Rystem.OpenAi 1.0.5

Unofficial Fluent C#/.NET SDK for accessing the OpenAI API

A simple C# .NET wrapper library to use with OpenAI's API.

Help the project

Contribute: https://www.buymeacoffee.com/keyserdsoze

Contribute: https://patreon.com/Rystem

Requirements

This library targets .NET standard 2.1 and above.

Adv

Watch out my Rystem framework to be able to do .Net webapp faster (easy integration with repository pattern or CQRS for your Azure services).

What is Rystem?

Setup

Install package Rystem.OpenAi from Nuget.
Here's how via command line:

Install-Package Rystem.OpenAi

Documentation

Table of Contents

• Dependency Injection
  • Azure
• Models
  • List Models
  • Retrieve Models
• Completions
  • Streaming
• Chat
  • Streaming
• Edits
• Images
  • Create Image
  • Create Image Edit
  • Create Image Variation
• Embeddings
  • Create Embedding
• Audio
  • Create Transcription
  • Create Translation
• File
  • List Files
  • Upload File
  • Delete File
  • Retrieve File Info
  • Retrieve File Content
• Fine-Tunes
  • Create Fine Tune
  • List Fine Tune
  • Retrieve Fine Tune
  • Cancel Fine Tune
  • List Fine Tune Events
  • List Fine Tune Events As Stream
  • Delete Fine Tune
• Moderations
  • Create Moderation
• Utilities
  • Cosine similarity

Dependency Injection

Add to service collection the OpenAi service in your DI

var apiKey = configuration["Azure:ApiKey"];
services.AddOpenAi(settings =>
{
    settings.ApiKey = apiKey;
});

Dependency Injection With Azure

Add to service collection the OpenAi service in your DI with Azure integration

When you want to use the integration with Azure, you need to specify all the models you're going to use. In the example you may find the model name for DavinciText3. You still may add a custom model, with AddDeploymentCustomModel.

builder.Services.AddOpenAi(settings =>
{
    settings.ApiKey = apiKey;
    settings.Azure.ResourceName = "AzureResourceName (Name of your deployed service on Azure)";
    settings.Azure
        .AddDeploymentTextModel("Test (The name from column 'Model deployment name' in Model deployments blade in your Azure service)", TextModelType.DavinciText3);
});

Add to service collection the OpenAi service in your DI with Azure integration and app registration

See how to create an app registration here.

var resourceName = builder.Configuration["Azure:ResourceName"];
var clientId = builder.Configuration["AzureAd:ClientId"];
var clientSecret = builder.Configuration["AzureAd:ClientSecret"];
var tenantId = builder.Configuration["AzureAd:TenantId"];
builder.Services.AddOpenAi(settings =>
{
    settings.Azure.ResourceName = resourceName;
    settings.Azure.AppRegistration.ClientId = clientId;
    settings.Azure.AppRegistration.ClientSecret = clientSecret;
    settings.Azure.AppRegistration.TenantId = tenantId;
    settings.Azure
        .AddDeploymentTextModel("Test", TextModelType.CurieText)
        .AddDeploymentTextModel("text-davinci-002", TextModelType.DavinciText2)
        .AddDeploymentEmbeddingModel("Test", EmbeddingModelType.AdaTextEmbedding);
});

Add to service collection the OpenAi service in your DI with Azure integration and system assigned managed identity

See how to create a managed identity here.
System Assigned Managed Identity

var resourceName = builder.Configuration["Azure:ResourceName"];
builder.Services.AddOpenAi(settings =>
{
    settings.Azure.ResourceName = resourceName;
    settings.Azure.ManagedIdentity.UseDefault = true;
    settings.Azure
        .AddDeploymentTextModel("Test", TextModelType.CurieText)
        .AddDeploymentTextModel("text-davinci-002", TextModelType.DavinciText2)
        .AddDeploymentEmbeddingModel("Test", EmbeddingModelType.AdaTextEmbedding);
});

Add to service collection the OpenAi service in your DI with Azure integration and user assigned managed identity

See how to create a managed identity here.
User Assigned Managed Identity

var resourceName = builder.Configuration["Azure:ResourceName"];
var managedIdentityId = builder.Configuration["ManagedIdentity:ClientId"];
builder.Services.AddOpenAi(settings =>
{
    settings.Azure.ResourceName = resourceName;
    settings.Azure.ManagedIdentity.Id = managedIdentityId;
    settings.Azure
        .AddDeploymentTextModel("Test", TextModelType.CurieText)
        .AddDeploymentTextModel("text-davinci-002", TextModelType.DavinciText2)
        .AddDeploymentEmbeddingModel("Test", EmbeddingModelType.AdaTextEmbedding);
});

Models

📖 Back to summary
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.
You may find more details here, and here samples from unit test.

List Models

Lists the currently available models, and provides basic information about each one such as the owner and availability.

IOpenAiApi _openAiApi;
var results = await _openAiApi.Model.ListAsync();

Retrieve Models

Retrieves a model instance, providing basic information about the model such as the owner and permissioning.

IOpenAiApi _openAiApi;
var result = await _openAiApi.Model.RetrieveAsync(TextModelType.DavinciText3.ToModelId());

Completions

📖 Back to summary
Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.
You may find more details here, and here samples from unit test

IOpenAiApi _openAiApi;
var results = await _openAiApi.Completion
    .Request("One Two Three Four Five Six Seven Eight Nine One Two Three Four Five Six Seven Eight")
    .WithModel(TextModelType.CurieText)
    .WithTemperature(0.1)
    .SetMaxTokens(5)
    .ExecuteAsync();

Streaming

IOpenAiApi _openAiApi;
var results = new List<CompletionResult>();
        await foreach (var x in _openAiApi.Completion
           .Request("Today is Monday, tomorrow is", "10 11 12 13 14")
           .WithTemperature(0)
           .SetMaxTokens(3)
           .ExecuteAsStreamAsync())
        {
            results.Add(x);
        }

Chat

📖 Back to summary
Given a chat conversation, the model will return a chat completion response.
You may find more details here, and here samples from unit test.

IOpenAiApi _openAiApi;
var results = await _openAiApi.Chat
        .Request(new ChatMessage { Role = ChatRole.User, Content = "Hello!! How are you?" })
        .WithModel(ChatModelType.Gpt4)
        .WithTemperature(1)
        .ExecuteAsync();

Chat Streaming

IOpenAiApi _openAiApi;
var results = new List<ChatResult>();
    await foreach (var x in _openAiApi.Chat
        .Request(new ChatMessage { Role = ChatRole.User, Content = "Hello!! How are you?" })
        .WithModel(ChatModelType.Gpt35Turbo)
        .WithTemperature(1)
        .ExecuteAsStreamAsync())
        {
            results.Add(x);
        }

Edits

Given a prompt and an instruction, the model will return an edited version of the prompt. You may find more details here, and here samples from unit test.

IOpenAiApi _openAiApi;
var results = await _openAiApi.Edit
        .Request("Fix the spelling mistakes")
        .WithModel(EditModelType.TextDavinciEdit)
        .SetInput("What day of the wek is it?")
        .WithTemperature(0.5)
        .ExecuteAsync();

Images

📖 Back to summary
Given a prompt and/or an input image, the model will generate a new image.
You may find more details here, and here samples from unit test.

Create Image

Creates an image given a prompt.

IOpenAiApi _openAiApi;
var response = await _openAiApi.Image
    .Generate("A cute baby sea otter")
    .WithSize(ImageSize.Small)
    .ExecuteAsync();    

Download directly and save as stream

IOpenAiApi _openAiApi;
var streams = new List<Stream>();
await foreach (var image in _openAiApi.Image
    .Generate("A cute baby sea otter")
    .WithSize(ImageSize.Small)
    .DownloadAsync())
{
    streams.Add(image);
}

Create Image Edit

Creates an edited or extended image given an original image and a prompt.

IOpenAiApi _openAiApi;
var response = await _openAiApi.Image
    .Generate("A cute baby sea otter wearing a beret")
    .EditAndTrasformInPng(editableFile, "otter.png")
    .WithSize(ImageSize.Small)
    .WithNumberOfResults(2)
    .ExecuteAsync();

Create Image Variation

Creates a variation of a given image.

IOpenAiApi _openAiApi;
var response = await _openAiApi.Image
    .VariateAndTransformInPng(editableFile, "otter.png")
    .WithSize(ImageSize.Small)
    .WithNumberOfResults(1)
    .ExecuteAsync();

Embeddings

📖 Back to summary
Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
You may find more details here, and here samples from unit test.

Create Embedding

Creates an embedding vector representing the input text.

IOpenAiApi _openAiApi;
var results = await _openAiApi.Embedding
    .Request("A test text for embedding")
    .ExecuteAsync();

Distance for embedding

For searching over many vectors quickly, we recommend using a vector database. You can find examples of working with vector databases and the OpenAI API in our Cookbook on GitHub. Vector database options include:

• Pinecone, a fully managed vector database
• Weaviate, an open-source vector search engine
• Redis as a vector database
• Qdrant, a vector search engine
• Milvus, a vector database built for scalable similarity search
• Chroma, an open-source embeddings store

Which distance function should I use?

We recommend cosine similarity. The choice of distance function typically doesn’t matter much.

OpenAI embeddings are normalized to length 1, which means that:

Cosine similarity can be computed slightly faster using just a dot product Cosine similarity and Euclidean distance will result in the identical rankings

You may use the utility service in this repository to calculate in C# the distance with Cosine similarity

Audio

📖 Back to summary
You may find more details here, and here samples from unit test.

Create Transcription

Transcribes audio into the input language.

IOpenAiApi _openAiApi;
var results = await _openAiApi.Audio
    .Request(editableFile, "default.mp3")
    .TranscriptAsync();

Create Translation

Translates audio into English.

IOpenAiApi _openAiApi;
var results = await _openAiApi.Audio
    .Request(editableFile, "default.mp3")
    .TranslateAsync();

File

📖 Back to summary
Files are used to upload documents that can be used with features like Fine-tuning.
You may find more details here, and here samples from unit test.

List files

Returns a list of files that belong to the user's organization.

  IOpenAiApi _openAiApi;
  var results = await _openAiApi.File
            .AllAsync();

Upload file

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.

IOpenAiApi _openAiApi;
var uploadResult = await _openAiApi.File
        .UploadFileAsync(editableFile, name);

Delete file

Delete a file.

IOpenAiApi _openAiApi;
var deleteResult = await _openAiApi.File
        .DeleteAsync(uploadResult.Id);

Retrieve file

Returns information about a specific file.

IOpenAiApi _openAiApi;
var retrieve = await _openAiApi.File
        .RetrieveAsync(uploadResult.Id);

Retrieve file content

Returns the contents of the specified file

IOpenAiApi _openAiApi;
var contentRetrieve = await _openAiApi.File
        .RetrieveFileContentAsStringAsync(uploadResult.Id);

Fine-Tunes

📖 Back to summary
Manage fine-tuning jobs to tailor a model to your specific training data.
You may find more details here, and here samples from unit test.

Create fine-tune

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.

IOpenAiApi _openAiApi;
var createResult = await _openAiApi.FineTune
                            .Create(fileId)
                            .ExecuteAsync();

List fine-tunes

List your organization's fine-tuning jobs

IOpenAiApi _openAiApi;
var allFineTunes = await _openAiApi.FineTune
                    .ListAsync();

Retrieve fine-tune

Gets info about the fine-tune job.

IOpenAiApi _openAiApi;
var retrieveFineTune = await _openAiApi.FineTune
                        .RetrieveAsync(fineTuneId);

Cancel fine-tune

Immediately cancel a fine-tune job.

IOpenAiApi _openAiApi;
var cancelResult = await _openAiApi.FineTune
                        .CancelAsync(fineTuneId);

List fine-tune events

Get fine-grained status updates for a fine-tune job.

IOpenAiApi _openAiApi;
var events = await _openAiApi.FineTune
                    .ListEventsAsync(fineTuneId);

List fine-tune events as stream

Get fine-grained status updates for a fine-tune job.

IOpenAiApi _openAiApi;
var events = await _openAiApi.FineTune
                    .ListEventsAsStreamAsync(fineTuneId);

Delete fine-tune model

Delete a fine-tuned model. You must have the Owner role in your organization.

IOpenAiApi _openAiApi;
var deleteResult = await _openAiApi.File
    .DeleteAsync(fileId);

Moderations

📖 Back to summary
Given a input text, outputs if the model classifies it as violating OpenAI's content policy.
You may find more details here, and here samples from unit test.

Create moderation

Classifies if text violates OpenAI's Content Policy

IOpenAiApi _openAiApi;
var results = await _openAiApi.Moderation
        .Create("I want to kill them.")
        .WithModel(ModerationModelType.TextModerationStable)
        .ExecuteAsync();

Utilities

📖 Back to summary
Utilities for OpenAi, you can inject the interface IOpenAiUtility everywhere you need it. In IOpenAiUtility you can find:

Cosine Similarity

📖 Back to embeddings
In data analysis, cosine similarity is a measure of similarity between two non-zero vectors defined in an inner product space. Cosine similarity is the cosine of the angle between the vectors; that is, it is the dot product of the vectors divided by the product of their lengths. It follows that the cosine similarity does not depend on the magnitudes of the vectors, but only on their angle. The cosine similarity always belongs to the interval [−1,1]. For example, two proportional vectors have a cosine similarity of 1, two orthogonal vectors have a similarity of 0, and two opposite vectors have a similarity of -1. In some contexts, the component values of the vectors cannot be negative, in which case the cosine similarity is bounded in [0,1]. Here an example from Unit test.

IOpenAiUtility _openAiUtility;
var resultOfCosineSimilarity = _openAiUtility.CosineSimilarity(results.Data.First().Embedding, results.Data.First().Embedding);
Assert.True(resultOfCosineSimilarity >= 1);