Tiktoken 2.2.0
dotnet add package Tiktoken --version 2.2.0
NuGet\Install-Package Tiktoken -Version 2.2.0
<PackageReference Include="Tiktoken" Version="2.2.0" />
paket add Tiktoken --version 2.2.0
#r "nuget: Tiktoken, 2.2.0"
// Install Tiktoken as a Cake Addin #addin nuget:?package=Tiktoken&version=2.2.0 // Install Tiktoken as a Cake Tool #tool nuget:?package=Tiktoken&version=2.2.0
Tiktoken
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
o200k_base
cl100k_base
r50k_base
p50k_base
p50k_edit
Usage
using Tiktoken;
var encoder = ModelToEncoder.For("gpt-4o"); // or explicitly using new Encoder(new O200KBase())
var tokens = encoder.Encode("hello world"); // [15339, 1917]
var text = encoder.Decode(tokens); // hello world
var numberOfTokens = encoder.CountTokens(text); // 2
var stringTokens = encoder.Explore(text); // ["hello", " world"]
Benchmarks
You can view the reports for each version here
BenchmarkDotNet v0.14.0, macOS Sequoia 15.1 (24B83) [Darwin 24.1.0]
Apple M1 Pro, 1 CPU, 10 logical and 10 physical cores
.NET SDK 9.0.100
[Host] : .NET 9.0.0 (9.0.24.52809), Arm64 RyuJIT AdvSIMD
DefaultJob : .NET 9.0.0 (9.0.24.52809), Arm64 RyuJIT AdvSIMD
Method | Categories | Data | Mean | Ratio | Gen0 | Gen1 | Allocated | Alloc Ratio |
---|---|---|---|---|---|---|---|---|
SharpTokenV2_0_3_ | CountTokens | 1. (...)57. [19866] | 567,130.0 ns | 1.00 | 2.9297 | - | 20115 B | 1.00 |
TiktokenSharpV1_1_5_ | CountTokens | 1. (...)57. [19866] | 483,976.7 ns | 0.85 | 64.4531 | 5.8594 | 404648 B | 20.12 |
MicrosoftMLTokenizerV1_0_0_ | CountTokens | 1. (...)57. [19866] | 427,733.2 ns | 0.75 | - | - | 297 B | 0.01 |
TokenizerLibV1_3_3_ | CountTokens | 1. (...)57. [19866] | 773,467.5 ns | 1.36 | 246.0938 | 83.9844 | 1547675 B | 76.94 |
Tiktoken_ | CountTokens | 1. (...)57. [19866] | 271,564.3 ns | 0.48 | 23.4375 | - | 148313 B | 7.37 |
SharpTokenV2_0_3_ | CountTokens | Hello, World! | 380.0 ns | 1.00 | 0.0405 | - | 256 B | 1.00 |
TiktokenSharpV1_1_5_ | CountTokens | Hello, World! | 263.8 ns | 0.69 | 0.0505 | - | 320 B | 1.25 |
MicrosoftMLTokenizerV1_0_0_ | CountTokens | Hello, World! | 305.7 ns | 0.80 | 0.0153 | - | 96 B | 0.38 |
TokenizerLibV1_3_3_ | CountTokens | Hello, World! | 509.6 ns | 1.34 | 0.2356 | 0.0010 | 1480 B | 5.78 |
Tiktoken_ | CountTokens | Hello, World! | 175.7 ns | 0.46 | 0.0191 | - | 120 B | 0.47 |
SharpTokenV2_0_3_ | CountTokens | King(...)edy. [275] | 5,990.7 ns | 1.00 | 0.0763 | - | 520 B | 1.00 |
TiktokenSharpV1_1_5_ | CountTokens | King(...)edy. [275] | 4,516.5 ns | 0.75 | 0.8011 | - | 5064 B | 9.74 |
MicrosoftMLTokenizerV1_0_0_ | CountTokens | King(...)edy. [275] | 3,871.2 ns | 0.65 | 0.0153 | - | 96 B | 0.18 |
TokenizerLibV1_3_3_ | CountTokens | King(...)edy. [275] | 7,465.8 ns | 1.25 | 3.0823 | 0.1373 | 19344 B | 37.20 |
Tiktoken_ | CountTokens | King(...)edy. [275] | 2,744.5 ns | 0.46 | 0.3128 | - | 1976 B | 3.80 |
SharpTokenV2_0_3_Encode | Encode | 1. (...)57. [19866] | 568,150.3 ns | 1.00 | 2.9297 | - | 20115 B | 1.00 |
TiktokenSharpV1_1_5_Encode | Encode | 1. (...)57. [19866] | 444,972.1 ns | 0.78 | 64.4531 | 5.8594 | 404649 B | 20.12 |
MicrosoftMLTokenizerV1_0_0_Encode | Encode | 1. (...)57. [19866] | 410,970.9 ns | 0.72 | 10.2539 | 0.4883 | 66137 B | 3.29 |
TokenizerLibV1_3_3_Encode | Encode | 1. (...)57. [19866] | 770,068.9 ns | 1.36 | 246.0938 | 90.8203 | 1547675 B | 76.94 |
Tiktoken_Encode | Encode | 1. (...)57. [19866] | 290,030.9 ns | 0.51 | 33.6914 | 1.4648 | 214465 B | 10.66 |
SharpTokenV2_0_3_Encode | Encode | Hello, World! | 381.2 ns | 1.00 | 0.0405 | - | 256 B | 1.00 |
TiktokenSharpV1_1_5_Encode | Encode | Hello, World! | 260.2 ns | 0.68 | 0.0505 | - | 320 B | 1.25 |
MicrosoftMLTokenizerV1_0_0_Encode | Encode | Hello, World! | 325.1 ns | 0.85 | 0.0267 | - | 168 B | 0.66 |
TokenizerLibV1_3_3_Encode | Encode | Hello, World! | 511.6 ns | 1.34 | 0.2356 | - | 1480 B | 5.78 |
Tiktoken_Encode | Encode | Hello, World! | 241.4 ns | 0.63 | 0.0801 | - | 504 B | 1.97 |
SharpTokenV2_0_3_Encode | Encode | King(...)edy. [275] | 5,957.3 ns | 1.00 | 0.0763 | - | 520 B | 1.00 |
TiktokenSharpV1_1_5_Encode | Encode | King(...)edy. [275] | 4,523.8 ns | 0.76 | 0.8011 | - | 5064 B | 9.74 |
MicrosoftMLTokenizerV1_0_0_Encode | Encode | King(...)edy. [275] | 4,069.8 ns | 0.68 | 0.1144 | - | 744 B | 1.43 |
TokenizerLibV1_3_3_Encode | Encode | King(...)edy. [275] | 7,207.8 ns | 1.21 | 3.0823 | 0.1373 | 19344 B | 37.20 |
Tiktoken_Encode | Encode | King(...)edy. [275] | 2,945.7 ns | 0.49 | 0.4654 | - | 2936 B | 5.65 |
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 | Versions Compatible and additional computed target framework versions. |
---|---|
.NET | net5.0 was computed. net5.0-windows was computed. net6.0 was computed. 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 was computed. 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 is compatible. |
.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 was computed. net462 is compatible. 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. |
-
.NETFramework 4.6.2
- Tiktoken.Core (>= 2.2.0)
- Tiktoken.Encodings.cl100k (>= 2.2.0)
- Tiktoken.Encodings.o200k (>= 2.2.0)
-
.NETStandard 2.0
- Tiktoken.Core (>= 2.2.0)
- Tiktoken.Encodings.cl100k (>= 2.2.0)
- Tiktoken.Encodings.o200k (>= 2.2.0)
-
.NETStandard 2.1
- Tiktoken.Core (>= 2.2.0)
- Tiktoken.Encodings.cl100k (>= 2.2.0)
- Tiktoken.Encodings.o200k (>= 2.2.0)
-
net8.0
- Tiktoken.Core (>= 2.2.0)
- Tiktoken.Encodings.cl100k (>= 2.2.0)
- Tiktoken.Encodings.o200k (>= 2.2.0)
-
net9.0
- Tiktoken.Core (>= 2.2.0)
- Tiktoken.Encodings.cl100k (>= 2.2.0)
- Tiktoken.Encodings.o200k (>= 2.2.0)
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 | 65 | 11/15/2024 |
2.1.1 | 543 | 11/9/2024 |
2.1.0 | 120 | 11/9/2024 |
2.0.3 | 74,468 | 7/10/2024 |
2.0.2 | 24,938 | 5/19/2024 |
2.0.1 | 124 | 5/18/2024 |
2.0.0 | 1,433 | 5/15/2024 |
1.2.0 | 114,013 | 2/18/2024 |
1.1.3 | 174,865 | 10/11/2023 |
1.1.2 | 122,026 | 8/28/2023 |
1.1.1 | 114,009 | 7/12/2023 |
1.1.0 | 2,351 | 6/28/2023 |
1.0.2 | 268 | 6/21/2023 |
1.0.1 | 335 | 6/16/2023 |
1.0.0 | 691 | 6/12/2023 |
0.9.7 | 277 | 6/11/2023 |
0.9.6 | 342 | 6/9/2023 |
0.9.5 | 260 | 6/9/2023 |
0.9.4 | 169 | 6/9/2023 |
0.9.3 | 166 | 6/9/2023 |
0.9.2 | 279 | 6/9/2023 |