Whetstone.ChatGPT 1.8.0

There is a newer version of this package available.
See the version list below for details.
dotnet add package Whetstone.ChatGPT --version 1.8.0                
NuGet\Install-Package Whetstone.ChatGPT -Version 1.8.0                
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="Whetstone.ChatGPT" Version="1.8.0" />                
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add Whetstone.ChatGPT --version 1.8.0                
#r "nuget: Whetstone.ChatGPT, 1.8.0"                
#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 Whetstone.ChatGPT as a Cake Addin
#addin nuget:?package=Whetstone.ChatGPT&version=1.8.0

// Install Whetstone.ChatGPT as a Cake Tool
#tool nuget:?package=Whetstone.ChatGPT&version=1.8.0                



A simple light-weight library that wraps the Open AI API with support for dependency injection.

Supported features include:

  • GPT 4, GPT 3.5 Turbo and Chat Completions
  • Audio Transcription and Translation (Whisper API)
  • Chat Completions
  • Vision Completions
  • Files
  • Fine Tunes
  • Images
  • Embeddings
  • Moderations
  • Response streaming

For a video walkthrough of a Blazor web app built on this library, please see:


This is deployed to github pages and available at: Open AI UI. Source for the Blazor web app is at Whetstone.ChatGPT.Blazor.App.

Examples include:

Dependency Injection Quickstart

services.Configure<ChatGPTCredentials>(options =>
    options.ApiKey = "YOURAPIKEY";
    options.Organization = "YOURORGANIZATIONID";




services.AddHttpClient<IChatGPTClient, ChatGPTClient>();

Configure IChatGPTClient service:

services.AddScoped<IChatGPTClient, ChatGPTClient>();

Chat Completions

Chat completions are a special type of completion that are optimized for chat. They are designed to be used in a conversational context.

Chat Completion Quickstart

This shows a usage of the GPT-3.5 Turbo model.

using Whetstone.ChatGPT;
using Whetstone.ChatGPT.Models;

. . .

var gptRequest = new ChatGPTChatCompletionRequest
    Model = ChatGPT35Models.Turbo,
    Messages = new List<ChatGPTChatCompletionMessage>()
            new ChatGPTChatCompletionMessage()
                Role = MessageRole.System,
                Content = "You are a helpful assistant."
            new ChatGPTChatCompletionMessage()
                Role = MessageRole.User,
                Content = "Who won the world series in 2020?"
            new ChatGPTChatCompletionMessage()
                Role = MessageRole.Assistant,
                Content = "The Los Angeles Dodgers won the World Series in 2020."
            new ChatGPTChatCompletionMessage()
                Role = MessageRole.User,
                Content = "Where was it played?"
    Temperature = 0.9f,
    MaxTokens = 100

using IChatGPTClient client = new ChatGPTClient("YOURAPIKEY");

var response = await client.CreateChatCompletionAsync(gptRequest);


GPT-4 models can also be used provided your account has been granted access to the limited beta.


Completions use models to answer a wide variety of tasks, including but not limited to classification, sentiment analysis, answering questions, etc.

Completion Quickstart

This shows a direct useage of the text-davinci-003 model without any prompts.

using Whetstone.ChatGPT;
using Whetstone.ChatGPT.Models;

. . .

var gptRequest = new ChatGPTCompletionRequest
    Model = ChatGPT35Models.Davinci003,
    Prompt = "How is the weather?"

using IChatGPTClient client = new ChatGPTClient("YOURAPIKEY");

var response = await client.CreateChatCompletionAsync(gptRequest);


GPT-3.5 is not deterministic. One of the test runs of the sample above returned:

The weather can vary greatly depending on location. In general, you can expect temperatures to be moderate and climate to be comfortable, but it is always best to check the forecast for your specific area.

Completion Code Sample

A C# console application that uses completions is available at:

Whetstone.ChatGPT.CommandLineBot (chatgpt-marv)

This sample includes:

  • Authentication
  • Created a completion request using a prompt
  • Processing completion responses

File Quickstart

How to create a upload a new fine tuning file.

List<ChatGPTFineTuneLine> tuningInput = new()
    new ChatGPTFineTuneLine("<PROMPT>", "<COMPLETION>"),
    new ChatGPTFineTuneLine("<PROMPT>", "<COMPLETION>"),
    . . .

byte[] tuningText = tuningInput.ToJsonLBinary();

string fileName = "finetuningsample.jsonl";

ChatGPTUploadFileRequest? uploadRequest = new ChatGPTUploadFileRequest
    File = new ChatGPTFileContent
        FileName = fileName,
        Content = tuningText

ChatGPTFileInfo? uploadedFileInfo;

IChatGPTClient client = new ChatGPTClient("YOURAPIKEY");

uploadedFileInfo = await client.UploadFileAsync(uploadRequest);

Fine Tuning Quickstart

Once the file has been created, get the fileId, and reference it when creating a new fine tuning.

IChatGPTClient client = new ChatGPTClient("YOURAPIKEY");

var fileList = await client.ListFilesAsync();
var foundFile =  fileList.Data.First(x => x.Filename.Equals("finetuningsample.jsonl"));

ChatGPTCreateFineTuneRequest tuningRequest = new ChatGPTCreateFineTuneRequest
    TrainingFileId = foundFile.Id,
    Model = "gpt-3.5-turbo-1106"

ChatGPTFineTuneJob? tuneResponse = await client.CreateFineTuneAsync(tuningRequest);

string fineTuneId = tuneResponse.Id;

Processing the fine tuning request will take some time. Once it finishes, the Status will report "succeeded" and it's ready to be used in a completion request.

using IChatGPTClient client = new ChatGPTClient("YOURAPIKEY");

ChatGPTFineTuneJob? tuneResponse = await client.RetrieveFineTuneAsync("FINETUNEID");

    var gptRequest = new ChatGPTCompletionRequest
        Model = ChatGPTCompletionModels.Davinci,
        Prompt = "How is the weather?"

    var response = await client.CreateCompletionAsync(gptRequest);


Image Quickstart

Here's an example that generates a 1024x1024 image.

ChatGPTCreateImageRequest imageRequest = new()
    Prompt = "A sail boat",
    Size = CreatedImageSize.Size1024,
    ResponseFormat = CreatedImageFormat.Base64

using IChatGPTClient client = new ChatGPTClient("YOURAPIKEY");

ChatGPTImageResponse? imageResponse = await client.CreateImageAsync(imageRequest);

var imageData = imageResponse?.Data[0];

if (imageData != null)
    byte[] imageBytes = await client.DownloadImageAsync(imageData);

Audio Transcription Quickstart

Her's an example that transcribes an audio file using the Whisper.

string audioFile = @"audiofiles\transcriptiontest.mp3";

byte[] fileContents = File.ReadAllBytes(audioFile);
ChatGPTFileContent gptFile = new ChatGPTFileContent
    FileName = audioFile,
    Content = fileContents

ChatGPTAudioTranscriptionRequest? transcriptionRequest = new ChatGPTAudioTranscriptionRequest
    File = gptFile

using IChatGPTClient client = new ChatGPTClient("YOURAPIKEY");

ChatGPTAudioResponse? audioResponse = await client.CreateTranscriptionAsync(transcriptionRequest, true);

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 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. 
.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 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.

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
1.8.1 2,114 2/17/2024
1.8.0 143 1/21/2024
1.7.1 162 1/8/2024
1.7.0 673 12/17/2023
1.6.2 624 10/8/2023
1.6.1 1,142 7/8/2023
1.6.0 2,258 3/18/2023
1.5.0 281 3/12/2023
1.4.0 4,051 2/11/2023
1.3.0 612 1/21/2023
1.2.0 405 1/8/2023
1.1.0 298 1/7/2023
1.0.0 322 1/4/2023

# 1.8.0
- Include Breaking changes
- Removed deprecated edit endpoint
- Updated fine tune endpoints and models
- Refactored Model namespaces
- Marked legacy completions as obsolete

# 1.7.1
- Replaced deprecated models with gpt-3.5-turbo-instruct
- Added vision completion

# 1.7.0
- Updated to target .NET 8.
- Added deserialization error checks.

# 1.6.2

- Updated dependencies
- Updated roles for GPT-3.5 and GPT-4.0 messages to accept strings instead of an enumeration.

# 1.6.1

- Updated package dependencies to latest versions
- Adjusted GPT model constants to match latest API

# 1.6.0

- Added support for GPT-3.5
- Added support for audio transcription and tranlation

# 1.5.0

- Break Change: Updated the StreamCompletionAsync method to return the ChatGPTCompletionStreamResponse which does not include Usage. Stream responses do not include token usage.

# 1.4.0

- Added support for .NET Standard 2.0
- Built a working Blazor sample project

# 1.3.0

- Added set-only Credentials property to IChatGPTClient so that credentials can be changed after instantiation.
- Moved Credentials validation from constructor to API invocation pre-flight checks.
- Started Blazor sample project.

# 1.2.0

- Added support for dependency injection
- Some ChatGPTClient constructors were removed

# 1.1.0

- Added IChatGPTClient interface method for:
- StreamFineTuneEventsAsync
- DownloadImageAsync
- Small updates from code analysis suggestions