Package org.springframework.ai.embedding

Class AbstractEmbeddingModel

java.lang.Object

org.springframework.ai.embedding.AbstractEmbeddingModel

All Implemented Interfaces:

EmbeddingModel, Model<EmbeddingRequest,EmbeddingResponse>

Direct Known Subclasses:

AzureOpenAiEmbeddingModel, BedrockCohereEmbeddingModel, BedrockTitanEmbeddingModel, MiniMaxEmbeddingModel, MistralAiEmbeddingModel, OCIEmbeddingModel, OllamaEmbeddingModel, OpenAiEmbeddingModel, PostgresMlEmbeddingModel, QianFanEmbeddingModel, TransformersEmbeddingModel, VertexAiPaLm2EmbeddingModel, VertexAiTextEmbeddingModel, WatsonxAiEmbeddingModel, ZhiPuAiEmbeddingModel

public abstract class AbstractEmbeddingModel
extends Object
implements EmbeddingModel

Abstract implementation of the EmbeddingModel interface that provides dimensions calculation caching.

Author:

Christian Tzolov

Field Summary

Fields

Modifier and Type	Field	Description
protected final AtomicInteger	embeddingDimensions

Constructor Summary

Constructors

Constructor	Description
AbstractEmbeddingModel()

Method Summary

Modifier and Type	Method	Description
int	dimensions()
static int	dimensions(EmbeddingModel embeddingModel, String modelName, String dummyContent)	Return the dimension of the requested embedding generative name.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.springframework.ai.embedding.EmbeddingModel

call, embed, embed, embed, embed, embedForResponse

Field Details

embeddingDimensions

protected final AtomicInteger embeddingDimensions

Constructor Details

AbstractEmbeddingModel

public AbstractEmbeddingModel()

Method Details

dimensions

public static int dimensions(EmbeddingModel embeddingModel,
 String modelName,
 String dummyContent)

Return the dimension of the requested embedding generative name. If the generative name is unknown uses the EmbeddingModel to perform a dummy EmbeddingModel#embed and count the response dimensions.

Parameters:

embeddingModel - Fall-back client to determine, empirically the dimensions.

modelName - Embedding generative name to retrieve the dimensions for.

dummyContent - Dummy content to use for the empirical dimension calculation.

Returns:

Returns the embedding dimensions for the modelName.

dimensions

public int dimensions()

Specified by:

dimensions in interface EmbeddingModel

Returns:

the number of dimensions of the embedded vectors. It is generative specific.