)
+  rspec
+  standard
   tiktoken_ruby!
-  yard-doctest (~> 0.1.17)
+  yard-doctest
 
 BUNDLED WITH
    2.4.6

data/README.md

@@ -1,8 +1,14 @@
 [![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. 
+This is a wrapper around it aimed primarily at enabling accurate counts of GPT model tokens used.
+
+## Request for maintainers
+
+I can't really put substantial time into maintaining this. Probably nothing more than a couple hours every few months. If you have experience maintaining ruby gems and would like to
+lend a hand please send me an email or reply to this [issue](https://github.com/IAPark/tiktoken_ruby/issues/26)
 
 ## Installation
 
@@ -15,17 +21,19 @@ If bundler is not being used to manage dependencies, install the gem by executin
     $ 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'
 
@@ -53,7 +61,6 @@ 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/lib/tiktoken_ruby/encoding.rb

@@ -1,6 +1,8 @@
 # frozen_string_literal: true
 
 class Tiktoken::Encoding
+  CACHE_MUTEX = Mutex.new
+
   attr_reader :name
 
   # This returns a new Tiktoken::Encoding instance for the requested encoding
@@ -15,8 +17,10 @@ class Tiktoken::Encoding
   # @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)
+    CACHE_MUTEX.synchronize do
+      @encodings ||= {}
+      @encodings[encoding.to_sym] ||= Tiktoken::Encoding.for_name(encoding)
+    end
   end
 
   # Encodes the text as a list of integer tokens. This encoding will encode special non text tokens

data/lib/tiktoken_ruby/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Tiktoken
-  VERSION = "0.0.6"
+  VERSION = "0.0.8"
 end

data/lib/tiktoken_ruby.rb

@@ -28,22 +28,22 @@ module Tiktoken
 
     # 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
+    # @return [Tiktoken::Encoding, nil] The encoding instance, or nil if no encoding is found
     # @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
+      if MODEL_TO_ENCODING_NAME.key?(model_name.to_sym)
+        return get_encoding(MODEL_TO_ENCODING_NAME[model_name.to_sym])
       end
 
-      encoding_name = MODEL_TO_ENCODING_NAME[model_name.to_sym]
-      return nil unless encoding_name
+      _prefix, encoding = MODEL_PREFIX_TO_ENCODING.find do |prefix, _encoding|
+        model_name.start_with?(prefix.to_s)
+      end
 
-      get_encoding(encoding_name)
+      if encoding
+        get_encoding(encoding)
+      end
     end
 
     # Lists all the encodings that are supported
@@ -67,12 +67,22 @@ module Tiktoken
       :cl100k_base
     ]
 
-    # taken from the python library here https://github.com/openai/tiktoken/blob/main/tiktoken/model.py#L13-L53
+    # taken from the python library here https://github.com/openai/tiktoken/blob/main/tiktoken/model.py
     # that is also MIT licensed but by OpenAI
     MODEL_TO_ENCODING_NAME = {
+      # chat
       "gpt-4": "cl100k_base",
       "gpt-3.5-turbo": "cl100k_base",
-      # text
+      "gpt-35-turbo": "cl100k_base",  # Azure deployment name
+      # base
+      "davinci-002": "cl100k_base",
+      "babbage-002": "cl100k_base",
+      # embeddings
+      "text-embedding-ada-002": "cl100k_base",
+      "text-embedding-3-small": "cl100k_base",
+      "text-embedding-3-large": "cl100k_base",
+      # DEPRECATED MODELS
+      # text (DEPRECATED)
       "text-davinci-003": "p50k_base",
       "text-davinci-002": "p50k_base",
       "text-davinci-001": "r50k_base",
@@ -83,19 +93,17 @@ module Tiktoken
       curie: "r50k_base",
       babbage: "r50k_base",
       ada: "r50k_base",
-      # code
+      # code (DEPRECATED)
       "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
+      # edit (DEPRECATED)
       "text-davinci-edit-001": "p50k_edit",
       "code-davinci-edit-001": "p50k_edit",
-      # embeddings
-      "text-embedding-ada-002": "cl100k_base",
-      # old embeddings
+      # old embeddings (DEPRECATED)
       "text-similarity-davinci-001": "r50k_base",
       "text-similarity-curie-001": "r50k_base",
       "text-similarity-babbage-001": "r50k_base",
@@ -105,10 +113,21 @@ module Tiktoken
       "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"
+      "code-search-ada-code-001": "r50k_base",
+      # open source
+      gpt2: "gpt2"
     }
 
-    # these are models that have a versioned models that are otherwise identical
-    PREFIX_MODELS = ["gpt-4", "gpt-3.5-turbo"]
+    MODEL_PREFIX_TO_ENCODING = {
+      # chat
+      "gpt-4-": "cl100k_base",  # e.g., gpt-4-0314, etc., plus gpt-4-32k
+      "gpt-3.5-turbo-": "cl100k_base",  # e.g, gpt-3.5-turbo-0301, -0401, etc.
+      "gpt-35-turbo-": "cl100k_base",  # Azure deployment name
+      # fine-tuned
+      "ft:gpt-4": "cl100k_base",
+      "ft:gpt-3.5-turbo": "cl100k_base",
+      "ft:davinci-002": "cl100k_base",
+      "ft:babbage-002": "cl100k_base"
+    }
   end
 end

data/tiktoken_ruby.gemspec

@@ -7,12 +7,10 @@ Gem::Specification.new do |spec|
   spec.version = Tiktoken::VERSION
   spec.authors = ["IAPark"]
   spec.email = ["isaac.a.park@gmail.com"]
-
   spec.summary = "Ruby wrapper for Tiktoken"
   spec.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."
-
   spec.homepage = "https://github.com/IAPark/tiktoken_ruby"
   spec.license = "MIT"
   spec.required_ruby_version = ">= 2.7.0"
@@ -22,11 +20,6 @@ Gem::Specification.new do |spec|
   spec.metadata["homepage_uri"] = spec.homepage
   spec.metadata["source_code_uri"] = "https://github.com/IAPark/tiktoken_ruby"
   spec.metadata["documentation_uri"] = "https://rubydoc.info/github/IAPark/tiktoken_ruby/main"
-
-  # spec.metadata["changelog_uri"] = "TODO: Put your gem's CHANGELOG.md URL here."
-
-  # 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(__dir__) do
     `git ls-files -z`.split("\x0").reject do |f|
       (f == __FILE__) || f.match(%r{\A(?:(?:bin|test|spec|features)/|\.(?:git|circleci)|appveyor)})
@@ -36,9 +29,5 @@ Gem::Specification.new do |spec|
   spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
   spec.extensions = ["ext/tiktoken_ruby/extconf.rb"]
-
-  spec.add_dependency "rb_sys", "~> 0.9.68"
-
-  # For more information and examples about making a new gem, check out our
-  # guide at: https://bundler.io/guides/creating_gem.html
+  spec.add_dependency "rb_sys", ">= 0.9.86"
 end

metadata

@@ -1,29 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: tiktoken_ruby
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.8
 platform: ruby
 authors:
 - IAPark
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-09-24 00:00:00.000000000 Z
+date: 2024-04-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.9.68
+        version: 0.9.86
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.9.68
+        version: 0.9.86
 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.