Skip to main content

IEmbeddingGenerationService

Namespace: Wisej.AI.Services

Assembly: Wisej.AI

Represents a service capable of generating embeddings from provided text chunks.

public interface IEmbeddingGenerationService

Properties

Endpoint

SmartEndpoint: Gets or sets the endpoint configuration for the embedding generation service.

MaxArraySize

Int32: Gets or sets the maximum number of text chunks that can be sent as an array to the provider.

VectorSize

Int32: Gets or sets the dimension of the embedding vectors.

Methods

EmbedAsync(chunks)

Asynchronously generates an embedding from the specified array of text chunks.

ParameterTypeDescription
chunksString[]An array of strings representing the text chunks to be embedded. The array can be empty.

Returns: Task<Embedding>. A task representing the asynchronous operation, with a result of type Embedding.

This method processes the supplied text chunks and returns an embedding that captures the semantic information contained within the text. Usage example:


IEmbeddingGenerationService embeddingService = new EmbeddingGenerationServiceImplementation();
embeddingService.Endpoint = new SmartEndpoint("http://example.com/api");
string[] textChunks = { "This is a sample text.", "Another piece of text." };
Embedding result = await embeddingService.EmbedAsync(textChunks);

Note that the quality and characteristics of the generated embedding depend on the implementation details of the embedding service.

Implemented By

NameDescription
DefaultEmbeddingGenerationServiceRepresents a service that provides functionality to generate embeddings for given text inputs using a SmartEndpoint
HuggingFaceEmbeddingGenerationServiceRepresents a service for generating embeddings using the Hugging Face API.