Tiktoken 0.9.3
See the version list below for details.
dotnet add package Tiktoken --version 0.9.3
NuGet\Install-Package Tiktoken -Version 0.9.3
<PackageReference Include="Tiktoken" Version="0.9.3" />
paket add Tiktoken --version 0.9.3
#r "nuget: Tiktoken, 0.9.3"
// Install Tiktoken as a Cake Addin #addin nuget:?package=Tiktoken&version=0.9.3 // Install Tiktoken as a Cake Tool #tool nuget:?package=Tiktoken&version=0.9.3
Tiktoken
Due to the lack of a C# version of cl100k_base
encoding (gpt-3.5-turbo), I have implemented a basic solution with encoding and decoding methods based on the official Rust implementation.
Currently, cl100k_base
p50k_base
has been implemented. Other encodings will be added in future submissions. If you encounter any issues or have questions, please feel free to submit them on the lssues
."
Usage
using Tiktoken;
var encoding = Encoding.ForModel("gpt-3.5-turbo");
var tokens = encoding.Encode("hello world"); // [15339, 1917]
var text = encoding.Decode(tokens); // hello world
var encoding = Encoding.Get("cl100k_base");
var tokens = encoding.Encode("hello world"); // [15339, 1917]
var text = encoding.Decode(tokens); // hello world
When using a new encoder for the first time, the required tiktoken files for the encoder will be downloaded from the internet. This may take some time. Once the download is successful, subsequent uses will not require downloading again. You can set TikToken.PBEFileDirectory
before using the encoder to modify the storage path of the downloaded tiktoken files, or you can pre-download the files to avoid network issues causing download failures.
Why are the tiktoken files not integrated into the package? On one hand, this would make the package size larger. On the other hand, I want to stay as consistent as possible with OpenAI's official Python code.
Below are the file download links: p50k_base.tiktoken cl100k_base.tiktoken
Benchmarks
You can view the reports for each version here
BenchmarkDotNet=v0.13.5, OS=macOS Ventura 13.3.1 (a) (22E772610a) [Darwin 22.4.0]
Apple M1 Pro, 1 CPU, 10 logical and 10 physical cores
.NET SDK=7.0.203
[Host] : .NET 7.0.5 (7.0.523.17405), Arm64 RyuJIT AdvSIMD
Job-YQCEPS : .NET 7.0.5 (7.0.523.17405), Arm64 RyuJIT AdvSIMD DEBUG
BuildConfiguration=Debug
Method | Data | Mean | Error | StdDev | Ratio | RatioSD | Gen0 | Gen1 | Allocated | Alloc Ratio |
---|---|---|---|---|---|---|---|---|---|---|
SharpTokenV1_0_28 | Hello, World! | 3.335 μs | 0.0589 μs | 0.0522 μs | 1.00 | 0.00 | 0.6752 | 0.0038 | 4.14 KB | 1.00 |
TiktokenSharpV1_0_5 | Hello, World! | 6.733 μs | 0.0506 μs | 0.0449 μs | 2.02 | 0.04 | 2.1820 | 0.0458 | 13.41 KB | 3.24 |
Tiktoken | Hello, World! | 6.742 μs | 0.0410 μs | 0.0364 μs | 2.02 | 0.03 | 2.1820 | 0.0458 | 13.41 KB | 3.24 |
SharpTokenV1_0_28 | King(...)edy. [275] | 63.037 μs | 0.4089 μs | 0.3624 μs | 1.00 | 0.00 | 8.5449 | 0.4883 | 52.89 KB | 1.00 |
TiktokenSharpV1_0_5 | King(...)edy. [275] | 21.937 μs | 0.0518 μs | 0.0404 μs | 0.35 | 0.00 | 5.0964 | 0.3052 | 31.34 KB | 0.59 |
Tiktoken | King(...)edy. [275] | 23.910 μs | 0.1035 μs | 0.0808 μs | 0.38 | 0.00 | 5.7678 | 0.3357 | 35.38 KB | 0.67 |
Product | Versions 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. 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. |
-
.NETFramework 4.6.1
- System.ValueTuple (>= 4.5.0)
-
.NETStandard 2.0
- No dependencies.
-
.NETStandard 2.1
- No dependencies.
-
net6.0
- No dependencies.
-
net7.0
- 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 |