EmbeddingsClient Class

Reference

Definition

Namespace:: Azure.AI.Inference

Assembly:: Azure.AI.Inference.dll

Package:: Azure.AI.Inference v1.0.0-beta.2

Source:: EmbeddingsClient.cs

Important

Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.

The Embeddings service client.

public class EmbeddingsClient

type EmbeddingsClient = class

Public Class EmbeddingsClient

Inheritance: Object
EmbeddingsClient

Constructors

EmbeddingsClient()	Initializes a new instance of EmbeddingsClient for mocking.
EmbeddingsClient(Uri, AzureKeyCredential, AzureAIInferenceClientOptions)	Initializes a new instance of EmbeddingsClient.
EmbeddingsClient(Uri, AzureKeyCredential)	Initializes a new instance of EmbeddingsClient.
EmbeddingsClient(Uri, TokenCredential, AzureAIInferenceClientOptions)	Initializes a new instance of EmbeddingsClient.
EmbeddingsClient(Uri, TokenCredential)	Initializes a new instance of EmbeddingsClient.

Properties

Pipeline

The HTTP pipeline for sending and receiving REST requests and responses.

Methods

Embed(EmbeddingsOptions, CancellationToken)	Return the embedding vectors for given text prompts. The method makes a REST API call to the `/embeddings` route on the given endpoint.
Embed(RequestContent, String, RequestContext)	[Protocol Method] Return the embedding vectors for given text prompts. The method makes a REST API call to the `/embeddings` route on the given endpoint. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios. Please try the simpler Embed(EmbeddingsOptions, CancellationToken) convenience overload with strongly typed models first.
EmbedAsync(EmbeddingsOptions, CancellationToken)	Return the embedding vectors for given text prompts. The method makes a REST API call to the `/embeddings` route on the given endpoint.
EmbedAsync(RequestContent, String, RequestContext)	[Protocol Method] Return the embedding vectors for given text prompts. The method makes a REST API call to the `/embeddings` route on the given endpoint. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios. Please try the simpler EmbedAsync(EmbeddingsOptions, CancellationToken) convenience overload with strongly typed models first.
GetModelInfo(CancellationToken)	Returns information about the AI model. The method makes a REST API call to the `/info` route on the given endpoint. This method will only work when using Serverless API or Managed Compute endpoint. It will not work for GitHub Models endpoint or Azure OpenAI endpoint.
GetModelInfo(RequestContext)	[Protocol Method] Returns information about the AI model. The method makes a REST API call to the `/info` route on the given endpoint. This method will only work when using Serverless API or Managed Compute endpoint. It will not work for GitHub Models endpoint or Azure OpenAI endpoint. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios. Please try the simpler GetModelInfo(CancellationToken) convenience overload with strongly typed models first.
GetModelInfoAsync(CancellationToken)	Returns information about the AI model. The method makes a REST API call to the `/info` route on the given endpoint. This method will only work when using Serverless API or Managed Compute endpoint. It will not work for GitHub Models endpoint or Azure OpenAI endpoint.
GetModelInfoAsync(RequestContext)	[Protocol Method] Returns information about the AI model. The method makes a REST API call to the `/info` route on the given endpoint. This method will only work when using Serverless API or Managed Compute endpoint. It will not work for GitHub Models endpoint or Azure OpenAI endpoint. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios. Please try the simpler GetModelInfoAsync(CancellationToken) convenience overload with strongly typed models first.

Applies to

Partilhar via