tryAGI.OpenAI
3.6.3
Prefix Reserved
See the version list below for details.
dotnet add package tryAGI.OpenAI --version 3.6.3
NuGet\Install-Package tryAGI.OpenAI -Version 3.6.3
<PackageReference Include="tryAGI.OpenAI" Version="3.6.3" />
paket add tryAGI.OpenAI --version 3.6.3
#r "nuget: tryAGI.OpenAI, 3.6.3"
// Install tryAGI.OpenAI as a Cake Addin #addin nuget:?package=tryAGI.OpenAI&version=3.6.3 // Install tryAGI.OpenAI as a Cake Tool #tool nuget:?package=tryAGI.OpenAI&version=3.6.3
OpenAI
Features 🔥
- Fully generated C# SDK based on official OpenAI OpenAPI specification using OpenApiGenerator
- Same day update to support new features
- Updated and supported automatically if there are no breaking changes
- Contains a supported list of constants such as current prices, models, and other
- Source generator to define functions natively through C# interfaces
- All modern .NET features - nullability, trimming, NativeAOT, etc.
- Support .Net Framework/.Net Standard 2.0
- Support all OpenAI API endpoints including completions, chat, embeddings, images, assistants and more.
- Regularly tested for compatibility with popular custom providers like OpenRouter/DeepSeek
Documentation
Examples and documentation can be found here: https://tryagi.github.io/OpenAI/
Usage
using var api = new OpenAiApi("API_KEY");
string response = await api.Chat.CreateChatCompletionAsync(
messages: ["Generate five random words."],
model: CreateChatCompletionRequestModel.Gpt4oMini);
Console.WriteLine(response); // "apple, banana, cherry, date, elderberry"
var enumerable = api.Chat.CreateChatCompletionAsStreamAsync(
messages: ["Generate five random words."],
model: CreateChatCompletionRequestModel.Gpt4oMini);
await foreach (string response in enumerable)
{
Console.WriteLine(response);
}
It uses three implicit conversions:
- from
string
toChatCompletionRequestUserMessage
. It will always be converted to the user message. - from
ChatCompletionResponseMessage
tostring
. It will always contain the first choice message content. - from
CreateChatCompletionStreamResponse
tostring
. It will always contain the first delta content.
You still can use the full response objects if you need more information, just replace string response
to var response
.
Tools
using OpenAI;
public enum Unit
{
Celsius,
Fahrenheit,
}
public class Weather
{
public string Location { get; set; } = string.Empty;
public double Temperature { get; set; }
public Unit Unit { get; set; }
public string Description { get; set; } = string.Empty;
}
[OpenAiTools(Strict = true)] // false by default. You can't use parameters with default values in Strict mode.
public interface IWeatherFunctions
{
[Description("Get the current weather in a given location")]
public Task<Weather> GetCurrentWeatherAsync(
[Description("The city and state, e.g. San Francisco, CA")] string location,
Unit unit,
CancellationToken cancellationToken = default);
}
public class WeatherService : IWeatherFunctions
{
public Task<Weather> GetCurrentWeatherAsync(string location, Unit unit = Unit.Celsius, CancellationToken cancellationToken = default)
{
return Task.FromResult(new Weather
{
Location = location,
Temperature = 22.0,
Unit = unit,
Description = "Sunny",
});
}
}
using var api = new OpenAiApi("API_KEY");
var service = new WeatherService();
var tools = service.AsTools();
var messages = new List<ChatCompletionRequestMessage>
{
"You are a helpful weather assistant.".AsSystemMessage(),
"What is the current temperature in Dubai, UAE in Celsius?".AsUserMessage(),
};
var model = CreateChatCompletionRequestModel.Gpt4oMini;
var result = await api.Chat.CreateChatCompletionAsync(
messages,
model: model,
tools: tools);
var resultMessage = result.Choices.First().Message;
messages.Add(resultMessage.AsRequestMessage());
foreach (var call in resultMessage.ToolCalls)
{
var json = await service.CallAsync(
functionName: call.Function.Name,
argumentsAsJson: call.Function.Arguments);
messages.Add(json.AsToolMessage(call.Id));
}
var result = await api.Chat.CreateChatCompletionAsync(
messages,
model: model,
tools: tools);
var resultMessage = result.Choices.First().Message;
messages.Add(resultMessage.AsRequestMessage());
> System:
You are a helpful weather assistant.
> User:
What is the current temperature in Dubai, UAE in Celsius?
> Assistant:
call_3sptsiHzKnaxF8bs8BWxPo0B:
GetCurrentWeather({"location":"Dubai, UAE","unit":"celsius"})
> Tool(call_3sptsiHzKnaxF8bs8BWxPo0B):
{"location":"Dubai, UAE","temperature":22,"unit":"celsius","description":"Sunny"}
> Assistant:
The current temperature in Dubai, UAE is 22°C with sunny weather.
Structured Outputs
using OpenAI;
using var api = new OpenAiApi("API_KEY");
var response = await api.Chat.CreateChatCompletionAsAsync<Weather>(
messages: ["Generate random weather."],
model: CreateChatCompletionRequestModel.Gpt4oMini,
jsonSerializerOptions: new JsonSerializerOptions
{
Converters = {new JsonStringEnumConverter()},
});
// or (if you need trimmable/NativeAOT version)
var response = await api.Chat.CreateChatCompletionAsAsync(
jsonTypeInfo: SourceGeneratedContext.Default.Weather,
messages: ["Generate random weather."],
model: CreateChatCompletionRequestModel.Gpt4oMini);
// response.Value1 contains the structured output
// response.Value2 contains the CreateChatCompletionResponse object
Weather:
Location: San Francisco, CA
Temperature: 65
Unit: Fahrenheit
Description: Partly cloudy with a light breeze and occasional sunshine.
Raw Response:
{"Location":"San Francisco, CA","Temperature":65,"Unit":"Fahrenheit","Description":"Partly cloudy with a light breeze and occasional sunshine."}
Additional code for trimmable/NativeAOT version:
[JsonSourceGenerationOptions(Converters = [typeof(JsonStringEnumConverter<Unit>)])]
[JsonSerializable(typeof(Weather))]
public partial class SourceGeneratedContext : JsonSerializerContext;
Custom providers
using OpenAI;
using var api = CustomProviders.GitHubModels("GITHUB_TOKEN");
using var api = CustomProviders.Azure("API_KEY", "ENDPOINT");
using var api = CustomProviders.DeepInfra("API_KEY");
using var api = CustomProviders.DeepSeek("API_KEY");
using var api = CustomProviders.Fireworks("API_KEY");
using var api = CustomProviders.OpenRouter("API_KEY");
using var api = CustomProviders.Together("API_KEY");
Constants
All tryGetXXX
methods return null
if the value is not found.
There also non-try methods that throw an exception if the value is not found.
using OpenAI;
// You can try to get the enum from string using:
var model = CreateChatCompletionRequestModelExtensions.ToEnum("gpt-4o") ?? throw new Exception("Invalid model");
// Chat
var model = CreateChatCompletionRequestModel.Gpt4oMini;
double? priceInUsd = model.TryGetPriceInUsd(
inputTokens: 500,
outputTokens: 500)
double? priceInUsd = model.TryGetFineTunePriceInUsd(
trainingTokens: 500,
inputTokens: 500,
outputTokens: 500)
int contextLength = model.TryGetContextLength() // 128_000
int outputLength = model.TryGetOutputLength() // 16_000
// Embeddings
var model = CreateEmbeddingRequestModel.TextEmbedding3Small;
int? maxInputTokens = model.TryGetMaxInputTokens() // 8191
double? priceInUsd = model.TryGetPriceInUsd(tokens: 500)
// Images
double? priceInUsd = CreateImageRequestModel.DallE3.TryGetPriceInUsd(
size: CreateImageRequestSize.x1024x1024,
quality: CreateImageRequestQuality.Hd)
// Speech to Text
double? priceInUsd = CreateTranscriptionRequestModel.Whisper1.TryGetPriceInUsd(
seconds: 60)
// Text to Speech
double? priceInUsd = CreateSpeechRequestModel.Tts1Hd.TryGetPriceInUsd(
characters: 1000)
Support
Priority place for bugs: https://github.com/tryAGI/OpenAI/issues
Priority place for ideas and general questions: https://github.com/tryAGI/OpenAI/discussions
Discord: https://discord.gg/Ca2xhfBf3v
Acknowledgments
This project is supported by JetBrains through the Open Source Support Program.
This project is supported by CodeRabbit through the Open Source Support Program.
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 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 was computed. |
.NET Framework | net461 was computed. net462 is compatible. 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 4.6.2
- System.Text.Json (>= 8.0.4)
- Tiktoken (>= 2.0.3)
-
.NETStandard 2.0
- System.Text.Json (>= 8.0.4)
- Tiktoken (>= 2.0.3)
-
net6.0
- System.Text.Json (>= 8.0.4)
- Tiktoken (>= 2.0.3)
-
net8.0
- Tiktoken (>= 2.0.3)
NuGet packages (4)
Showing the top 4 NuGet packages that depend on tryAGI.OpenAI:
Package | Downloads |
---|---|
LangChain.Providers.OpenAI
OpenAI API LLM and Chat model provider. |
|
Anyscale
SDK for Anyscale Endpoint that makes it easy and cheap to use LLama 2 |
|
LangChain.Providers.Azure
OpenAI API LLM and Chat model provider. |
|
LangChain.Serve.OpenAI
LangChain Serve as OpenAI sdk compatible API |
GitHub repositories (1)
Showing the top 1 popular GitHub repositories that depend on tryAGI.OpenAI:
Repository | Stars |
---|---|
tryAGI/LangChain
C# implementation of LangChain. We try to be as close to the original as possible in terms of abstractions, but are open to new entities.
|
Version | Downloads | Last updated |
---|---|---|
3.8.1 | 0 | 10/9/2024 |
3.8.1-dev.14 | 55 | 10/2/2024 |
3.8.1-dev.13 | 43 | 10/2/2024 |
3.8.1-dev.6 | 35 | 9/28/2024 |
3.8.1-dev.3 | 42 | 9/28/2024 |
3.8.1-dev.2 | 40 | 9/26/2024 |
3.8.0 | 501 | 9/26/2024 |
3.7.1-dev.14 | 32 | 9/24/2024 |
3.7.1-dev.12 | 46 | 9/23/2024 |
3.7.1-dev.5 | 62 | 9/16/2024 |
3.7.1-dev.3 | 1,386 | 9/15/2024 |
3.7.0 | 278 | 9/14/2024 |
3.6.4-dev.10 | 52 | 9/14/2024 |
3.6.4-dev.9 | 48 | 9/14/2024 |
3.6.4-dev.7 | 40 | 9/13/2024 |
3.6.4-dev.5 | 50 | 9/9/2024 |
3.6.3 | 391 | 9/2/2024 |
3.6.2 | 113 | 9/1/2024 |
3.6.1 | 119 | 9/1/2024 |
3.5.2-dev.24 | 57 | 8/31/2024 |
3.5.2-dev.22 | 48 | 8/31/2024 |
3.5.2-dev.21 | 51 | 8/31/2024 |
3.5.2-dev.14 | 51 | 8/29/2024 |
3.5.2-dev.10 | 72 | 8/24/2024 |
3.5.2-dev.9 | 81 | 8/21/2024 |
3.5.2-dev.7 | 74 | 8/19/2024 |
3.5.2-dev.6 | 67 | 8/19/2024 |
3.5.2-dev.5 | 73 | 8/19/2024 |
3.5.2-dev.2 | 85 | 8/18/2024 |
3.5.1 | 681 | 8/18/2024 |
3.5.1-dev.4 | 70 | 8/18/2024 |
3.5.1-dev.3 | 78 | 8/18/2024 |
3.5.0 | 132 | 8/17/2024 |
3.4.2-dev.5 | 70 | 8/17/2024 |
3.4.2-dev.1 | 71 | 8/17/2024 |
3.4.1 | 217 | 8/16/2024 |
3.4.0 | 132 | 8/16/2024 |
3.3.1-dev.17 | 82 | 8/15/2024 |
3.3.1-dev.16 | 62 | 8/15/2024 |
3.3.1-dev.14 | 65 | 8/15/2024 |
3.3.1-dev.12 | 73 | 8/13/2024 |
3.3.1-dev.11 | 70 | 8/13/2024 |
3.3.1-dev.8 | 64 | 8/12/2024 |
3.3.1-dev.7 | 58 | 8/12/2024 |
3.3.1-dev.1 | 35 | 8/6/2024 |
3.3.0 | 290 | 8/6/2024 |
3.2.2-dev.3 | 30 | 8/6/2024 |
3.2.1 | 796 | 8/6/2024 |
3.2.1-dev.2 | 47 | 8/6/2024 |
3.2.1-dev.1 | 33 | 8/5/2024 |
3.2.0 | 81 | 8/5/2024 |
3.1.1-dev.1 | 35 | 8/4/2024 |
3.1.0 | 152 | 8/1/2024 |
3.0.4-dev.11 | 44 | 8/1/2024 |
3.0.4-dev.9 | 647 | 7/24/2024 |
3.0.4-dev.8 | 106 | 7/23/2024 |
3.0.4-dev.6 | 157 | 7/20/2024 |
3.0.4-dev.5 | 55 | 7/20/2024 |
3.0.4-dev.4 | 55 | 7/20/2024 |
3.0.4-dev.3 | 55 | 7/20/2024 |
3.0.4-dev.2 | 58 | 7/19/2024 |
3.0.4-dev.1 | 54 | 7/18/2024 |
3.0.3 | 150 | 7/18/2024 |
3.0.3-dev.1 | 47 | 7/18/2024 |
3.0.1 | 111 | 7/13/2024 |
3.0.0 | 87 | 7/11/2024 |
3.0.0-alpha.3 | 51 | 7/7/2024 |
3.0.0-alpha.2 | 49 | 7/6/2024 |
2.0.9 | 24,661 | 5/14/2024 |
2.0.8 | 142 | 4/29/2024 |
2.0.7 | 121 | 4/29/2024 |
2.0.6 | 9,149 | 4/22/2024 |
2.0.5 | 613 | 4/10/2024 |
2.0.4 | 356 | 4/4/2024 |
2.0.3 | 123 | 4/3/2024 |
2.0.2 | 199 | 4/3/2024 |
2.0.1 | 128 | 4/2/2024 |
2.0.0 | 300 | 3/22/2024 |
2.0.0-alpha.10 | 2,659 | 2/23/2024 |
2.0.0-alpha.9 | 14,144 | 1/27/2024 |
2.0.0-alpha.8 | 55 | 1/27/2024 |
2.0.0-alpha.7 | 100 | 1/20/2024 |
2.0.0-alpha.5 | 508 | 12/5/2023 |
2.0.0-alpha.4 | 186 | 11/16/2023 |
2.0.0-alpha.3 | 96 | 11/16/2023 |
2.0.0-alpha.2 | 65 | 11/16/2023 |
2.0.0-alpha.1 | 62 | 11/15/2023 |
2.0.0-alpha.0 | 60 | 11/15/2023 |
1.8.2 | 62,070 | 10/13/2023 |
1.8.1 | 445 | 10/11/2023 |
1.8.0 | 281 | 9/29/2023 |
1.7.2 | 1,646 | 8/15/2023 |
1.7.1 | 160 | 8/15/2023 |
1.7.0 | 329 | 8/15/2023 |
1.6.3 | 1,890 | 7/29/2023 |
1.6.1 | 154 | 7/29/2023 |
1.6.0 | 289 | 7/29/2023 |
1.5.0 | 545 | 7/13/2023 |
1.4.1 | 169 | 7/12/2023 |
1.4.0 | 165 | 7/12/2023 |
1.3.0 | 167 | 7/12/2023 |
1.2.0 | 587 | 7/5/2023 |
1.1.2 | 320 | 6/30/2023 |
1.1.1 | 166 | 6/30/2023 |
1.1.0 | 162 | 6/29/2023 |
1.0.0 | 176 | 6/28/2023 |
0.9.0 | 216 | 6/24/2023 |
0.0.0-dev.150 | 53 | 7/18/2024 |
0.0.0-dev | 102 | 9/14/2024 |