Class EmbeddingsEndpoint

Namespace

OpenAI.Embeddings

Assembly

OpenAI-DotNet.dll

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
https://platform.openai.com/docs/guides/embeddings

public sealed class EmbeddingsEndpoint : OpenAIBaseEndpoint

Inheritance

object

OpenAIBaseEndpoint

EmbeddingsEndpoint

Inherited Members

OpenAIBaseEndpoint.EnableDebug

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Constructors

EmbeddingsEndpoint(OpenAIClient)

public EmbeddingsEndpoint(OpenAIClient client)

Parameters

client OpenAIClient

Properties

IsAzureDeployment

Indicates if the endpoint has an Azure Deployment.

protected override bool? IsAzureDeployment { get; }

Property Value

bool?

Remarks

If the endpoint is an Azure deployment, is true. If it is not an Azure deployment, is false. If it is not an Azure supported Endpoint, is null.

Root

The root endpoint address.

protected override string Root { get; }

Property Value

string

Methods

CreateEmbeddingAsync(EmbeddingsRequest, CancellationToken)

Creates an embedding vector representing the input text.

public Task<EmbeddingsResponse> CreateEmbeddingAsync(EmbeddingsRequest request, CancellationToken cancellationToken = default)

Parameters

request EmbeddingsRequest

EmbeddingsRequest.

cancellationToken CancellationToken

Optional, CancellationToken.

Returns

Task<EmbeddingsResponse>

EmbeddingsResponse.

CreateEmbeddingAsync(IEnumerable<string>, string, string, int?, CancellationToken)

Creates an embedding vector representing the input text.

public Task<EmbeddingsResponse> CreateEmbeddingAsync(IEnumerable<string> input, string model = null, string user = null, int? dimensions = null, CancellationToken cancellationToken = default)

Parameters

input IEnumerable<string>

Input text to get embeddings for, encoded as a string or array of tokens. To get embeddings for multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed 8192 tokens in length.

model string

ID of the model to use. Defaults to: text-embedding-ada-002

user string

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

dimensions int?

The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models

cancellationToken CancellationToken

Optional, CancellationToken.

Returns

Task<EmbeddingsResponse>

EmbeddingsResponse.

CreateEmbeddingAsync(string, string, string, int?, CancellationToken)

Creates an embedding vector representing the input text.

public Task<EmbeddingsResponse> CreateEmbeddingAsync(string input, string model = null, string user = null, int? dimensions = null, CancellationToken cancellationToken = default)

Parameters

input string

Input text to get embeddings for, encoded as a string or array of tokens. To get embeddings for multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed 8192 tokens in length.

model string

ID of the model to use. Defaults to: text-embedding-ada-002

user string

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

dimensions int?

The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models

cancellationToken CancellationToken

Optional, CancellationToken.

Returns

Task<EmbeddingsResponse>

EmbeddingsResponse.