A simple C# .NET client library for OpenAI to use GPT-3 and Dall-E though their RESTful API (currently in beta). Independently developed, this is not an official library and I am not affiliated with OpenAI. An OpenAI API account is required.
Forked from OpenAI-API-dotnet.
More context on Roger Pincombe's blog.
This repository is available to transfer to the OpenAI organization if they so choose to accept it.
This library targets .NET 6.0 and above.
It should work across console apps, winforms, wpf, asp.net, etc.
It should also work across Windows, Linux, and Mac.
Install package OpenAI from Nuget. Here's how via command line:
Install-Package OpenAI-DotNetLooking to use OpenAI in the Unity Game Engine? Check out our unity package on OpenUPM:
- Authentication
- Azure OpenAI
- Models
- Completions
- Chat
- Edits
- Embeddings
- Audio
- Images
- Files
- Fine Tuning
- Moderations
There are 3 ways to provide your API keys, in order of precedence:
- Pass keys directly with constructor
- Load key from configuration file
- Use System Environment Variables
You use the OpenAIAuthentication when you initialize the API as shown:
var api = new OpenAIClient("sk-apiKey");Or create a OpenAIAuthentication object manually
var api = new OpenAIClient(new OpenAIAuthentication("sk-apiKey", "org-yourOrganizationId"));Attempts to load api keys from a configuration file, by default .openai in the current directory, optionally traversing up the directory tree or in the user's home directory.
To create a configuration file, create a new text file named .openai and containing the line:
Organization entry is optional.
{
"apiKey": "sk-aaaabbbbbccccddddd",
"organization": "org-yourOrganizationId"
}OPENAI_KEY=sk-aaaabbbbbccccddddd
ORGANIZATION=org-yourOrganizationIdYou can also load the file directly with known path by calling a static method in Authentication:
var api = new OpenAIClient(OpenAIAuthentication.LoadFromDirectory("your/path/to/.openai"));;Use your system's environment variables specify an api key and organization to use.
- Use
OPENAI_API_KEYfor your api key. - Use
OPENAI_ORGANIZATION_IDto specify an organization.
var api = new OpenAIClient(OpenAIAuthentication.LoadFromEnv());You can also choose to use Microsoft's Azure OpenAI deployments as well.
To setup the client to use your deployment, you'll need to pass in OpenAIClientSettings into the client constructor.
var auth = new OpenAIAuthentication("sk-apiKey");
var settings = new OpenAIClientSettings("your-resource", "your-deployment-id");
var api = new OpenAIClient(auth, settings);List and describe the various models available in the API. You can refer to the Models documentation to understand what models are available and the differences between them.
The Models API is accessed via OpenAIClient.ModelsEndpoint
Lists the currently available models, and provides basic information about each one such as the owner and availability.
var api = new OpenAIClient();
var models = await api.ModelsEndpoint.GetModelsAsync();
foreach (var model in models)
{
Console.WriteLine(model.ToString());
}Retrieves a model instance, providing basic information about the model such as the owner and permissioning.
var api = new OpenAIClient();
var model = await api.ModelsEndpoint.GetModelDetailsAsync("text-davinci-003");
Console.WriteLine(model.ToString());Delete a fine-tuned model. You must have the Owner role in your organization.
var api = new OpenAIClient();
var result = await api.ModelsEndpoint.DeleteFineTuneModelAsync("your-fine-tuned-model");
Assert.IsTrue(result);Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.
var api = new OpenAIClient();
var result = await api.CompletionsEndpoint.CreateCompletionAsync("One Two Three One Two", temperature: 0.1, model: Model.Davinci);
Console.WriteLine(result);To get the
CompletionResult(which is mostly metadata), use its implicit string operator to get the text if all you want is the completion choice.
Streaming allows you to get results are they are generated, which can help your application feel more responsive, especially on slow models like Davinci.
var api = new OpenAIClient();
await api.CompletionsEndpoint.StreamCompletionAsync(result =>
{
foreach (var choice in result.Completions)
{
Console.WriteLine(choice);
}
}, "My name is Roger and I am a principal software engineer at Salesforce. This is my resume:", maxTokens: 200, temperature: 0.5, presencePenalty: 0.1, frequencyPenalty: 0.1, model: Model.Davinci);Or if using IAsyncEnumerable{T} (C# 8.0+)
var api = new OpenAIClient();
await foreach (var token in api.CompletionsEndpoint.StreamCompletionEnumerableAsync("My name is Roger and I am a principal software engineer at Salesforce. This is my resume:", maxTokens: 200, temperature: 0.5, presencePenalty: 0.1, frequencyPenalty: 0.1, model: Model.Davinci))
{
Console.WriteLine(token);
}Given a chat conversation, the model will return a chat completion response.
Creates a completion for the chat message
var api = new OpenAIClient();
var chatPrompts = new List<ChatPrompt>
{
new ChatPrompt("system", "You are a helpful assistant."),
new ChatPrompt("user", "Who won the world series in 2020?"),
new ChatPrompt("assistant", "The Los Angeles Dodgers won the World Series in 2020."),
new ChatPrompt("user", "Where was it played?"),
};
var chatRequest = new ChatRequest(chatPrompts);
var result = await api.ChatEndpoint.GetCompletionAsync(chatRequest);
Console.WriteLine(result.FirstChoice);var api = new OpenAIClient();
var chatPrompts = new List<ChatPrompt>
{
new ChatPrompt("system", "You are a helpful assistant."),
new ChatPrompt("user", "Who won the world series in 2020?"),
new ChatPrompt("assistant", "The Los Angeles Dodgers won the World Series in 2020."),
new ChatPrompt("user", "Where was it played?"),
};
var chatRequest = new ChatRequest(chatPrompts, Model.GPT3_5_Turbo);
await api.ChatEndpoint.StreamCompletionAsync(chatRequest, result =>
{
Console.WriteLine(result.FirstChoice);
});Or if using IAsyncEnumerable{T} (C# 8.0+)
var api = new OpenAIClient();
var chatPrompts = new List<ChatPrompt>
{
new ChatPrompt("system", "You are a helpful assistant."),
new ChatPrompt("user", "Who won the world series in 2020?"),
new ChatPrompt("assistant", "The Los Angeles Dodgers won the World Series in 2020."),
new ChatPrompt("user", "Where was it played?"),
};
var chatRequest = new ChatRequest(chatPrompts, Model.GPT3_5_Turbo);
await foreach (var result in api.ChatEndpoint.StreamCompletionEnumerableAsync(chatRequest))
{
Console.WriteLine(result.FirstChoice);
}Given a prompt and an instruction, the model will return an edited version of the prompt.
The Edits API is accessed via OpenAIClient.EditsEndpoint
Creates a new edit for the provided input, instruction, and parameters using the provided input and instruction.
var api = new OpenAIClient();
var request = new EditRequest("What day of the wek is it?", "Fix the spelling mistakes");
var result = await api.EditsEndpoint.CreateEditAsync(request);
Console.WriteLine(result);Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
Related guide: Embeddings
The Edits API is accessed via OpenAIClient.EmbeddingsEndpoint
Creates an embedding vector representing the input text.
var api = new OpenAIClient();
var model = await api.ModelsEndpoint.GetModelDetailsAsync("text-embedding-ada-002");
var result = await api.EmbeddingsEndpoint.CreateEmbeddingAsync("The food was delicious and the waiter...", model);
Console.WriteLine(result);Converts audio into text.
Transcribes audio into the input language.
var api = new OpenAIClient();
var request = new AudioTranscriptionRequest(Path.GetFullPath(audioAssetPath), language: "en");
var result = await api.AudioEndpoint.CreateTranscriptionAsync(request);
Console.WriteLine(result);Translates audio into into English.
var api = new OpenAIClient();
var request = new AudioTranslationRequest(Path.GetFullPath(audioAssetPath));
var result = await api.AudioEndpoint.CreateTranslationAsync(request);
Console.WriteLine(result);Given a prompt and/or an input image, the model will generate a new image.
The Images API is accessed via OpenAIClient.ImagesEndpoint
Creates an image given a prompt.
var api = new OpenAIClient();
var results = await api.ImagesEndPoint.GenerateImageAsync("A house riding a velociraptor", 1, ImageSize.Small);
foreach (var result in results)
{
Console.WriteLine(result);
// result == file:https://path/to/image.png
}Creates an edited or extended image given an original image and a prompt.
var api = new OpenAIClient();
var results = await api.ImagesEndPoint.CreateImageEditAsync(Path.GetFullPath(imageAssetPath), Path.GetFullPath(maskAssetPath), "A sunlit indoor lounge area with a pool containing a flamingo", 1, ImageSize.Small);
foreach (var result in results)
{
Console.WriteLine(result);
// result == file:https://path/to/image.png
}Creates a variation of a given image.
var api = new OpenAIClient();
var results = await api.ImagesEndPoint.CreateImageVariationAsync(Path.GetFullPath(imageAssetPath), 1, ImageSize.Small);
foreach (var result in results)
{
Console.WriteLine(result);
// result == file:https://path/to/image.png
}Files are used to upload documents that can be used with features like Fine-tuning.
The Files API is accessed via OpenAIClient.FilesEndpoint
Returns a list of files that belong to the user's organization.
var api = new OpenAIClient();
var files = await api.FilesEndpoint.ListFilesAsync();
foreach (var file in files)
{
Console.WriteLine($"{file.Id} -> {file.Object}: {file.FileName} | {file.Size} bytes");
}Upload a file that contains document(s) to be used across various endpoints/features. Currently, the size of all the files uploaded by one organization can be up to 1 GB. Please contact us if you need to increase the storage limit.
var api = new OpenAIClient();
var fileData = await api.FilesEndpoint.UploadFileAsync("path/to/your/file.jsonl", "fine-tune");
Console.WriteLine(fileData.Id);Delete a file.
var api = new OpenAIClient();
var result = await api.FilesEndpoint.DeleteFileAsync(fileData);
Assert.IsTrue(result);Returns information about a specific file.
var api = new OpenAIClient();
var fileData = await GetFileInfoAsync(fileId);
Console.WriteLine($"{fileData.Id} -> {fileData.Object}: {fileData.FileName} | {fileData.Size} bytes");Downloads the specified file.
var api = new OpenAIClient();
var downloadedFilePath = await api.FilesEndpoint.DownloadFileAsync(fileId, "path/to/your/save/directory");
Console.WriteLine(downloadedFilePath);
Assert.IsTrue(File.Exists(downloadedFilePath));Manage fine-tuning jobs to tailor a model to your specific training data.
Related guide: Fine-tune models
The Files API is accessed via OpenAIClient.FineTuningEndpoint
Creates a job that fine-tunes a specified model from a given dataset.
Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete.
var api = new OpenAIClient();
var request = new CreateFineTuneRequest(fileData);
var fineTuneJob = await api.FineTuningEndpoint.CreateFineTuneJobAsync(request);
Console.WriteLine(fineTuneJob.Id);List your organization's fine-tuning jobs.
var api = new OpenAIClient();
var fineTuneJobs = await api.FineTuningEndpoint.ListFineTuneJobsAsync();
foreach (var job in fineTuneJobs)
{
Console.WriteLine($"{job.Id} -> {job.Status}");
}Gets info about the fine-tune job.
var api = new OpenAIClient();
var result = await api.FineTuningEndpoint.RetrieveFineTuneJobInfoAsync(fineTuneJob);
Console.WriteLine($"{result.Id} -> {result.Status}");Immediately cancel a fine-tune job.
var api = new OpenAIClient();
var result = await api.FineTuningEndpoint.CancelFineTuneJobAsync(fineTuneJob);
Assert.IsTrue(result);Get fine-grained status updates for a fine-tune job.
var api = new OpenAIClient();
var fineTuneEvents = await api.FineTuningEndpoint.ListFineTuneEventsAsync(fineTuneJob);
Console.WriteLine($"{fineTuneJob.Id} -> status: {fineTuneJob.Status} | event count: {fineTuneEvents.Count}");var api = new OpenAIClient();
await api.FineTuningEndpoint.StreamFineTuneEventsAsync(fineTuneJob, fineTuneEvent =>
{
Console.WriteLine($" {fineTuneEvent.CreatedAt} [{fineTuneEvent.Level}] {fineTuneEvent.Message}");
});Or if using IAsyncEnumerable{T} (C# 8.0+)
var api = new OpenAIClient();
await foreach (var fineTuneEvent in api.FineTuningEndpoint.StreamFineTuneEventsEnumerableAsync(fineTuneJob))
{
Console.WriteLine($" {fineTuneEvent.CreatedAt} [{fineTuneEvent.Level}] {fineTuneEvent.Message}");
}Given a input text, outputs if the model classifies it as violating OpenAI's content policy.
Related guide: Moderations
The Moderations API can be accessed via OpenAIClient.ModerationsEndpoint
Classifies if text violates OpenAI's Content Policy.
var api = new OpenAIClient();
var response = await api.ModerationsEndpoint.GetModerationAsync("I want to kill them.");
Assert.IsTrue(response);
This library is licensed CC-0, in the public domain. You can use it for whatever you want, publicly or privately, without worrying about permission or licensing or whatever. It's just a wrapper around the OpenAI API, so you still need to get access to OpenAI from them directly. I am not affiliated with OpenAI and this library is not endorsed by them, I just have beta access and wanted to make a C# library to access it more easily. Hopefully others find this useful as well. Feel free to open a PR if there's anything you want to contribute.