Package org.springframework.ai.vertexai.embedding.text

Class VertexAiTextEmbeddingModel

java.lang.Object

org.springframework.ai.embedding.AbstractEmbeddingModel

org.springframework.ai.vertexai.embedding.text.VertexAiTextEmbeddingModel

All Implemented Interfaces:

EmbeddingModel, Model<EmbeddingRequest,EmbeddingResponse>

public class VertexAiTextEmbeddingModel
extends AbstractEmbeddingModel

A class representing a Vertex AI Text Embedding Model.

Since:

1.0.0

Author:

Christian Tzolov, Mark Pollack

Field Summary

Fields

Modifier and Type	Field	Description
final VertexAiTextEmbeddingOptions	defaultOptions

Fields inherited from class org.springframework.ai.embedding.AbstractEmbeddingModel

embeddingDimensions

Constructor Summary

Constructors

Constructor	Description
VertexAiTextEmbeddingModel(VertexAiEmbeddingConnectionDetails connectionDetails, VertexAiTextEmbeddingOptions defaultEmbeddingOptions)
VertexAiTextEmbeddingModel(VertexAiEmbeddingConnectionDetails connectionDetails, VertexAiTextEmbeddingOptions defaultEmbeddingOptions, org.springframework.retry.support.RetryTemplate retryTemplate)
VertexAiTextEmbeddingModel(VertexAiEmbeddingConnectionDetails connectionDetails, VertexAiTextEmbeddingOptions defaultEmbeddingOptions, org.springframework.retry.support.RetryTemplate retryTemplate, io.micrometer.observation.ObservationRegistry observationRegistry)

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(Document document)	Embeds the given document's content into a vector.
protected com.google.cloud.aiplatform.v1.PredictRequest.Builder	getPredictRequestBuilder(EmbeddingRequest request, com.google.cloud.aiplatform.v1.EndpointName endpointName, VertexAiTextEmbeddingOptions finalOptions)
void	setObservationConvention(EmbeddingModelObservationConvention observationConvention)	Use the provided convention for reporting observation data

Methods inherited from class org.springframework.ai.embedding.AbstractEmbeddingModel

dimensions

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, embed, embedForResponse

Field Details

defaultOptions

public final VertexAiTextEmbeddingOptions defaultOptions

Constructor Details

VertexAiTextEmbeddingModel

public VertexAiTextEmbeddingModel(VertexAiEmbeddingConnectionDetails connectionDetails,
 VertexAiTextEmbeddingOptions defaultEmbeddingOptions)

VertexAiTextEmbeddingModel

public VertexAiTextEmbeddingModel(VertexAiEmbeddingConnectionDetails connectionDetails,
 VertexAiTextEmbeddingOptions defaultEmbeddingOptions,
 org.springframework.retry.support.RetryTemplate retryTemplate)

VertexAiTextEmbeddingModel

public VertexAiTextEmbeddingModel(VertexAiEmbeddingConnectionDetails connectionDetails,
 VertexAiTextEmbeddingOptions defaultEmbeddingOptions,
 org.springframework.retry.support.RetryTemplate retryTemplate,
 io.micrometer.observation.ObservationRegistry observationRegistry)

Method Details

embed

public float[] embed(Document document)

Description copied from interface: EmbeddingModel

Embeds the given document's content into a vector.

Parameters:

document - the document 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.

Parameters:

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

Returns:

the response from the AI model

getPredictRequestBuilder

protected com.google.cloud.aiplatform.v1.PredictRequest.Builder getPredictRequestBuilder(EmbeddingRequest request,
 com.google.cloud.aiplatform.v1.EndpointName endpointName,
 VertexAiTextEmbeddingOptions finalOptions)

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

Overrides:

dimensions in class AbstractEmbeddingModel

Returns:

the number of dimensions of the embedded vectors.

setObservationConvention

public void setObservationConvention(EmbeddingModelObservationConvention observationConvention)

Use the provided convention for reporting observation data

Parameters:

observationConvention - The provided convention