A .NET Library for accessing OpenAI's API, provided as a community library. This Library allows you to integrate OpenAI's capabilities into your .NET applications with ease.
⭐ We appreciate your star, it helps!
We have a very new and channel. Please come and help us build the .NET AI community.
Install-Package Betalgo.OpenAI
Install-Package Betalgo.OpenAI.Utilities
Maintenance of this project is made possible by all the bug reporters, contributors, and sponsors.
💖 Sponsors:
@betalgo, Laser Cat Eyes
@tylerje, @oferavnery, @MayDay-wpf, @AnukarOP, @Removable, @Scar11
The repository contains a sample project named OpenAI.Playground to help you understand how the library works. However, please exercise caution while experimenting, as some test methods may result in unintended consequences such as file deletion or fine-tuning.
!! It is highly recommended that you use a separate account instead of your primary account while using the playground. Some test methods may add or delete your files and models, potentially causing unwanted issues. !!
Your API Key can be obtained from here: https://platform.openai.com/account/api-keys
Your Organization ID can be found here: https://platform.openai.com/account/org-settings
var openAiService = new OpenAIService(new OpenAiOptions()
{
ApiKey = Environment.GetEnvironmentVariable("MY_OPEN_AI_API_KEY")
});
"OpenAIServiceOptions": {
"ApiKey": "Your api key goes here",
"Organization": "Your Organization Id goes here (optional)",
"UseBeta": "true/false (optional)"
}
(To use user secrets: Right-click your project name in "Solution Explorer", then click "Manage User Secrets". This is a good way to keep your API keys secure.)
serviceCollection.AddOpenAIService();
OR
serviceCollection.AddOpenAIService(settings => { settings.ApiKey = Environment.GetEnvironmentVariable("MY_OPEN_AI_API_KEY"); });
After injecting your service, you can retrieve it from the service provider:
var openAiService = serviceProvider.GetRequiredService<IOpenAIService>();
You can set a default model (optional):
openAiService.SetDefaultModelId(Models.Gpt_4o);
var completionResult = await openAiService.ChatCompletion.CreateCompletion(new ChatCompletionCreateRequest
{
Messages = new List<ChatMessage>
{
ChatMessage.FromSystem("You are a helpful assistant."),
ChatMessage.FromUser("Who won the world series in 2020?"),
ChatMessage.FromAssistant("The Los Angeles Dodgers won the World Series in 2020."),
ChatMessage.FromUser("Where was it played?")
},
Model = Models.Gpt_4o,
});
if (completionResult.Successful)
{
Console.WriteLine(completionResult.Choices.First().Message.Content);
}
Due to time constraints, not all methods have been thoroughly tested or fully documented. If you encounter any issues, please report them or submit a pull request. Your contributions are always appreciated.
Needless to say, I cannot accept responsibility for any damage caused by using the library.
- moved
strict
paremeter fromToolDefinition
toFunctionDefinition
- Added Support for o1 reasing models (
o1-mini
ando1-preview
). - Added
MaxCompletionTokens
forchat completions
. - Added support for
ParallelToolCalls
forchat completions
. - Added support for
ServiceTier
forchat completions
. - Added support for
ChunkingStrategy
inVector Store
andVector Store Files
. - Added support for
Strict
inToolDefinition
. - Added support for
MaxNumberResults
andRankingOptions
forFileSearchTool
. - Added support for
ReasoningTokens
fortoken usage
. - Added support for
ResponseFormatOneOfType
forAssistantResponse.cs
.
For any issues, contributions, or feedback, feel free to reach out or submit a pull request.
Betalgo X: Betalgo (@Betalgo) / X (twitter.com)
Betalgo Linkedin: Betalgo | LinkedIn
Tolga X: Tolga Kayhan (@kayhantolga) / X (twitter.com)
Tolga Linkedin: Tolga Kayhan | LinkedIn