Package org.springframework.ai.test.vectorstore

Class FixedDimensionEmbeddingModel

java.lang.Object

org.springframework.ai.test.vectorstore.FixedDimensionEmbeddingModel

All Implemented Interfaces:

EmbeddingModel, Model<EmbeddingRequest,EmbeddingResponse>

public final class FixedDimensionEmbeddingModel
extends Object
implements EmbeddingModel

A minimal deterministic EmbeddingModel that returns a constant vector of a configured dimension, for tests that must not depend on a hosted embedding provider.

It is the query-side model for the AbstractVectorStoreUpsertTests suite: upsert supplies its own vectors, and the suite reads back with similarityThresholdAll() regardless of ranking, so a constant vector is sufficient and no API key is needed. Wire it into a store's upsert integration test and size the store's index to dimensions().

Since:

2.1.0

Author:

Soby Chacko

Constructor Summary

Constructors

Constructor	Description
FixedDimensionEmbeddingModel(int dimensions)

Method Summary

Modifier and Type	Method	Description
EmbeddingResponse	call(EmbeddingRequest request)	Executes a method call to the AI model.
int	dimensions()	Get the number of dimensions of the embedded vectors.
float[]	embed(String text)	Embeds the given text into a vector.
float[]	embed(Document document)	Embeds the given document's content into a vector.

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

embed, embed, embedForResponse, getEmbeddingContent

Constructor Details

FixedDimensionEmbeddingModel

public FixedDimensionEmbeddingModel(int dimensions)

Method Details

embed

public float[] embed(Document document)

Description copied from interface: EmbeddingModel

Embeds the given document's content into a vector.

Specified by:

embed in interface EmbeddingModel

Parameters:

document - the document to embed.

Returns:

the embedded vector.

embed

public float[] embed(String text)

Description copied from interface: EmbeddingModel

Embeds the given text into a vector.

Specified by:

embed in interface EmbeddingModel

Parameters:

text - the text to embed.

Returns:

the embedded vector.

call

public EmbeddingResponse call(EmbeddingRequest request)

Description copied from interface: Model

Executes a method call to the AI model.

Specified by:

call in interface EmbeddingModel

Specified by:

call in interface Model<EmbeddingRequest,EmbeddingResponse>

Parameters:

request - the request object to be sent to the AI model

Returns:

the response from the AI model

dimensions

public int dimensions()

Description copied from interface: EmbeddingModel

Get the number of dimensions of the embedded vectors. Note that by default, this method will call the remote Embedding endpoint to get the dimensions of the embedded vectors. If the dimensions are known ahead of time, it is recommended to override this method.

Specified by:

dimensions in interface EmbeddingModel

Returns:

the number of dimensions of the embedded vectors.