Tiktoken 1.2.0

.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There is a newer version of this package available.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 1.2.0                

                    
                

            
NuGet\Install-Package Tiktoken -Version 1.2.0
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="1.2.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
paket add Tiktoken --version 1.2.0                

                    
                

            
#r "nuget: Tiktoken, 1.2.0"
#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=1.2.0

// Install Tiktoken as a Cake Tool
#tool nuget:?package=Tiktoken&version=1.2.0

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 v0.13.12, macOS Sonoma 14.2.1 (23C71) [Darwin 23.2.0]
Apple M1 Pro, 1 CPU, 10 logical and 10 physical cores
.NET SDK 8.0.100
  [Host]     : .NET 8.0.0 (8.0.23.53103), Arm64 RyuJIT AdvSIMD
  DefaultJob : .NET 8.0.0 (8.0.23.53103), Arm64 RyuJIT AdvSIMD
Method Categories Data Mean Median Ratio Gen0 Gen1 Gen2 Allocated Alloc Ratio
SharpTokenV1_2_16_ CountTokens 1. (...)57. [19866] 1,554,552.0 ns 1,552,769.4 ns 1.00 292.9688 146.4844 - 1846147 B 1.00
TiktokenSharpV1_0_9_ CountTokens 1. (...)57. [19866] 1,242,157.7 ns 1,241,657.7 ns 0.80 253.9063 117.1875 3.9063 1570786 B 0.85
TokenizerLibV1_3_3_ CountTokens 1. (...)57. [19866] 815,490.5 ns 806,761.4 ns 0.52 247.0703 98.6328 0.9766 1547678 B 0.84
Tiktoken_ CountTokens 1. (...)57. [19866] 311,744.2 ns 311,591.0 ns 0.20 49.3164 - - 309449 B 0.17
SharpTokenV1_2_16_ CountTokens Hello, World! 1,585.8 ns 1,586.5 ns 1.00 0.5188 0.0019 - 3264 B 1.00
TiktokenSharpV1_0_9_ CountTokens Hello, World! 5,806.8 ns 5,805.7 ns 3.66 2.1286 0.0381 0.0076 13344 B 4.09
TokenizerLibV1_3_3_ CountTokens Hello, World! 766.2 ns 766.7 ns 0.48 0.2356 - - 1480 B 0.45
Tiktoken_ CountTokens Hello, World! 210.9 ns 210.2 ns 0.13 0.0420 - - 264 B 0.08
SharpTokenV1_2_16_ CountTokens King(...)edy. [275] 13,851.9 ns 13,808.5 ns 1.00 4.1351 0.0153 - 25968 B 1.00
TiktokenSharpV1_0_9_ CountTokens King(...)edy. [275] 13,387.6 ns 13,395.3 ns 0.97 5.0659 0.1984 0.0153 31712 B 1.22
TokenizerLibV1_3_3_ CountTokens King(...)edy. [275] 10,861.4 ns 10,865.2 ns 0.78 3.0975 0.1526 0.0153 19344 B 0.74
Tiktoken_ CountTokens King(...)edy. [275] 3,162.3 ns 3,162.0 ns 0.23 0.6447 - - 4064 B 0.16
SharpTokenV1_2_16_Encode Encode 1. (...)57. [19866] 1,327,775.1 ns 1,330,166.1 ns 1.00 294.9219 142.5781 1.9531 1846151 B 1.00
TiktokenSharpV1_0_9_Encode Encode 1. (...)57. [19866] 1,016,985.4 ns 994,095.3 ns 0.80 250.0000 125.0000 - 1570772 B 0.85
TokenizerLibV1_3_3_Encode Encode 1. (...)57. [19866] 804,657.4 ns 803,549.7 ns 0.61 247.0703 108.3984 0.9766 1547678 B 0.84
Tiktoken_Encode Encode 1. (...)57. [19866] 331,107.8 ns 331,142.1 ns 0.25 59.5703 2.4414 - 375601 B 0.20
SharpTokenV1_2_16_Encode Encode Hello, World! 1,891.1 ns 1,894.6 ns 1.00 0.5188 0.0019 - 3264 B 1.00
TiktokenSharpV1_0_9_Encode Encode Hello, World! 5,816.9 ns 5,824.0 ns 3.08 2.1210 0.0381 - 13344 B 4.09
TokenizerLibV1_3_3_Encode Encode Hello, World! 496.7 ns 496.8 ns 0.26 0.2356 - - 1480 B 0.45
Tiktoken_Encode Encode Hello, World! 265.3 ns 264.7 ns 0.14 0.1030 - - 648 B 0.20
SharpTokenV1_2_16_Encode Encode King(...)edy. [275] 17,497.7 ns 17,480.3 ns 1.00 4.1199 0.0305 - 25968 B 1.00
TiktokenSharpV1_0_9_Encode Encode King(...)edy. [275] 13,374.0 ns 13,348.4 ns 0.76 5.0659 0.1984 0.0153 31712 B 1.22
TokenizerLibV1_3_3_Encode Encode King(...)edy. [275] 7,333.9 ns 7,338.7 ns 0.42 3.0899 0.1450 0.0076 19344 B 0.74
Tiktoken_Encode Encode King(...)edy. [275] 3,450.2 ns 3,452.9 ns 0.20 0.7973 - - 5024 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 is compatible.  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.  net9.0 was computed.  net9.0-android was computed.  net9.0-browser was computed.  net9.0-ios was computed.  net9.0-maccatalyst was computed.  net9.0-macos was computed.  net9.0-tvos was computed.  net9.0-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.

  • net8.0

    • No dependencies.

NuGet packages (8)

Showing the top 5 NuGet packages that depend on Tiktoken:

Package Downloads
tryAGI.OpenAI

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
LangChain.Providers.HuggingFace

HuggingFace API LLM and Chat model provider.
LangChain.Providers.Anyscale

Anyscale Endpoints Chat model provider.
drittich.SemanticSlicer

A library for slicing text data into smaller chunks while attempting to preserve context.
Aeolin.AwosFramework.OpenAIFunctionCalling

Package Description

GitHub repositories (1)

Showing the top 1 popular GitHub repositories that depend on Tiktoken:

Repository Stars
Richasy/Rodel.Agent
支持主流在线 AI 服务的应用
Version Downloads Last updated
2.2.0 12,770 11/15/2024
2.1.1 2,811 11/9/2024
2.1.0 637 11/9/2024
2.0.3 133,171 7/10/2024
2.0.2 33,935 5/19/2024
2.0.1 141 5/18/2024
2.0.0 1,743 5/15/2024
1.2.0 133,143 2/18/2024
1.1.3 188,052 10/11/2023
1.1.2 138,213 8/28/2023
1.1.1 130,137 7/12/2023
1.1.0 2,603 6/28/2023
1.0.2 281 6/21/2023
1.0.1 351 6/16/2023
1.0.0 704 6/12/2023
0.9.7 290 6/11/2023
0.9.6 355 6/9/2023
0.9.5 273 6/9/2023
0.9.4 182 6/9/2023
0.9.3 177 6/9/2023
0.9.2 383 6/9/2023