Package org.springframework.ai.bedrock.titan

Class BedrockTitanEmbeddingModel

java.lang.Object

org.springframework.ai.embedding.AbstractEmbeddingModel

org.springframework.ai.bedrock.titan.BedrockTitanEmbeddingModel

All Implemented Interfaces:

org.springframework.ai.embedding.EmbeddingModel, org.springframework.ai.model.Model<org.springframework.ai.embedding.EmbeddingRequest,org.springframework.ai.embedding.EmbeddingResponse>

public class BedrockTitanEmbeddingModel
extends org.springframework.ai.embedding.AbstractEmbeddingModel

EmbeddingModel implementation that uses the Bedrock Titan Embedding API. Titan Embedding supports text and image (encoded in base64) inputs. Note: Titan Embedding does not support batch embedding.

Since:

0.8.0

Author:

Christian Tzolov, Wei Jiang

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static enum	BedrockTitanEmbeddingModel.InputType

Field Summary

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

embeddingDimensions

Constructor Summary

Constructors

Constructor	Description
BedrockTitanEmbeddingModel(TitanEmbeddingBedrockApi titanEmbeddingBedrockApi, io.micrometer.observation.ObservationRegistry observationRegistry)

Method Summary

Modifier and Type	Method	Description
org.springframework.ai.embedding.EmbeddingResponse	call(org.springframework.ai.embedding.EmbeddingRequest request)
int	dimensions()
float[]	embed(org.springframework.ai.document.Document document)
BedrockTitanEmbeddingModel	withInputType(BedrockTitanEmbeddingModel.InputType inputType)	Titan Embedding API input types.

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

Constructor Details

BedrockTitanEmbeddingModel

public BedrockTitanEmbeddingModel(TitanEmbeddingBedrockApi titanEmbeddingBedrockApi,
 io.micrometer.observation.ObservationRegistry observationRegistry)

Method Details

withInputType

public BedrockTitanEmbeddingModel withInputType(BedrockTitanEmbeddingModel.InputType inputType)

Titan Embedding API input types. Could be either text or image (encoded in base64).

Parameters:

inputType - the input type to use.

embed

public float[] embed(org.springframework.ai.document.Document document)

call

public org.springframework.ai.embedding.EmbeddingResponse call(org.springframework.ai.embedding.EmbeddingRequest request)

dimensions

public int dimensions()

Specified by:

dimensions in interface org.springframework.ai.embedding.EmbeddingModel

Overrides:

dimensions in class org.springframework.ai.embedding.AbstractEmbeddingModel