Tiktoken 1.1.2

.NET 6.0 This package targets .NET 6.0. The package is compatible with this framework or higher. .NET Standard 2.0 This package targets .NET Standard 2.0. The package is compatible with this framework or higher. .NET Framework 4.6.1 This package targets .NET Framework 4.6.1. The package is compatible with this framework or higher.
There is a newer version of this package available.
See the version list below for details. 
dotnet add package Tiktoken --version 1.1.2
NuGet\Install-Package Tiktoken -Version 1.1.2
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package. 
<PackageReference Include="Tiktoken" Version="1.1.2" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
paket add Tiktoken --version 1.1.2
#r "nuget: Tiktoken, 1.1.2"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package. 
// Install Tiktoken as a Cake Addin
#addin nuget:?package=Tiktoken&version=1.1.2

// Install Tiktoken as a Cake Tool
#tool nuget:?package=Tiktoken&version=1.1.2

Tiktoken

Nuget package dotnet License: MIT Discord

This implementation aims for maximum performance, especially in the token count operation.
There's also a benchmark console app here for easy tracking of this.
We will be happy to accept any PR.

Implemented encodings

  • cl100k_base
  • r50k_base
  • p50k_base
  • p50k_edit

Usage

var encoding = Tiktoken.Encoding.ForModel("gpt-4");
var tokens = encoding.Encode("hello world"); // [15339, 1917]
var text = encoding.Decode(tokens); // hello world
var numberOfTokens = encoding.CountTokens(text); // 2
var stringTokens = encoding.Explore(text); // ["hello", " world"]

var encoding = Tiktoken.Encoding.Get(Encodings.P50KBase);
var tokens = encoding.Encode("hello world"); // [31373, 995]
var text = encoding.Decode(tokens); // hello world

Benchmarks

You can view the reports for each version here


BenchmarkDotNet v0.13.7, macOS Ventura 13.5.1 (22G90) [Darwin 22.6.0]
Apple M1 Pro, 1 CPU, 10 logical and 10 physical cores
.NET SDK 7.0.400
  [Host]     : .NET 7.0.10 (7.0.1023.36312), Arm64 RyuJIT AdvSIMD
  DefaultJob : .NET 7.0.10 (7.0.1023.36312), Arm64 RyuJIT AdvSIMD
Method Categories Data Mean Ratio Gen0 Gen1 Allocated Alloc Ratio
SharpTokenV1_2_8_ CountTokens 1. (...)57. [19866] 1,450,007.0 ns 1.00 292.9688 146.4844 1846187 B 1.00
TiktokenSharpV1_0_6_ CountTokens 1. (...)57. [19866] 977,818.9 ns 0.67 250.0000 125.0000 1571155 B 0.85
TokenizerLibV1_3_2_ CountTokens 1. (...)57. [19866] 854,357.2 ns 0.59 246.0938 85.9375 1547673 B 0.84
Tiktoken_ CountTokens 1. (...)57. [19866] 355,029.1 ns 0.24 49.3164 - 309449 B 0.17
SharpTokenV1_2_8_ CountTokens Hello, World! 1,722.2 ns 1.00 0.5264 - 3304 B 1.00
TiktokenSharpV1_0_6_ CountTokens Hello, World! 6,291.2 ns 3.65 2.1820 0.0305 13728 B 4.15
TokenizerLibV1_3_2_ CountTokens Hello, World! 604.0 ns 0.35 0.2356 - 1480 B 0.45
Tiktoken_ CountTokens Hello, World! 247.0 ns 0.14 0.0420 - 264 B 0.08
SharpTokenV1_2_8_ CountTokens King(...)edy. [275] 15,377.1 ns 1.00 4.1199 0.1526 26008 B 1.00
TiktokenSharpV1_0_6_ CountTokens King(...)edy. [275] 14,758.1 ns 0.96 5.1117 0.1526 32096 B 1.23
TokenizerLibV1_3_2_ CountTokens King(...)edy. [275] 8,366.9 ns 0.54 3.0823 0.1373 19344 B 0.74
Tiktoken_ CountTokens King(...)edy. [275] 3,838.6 ns 0.25 0.6409 - 4032 B 0.16
SharpTokenV1_2_8_Encode Encode 1. (...)57. [19866] 1,393,026.6 ns 1.00 292.9688 146.4844 1846187 B 1.00
TiktokenSharpV1_0_6_Encode Encode 1. (...)57. [19866] 1,246,776.8 ns 0.90 250.0000 125.0000 1571155 B 0.85
TokenizerLibV1_3_2_Encode Encode 1. (...)57. [19866] 852,519.6 ns 0.61 246.0938 85.9375 1547673 B 0.84
Tiktoken_Encode Encode 1. (...)57. [19866] 378,546.7 ns 0.27 59.5703 2.4414 375665 B 0.20
SharpTokenV1_2_8_Encode Encode Hello, World! 1,719.3 ns 1.00 0.5264 - 3304 B 1.00
TiktokenSharpV1_0_6_Encode Encode Hello, World! 6,293.3 ns 3.66 2.1820 0.0305 13728 B 4.15
TokenizerLibV1_3_2_Encode Encode Hello, World! 607.6 ns 0.35 0.2356 - 1480 B 0.45
Tiktoken_Encode Encode Hello, World! 320.6 ns 0.19 0.1135 - 712 B 0.22
SharpTokenV1_2_8_Encode Encode King(...)edy. [275] 15,444.0 ns 1.00 4.1199 0.1526 26008 B 1.00
TiktokenSharpV1_0_6_Encode Encode King(...)edy. [275] 14,704.0 ns 0.95 5.1117 0.1526 32096 B 1.23
TokenizerLibV1_3_2_Encode Encode King(...)edy. [275] 8,556.8 ns 0.55 3.0823 0.1373 19344 B 0.74
Tiktoken_Encode Encode King(...)edy. [275] 4,136.4 ns 0.27 0.8011 - 5056 B 0.19

Support

Priority place for bugs: https://github.com/tryAGI/LangChain/issues
Priority place for ideas and general questions: https://github.com/tryAGI/LangChain/discussions
Discord: https://discord.gg/Ca2xhfBf3v

Product Compatible and additional computed target framework versions.
.NET net5.0 was computed.  net5.0-windows was computed.  net6.0 is compatible.  net6.0-android was computed.  net6.0-ios was computed.  net6.0-maccatalyst was computed.  net6.0-macos was computed.  net6.0-tvos was computed.  net6.0-windows was computed.  net7.0 is compatible.  net7.0-android was computed.  net7.0-ios was computed.  net7.0-maccatalyst was computed.  net7.0-macos was computed.  net7.0-tvos was computed.  net7.0-windows was computed.  net8.0 was computed.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed. 
.NET Core netcoreapp2.0 was computed.  netcoreapp2.1 was computed.  netcoreapp2.2 was computed.  netcoreapp3.0 was computed.  netcoreapp3.1 was computed. 
.NET Standard netstandard2.0 is compatible.  netstandard2.1 is compatible. 
.NET Framework net461 is compatible.  net462 was computed.  net463 was computed.  net47 was computed.  net471 was computed.  net472 was computed.  net48 was computed.  net481 was computed. 
MonoAndroid monoandroid was computed. 
MonoMac monomac was computed. 
MonoTouch monotouch was computed. 
Tizen tizen40 was computed.  tizen60 was computed. 
Xamarin.iOS xamarinios was computed. 
Xamarin.Mac xamarinmac was computed. 
Xamarin.TVOS xamarintvos was computed. 
Xamarin.WatchOS xamarinwatchos was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

  • .NETFramework 4.6.1

  • .NETStandard 2.0

    • No dependencies.

  • .NETStandard 2.1

    • No dependencies.

  • net6.0

    • No dependencies.

  • net7.0

    • No dependencies.

NuGet packages (11)

Showing the top 5 NuGet packages that depend on Tiktoken:

Package Downloads
tryAGI.OpenAI The ID prefix of this package has been reserved for one of the owners of this package by NuGet.org.

Generated C# SDK based on official OpenAI OpenAPI specification. Includes C# Source Generator which allows you to define functions natively through a C# interface, and also provides extensions that make it easier to call this interface later
HuggingFace

Generated C# SDK based on HuggingFace OpenAPI specification.
Anthropic

Generated C# SDK based on official Anthropic OpenAPI specification.
Aeolin.AwosFramework.OpenAIFunctionCalling

Package Description
Midjourney

Generated C# SDK based on Midjourney OpenAPI specification.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last updated
2.0.0 26 5/15/2024
1.2.0 21,547 2/18/2024
1.1.3 86,992 10/11/2023
1.1.2 59,648 8/28/2023
1.1.1 55,089 7/12/2023
1.1.0 1,550 6/28/2023
1.0.2 238 6/21/2023
1.0.1 285 6/16/2023
1.0.0 523 6/12/2023
0.9.7 218 6/11/2023
0.9.6 287 6/9/2023
0.9.5 208 6/9/2023
0.9.4 142 6/9/2023
0.9.3 131 6/9/2023
0.9.2 162 6/9/2023