OpenAiNg 2.3.3

There is a newer prerelease version of this package available.
See the version list below for details.
dotnet add package OpenAiNg --version 2.3.3
NuGet\Install-Package OpenAiNg -Version 2.3.3
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="OpenAiNg" Version="2.3.3" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add OpenAiNg --version 2.3.3
#r "nuget: OpenAiNg, 2.3.3"
#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 OpenAiNg as a Cake Addin
#addin nuget:?package=OpenAiNg&version=2.3.3

// Install OpenAiNg as a Cake Tool
#tool nuget:?package=OpenAiNg&version=2.3.3

OpenAI

.NET SDK for accessing the OpenAI Compatible APIs such as GPT-4 (Vision), GPT-3.5-instruct, and DALL-E 3

OpenAiNextGeneration is a simple .NET library to use with various OpenAI compatible providers, such as OpenAI, Azure OpenAI, and KoboldCpp ( v1.45.2+). Supports features such as function calling in conjunction with streaming, caches its own HttpClients.

Supported features compared to OpenAI-API-dotnet:

  • Supports new models.
  • Parallel function calling.
  • Improved memory usage, and function calling in conjunction with streaming.
  • Manages its pool of HttpClients.
  • Improved credentials passing.
  • Supports OpenAI-compatible API providers, such as KoboldCpp.
  • Improved Azure OpenAI integration.
  • Nullability annotations.
  • Actively maintained, backed by a company I work for.

Features scheduled for open-sourcing:

  • High-level plugin API.
  • Approximate token counting for streaming & function calling.

⚡Getting Started

Install the library via NuGet:

Install-Package OpenAiNg

🔮 Quick Inference

var api = new OpenAiNg.OpenAiApi("YOUR_API_KEY");
var result = await api.Completions.GetCompletion("One Two Three One Two");
Console.WriteLine(result);
// should print something starting with "Three"

📖 Readme

Requirements

Unlike the original library, OpenAiNg supports only .NET Core >= 6.0, if you need .NET Standard 2.0 /.NET Framework support, please use OpenAI-API-DotNet.

Getting started

Install from NuGet

Install package OpenAiNg from Nuget. Here's how via the command line:

Install-Package OpenAiNg

Authentication

Pass keys directly to ApiAuthentication(string key) constructor.

You use the APIAuthentication when you initialize the API as shown:

// for example
var api = new OpenAiApi("YOUR_API_KEY"); // shorthand
// or
var api = new OpenAiApi(new APIAuthentication("YOUR_API_KEY")); // create object manually

You may optionally include an OpenAiOrganization if you have multiple Organizations under one account.

// for example
var api = new OpenAiApi(new ApiAuthentication("YOUR_API_KEY", "org-yourOrgHere"));

Audio Transcription

You can transcribe an audio file with OpenAiNg using the following code snippet:

// Create the audioFile object
AudioFile audioFile = new()
{
    File = fileStream,       // your FileStream instance here
    ContentType = "audio/ogg",  // content type may vary depending on the file type
    Name = Path.GetFileName(filePath) // name of the file
};

// Create the transcriptionRequest object
TranscriptionRequest transcriptionRequest = new()
{
    File = audioFile, // the audio file to be transcribed
    Model = OpenAiNg.Models.Model.Whisper_1, // the model to be used for transcription
};

// Async call to create transcriptions
TranscriptionVerboseJsonResult? result =
    await api.Audio.CreateTranscriptionAsync(transcriptionRequest);

// Get the transcript text from the result
return result.Text;

Create a Speech

Here is an example of how you can generate speech from a given text.

SpeechTtsResult? ttsResult = await api.Audio.CreateSpeechAsync(new SpeechRequest
{
    Input = text,  // Text that need to convert into speech
    Model = OpenAiNg.Models.Model.TTS_1_HD,  // Model that will be used for text-to-speech conversation
    Voice = SpeechVoice.Nova,  // OpenAi's Nova voice will be used for speech output
    ResponseFormat = SpeechResponseFormat.Mp3,  // Output will be in Mp3 format
});

string path = Path.Combine(Path.GetTempPath(), // getting directory path for temp files
    Path.ChangeExtension(Path.GetTempFileName(), "mp3"));  // Generating a unique temp file and changing its extension to .mp3

// Save the audio and dispose the source stream
await ttsResult.SaveAndDispose(path);

Documentation

Every single class, method, and property has extensive XML documentation, so it should show up automatically in IntelliSense. That combined with the official OpenAI documentation should be enough to get started. Feel free to open an issue here if you have any questions.

License

This library is licensed under MIT license.

Product Compatible and additional computed target framework versions.
.NET 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. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages

This package is not used by any NuGet packages.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last updated
3.0.0-beta7 86 4/21/2024
3.0.0-beta6 77 4/20/2024
3.0.0-beta5 63 4/20/2024
3.0.0-beta4 89 3/12/2024
3.0.0-beta3 78 3/10/2024
3.0.0-beta2 100 2/6/2024
3.0.0-beta1 81 1/29/2024
2.3.3 614 12/14/2023
2.3.2 157 12/3/2023
2.3.1 119 12/2/2023
2.3.0 117 12/1/2023
2.2.9 956 11/9/2023
2.2.8 99 11/8/2023
2.2.7 127 11/7/2023
2.2.6 94 11/7/2023
2.2.5 96 11/7/2023
2.2.4 154 10/8/2023
2.2.3 134 10/8/2023
2.2.2 128 10/8/2023
2.2.1 127 10/8/2023
2.2.0 135 10/8/2023

TTS endpoint