Titan Embeddings

提供 Bedrock Titan Embedding 模型。 Amazon Titan 基础模型 (FM) 通过完全托管的 API 为客户提供广泛的高性能图像、多模态嵌入和文本模型选择。Amazon Titan 模型由 AWS 创建，并使用大型数据集进行预训练，使其成为功能强大、通用型模型，旨在支持各种用例，同时支持负责任地使用 AI。您可以按原样使用它们，也可以使用自己的数据私下自定义它们。

Provides Bedrock Titan Embedding model. Amazon Titan foundation models (FMs) provide customers with a breadth of high-performing image, multimodal embeddings, and text model choices, via a fully managed API. Amazon Titan models are created by AWS and pretrained on large datasets, making them powerful, general-purpose models built to support a variety of use cases, while also supporting the responsible use of AI. Use them as is or privately customize them with your own data.

Bedrock Titan Embedding 支持文本和图像嵌入。

Bedrock Titan Embedding supports Text and Image embedding.

Bedrock Titan Embedding 并不支持批处理嵌入。

Bedrock Titan Embedding does NOT support batch embedding.

AWS Bedrock Titan Model Page 和 Amazon Bedrock User Guide 包含有关如何使用 AWS 托管模型的详细信息。

The AWS Bedrock Titan Model Page and Amazon Bedrock User Guide contains detailed information on how to use the AWS hosted model.

Prerequisites

请参阅 Spring AI documentation on Amazon Bedrock 以设置 API 访问。

Refer to the Spring AI documentation on Amazon Bedrock for setting up API access.

Add Repositories and BOM

Spring AI 工件发布在 Maven Central 和 Spring Snapshot 存储库中。请参阅“添加 Spring AI 仓库”部分，将这些仓库添加到您的构建系统。

Spring AI artifacts are published in Maven Central and Spring Snapshot repositories. Refer to the Artifact Repositories section to add these repositories to your build system.

为了帮助进行依赖项管理，Spring AI 提供了一个 BOM（物料清单）以确保在整个项目中使用一致版本的 Spring AI。有关将 Spring AI BOM 添加到你的构建系统的说明，请参阅 Dependency Management 部分。

To help with dependency management, Spring AI provides a BOM (bill of materials) to ensure that a consistent version of Spring AI is used throughout the entire project. Refer to the Dependency Management section to add the Spring AI BOM to your build system.

Auto-configuration

Spring AI 自动配置、启动器模块的工件名称发生了重大变化。请参阅 upgrade notes 以获取更多信息。

There has been a significant change in the Spring AI auto-configuration, starter modules' artifact names. Please refer to the upgrade notes for more information.

将 spring-ai-starter-model-bedrock 依赖项添加到您项目的 Maven pom.xml 文件中：

Add the spring-ai-starter-model-bedrock dependency to your project’s Maven pom.xml file:

<dependency>
  <groupId>org.springframework.ai</groupId>
  <artifactId>spring-ai-starter-model-bedrock</artifactId>
</dependency>

或添加到 Gradle build.gradle 构建文件中。

or to your Gradle build.gradle build file.

dependencies {
    implementation 'org.springframework.ai:spring-ai-starter-model-bedrock'
}

  1. 参见 Dependency Management 部分，将 Spring AI BOM 添加到你的构建文件中。

Refer to the Dependency Management section to add the Spring AI BOM to your build file.

Enable Titan Embedding Support

默认情况下，Titan 嵌入模型已禁用。要启用它，请在您的应用程序配置中将 spring.ai.model.embedding 属性设置为 bedrock-titan ：

By default, the Titan embedding model is disabled. To enable it, set the spring.ai.model.embedding property to bedrock-titan in your application configuration:

spring.ai.model.embedding=bedrock-titan

或者，您可以使用 Spring Expression Language (SpEL) 来引用环境变量：

Alternatively, you can use Spring Expression Language (SpEL) to reference an environment variable:

# In application.yml
spring:
  ai:
    model:
      embedding: ${AI_MODEL_EMBEDDING}
# In your environment or .env file
export AI_MODEL_EMBEDDING=bedrock-titan

您还可以在启动应用程序时使用 Java 系统属性设置此属性：

You can also set this property using Java system properties when starting your application:

java -Dspring.ai.model.embedding=bedrock-titan -jar your-application.jar

Embedding Properties

spring.ai.bedrock.aws 前缀是配置与 AWS Bedrock 的连接的属性前缀。

The prefix spring.ai.bedrock.aws is the property prefix to configure the connection to AWS Bedrock.

Property Description Default

spring.ai.bedrock.aws.region

AWS region to use.

us-east-1

spring.ai.bedrock.aws.access-key

AWS access key.

-

spring.ai.bedrock.aws.secret-key

AWS secret key.

-

嵌入自动配置的启用和禁用现在通过前缀为 spring.ai.azure.openai.embedding 的顶级属性进行配置。

Enabling and disabling of the embedding auto-configurations are now configured via top level properties with the prefix spring.ai.model.embedding.

要启用，spring.ai.model.embedding=bedrock-titan（默认启用）

To enable, spring.ai.model.embedding=bedrock-titan (It is enabled by default)

要禁用，spring.ai.model.embedding=none（或任何与 bedrock-titan 不匹配的值）

To disable, spring.ai.model.embedding=none (or any value which doesn’t match bedrock-titan)

此更改旨在允许配置多个模型。

This change is done to allow configuration of multiple models.

前缀` spring.ai.bedrock.titan.embedding （在 BedrockTitanEmbeddingProperties `中定义）是配置Titan嵌入模型实现属性的前缀。

The prefix spring.ai.bedrock.titan.embedding (defined in BedrockTitanEmbeddingProperties) is the property prefix that configures the embedding model implementation for Titan.

Property

Description

Default

spring.ai.bedrock.titan.embedding.enabled (Removed and no longer valid)

Enable or disable support for Titan embedding

false

spring.ai.model.embedding

Enable or disable support for Titan embedding

bedrock-titan

spring.ai.bedrock.titan.embedding.model

The model id to use. See the TitanEmbeddingModel for the supported models.

amazon.titan-embed-image-v1

支持的值包括：` amazon.titan-embed-image-v1 、 amazon.titan-embed-text-v1 和 amazon.titan-embed-text-v2:0 。模型ID值也可以在 AWS Bedrock documentation for base model IDs `中找到。

Supported values are: amazon.titan-embed-image-v1, amazon.titan-embed-text-v1 and amazon.titan-embed-text-v2:0. Model ID values can also be found in the AWS Bedrock documentation for base model IDs.

Runtime Options

` BedrockTitanEmbeddingOptions.java 提供模型配置，例如 input-type 。在启动时，可以使用 BedrockTitanEmbeddingModel(api).withInputType(type) 方法或 spring.ai.bedrock.titan.embedding.input-type `属性配置默认选项。

The BedrockTitanEmbeddingOptions.java provides model configurations, such as input-type. On start-up, the default options can be configured with the BedrockTitanEmbeddingModel(api).withInputType(type) method or the spring.ai.bedrock.titan.embedding.input-type properties.

在运行时，你可以通过将新的特定于请求的选项添加到 EmbeddingRequest 调用来覆盖默认选项。例如，要覆盖特定请求的默认温度：

At run-time you can override the default options by adding new, request specific, options to the EmbeddingRequest call. For example to override the default temperature for a specific request:

EmbeddingResponse embeddingResponse = embeddingModel.call(
    new EmbeddingRequest(List.of("Hello World", "World is big and salvation is near"),
        BedrockTitanEmbeddingOptions.builder()
        	.withInputType(InputType.TEXT)
        .build()));

Sample Controller

` Create 一个新的Spring Boot项目，并将 spring-ai-starter-model-bedrock `添加到你的pom（或gradle）依赖中。

Create a new Spring Boot project and add the spring-ai-starter-model-bedrock to your pom (or gradle) dependencies.

在` src/main/resources 目录下添加一个 application.properties `文件，以启用和配置Titan嵌入模型：

Add a application.properties file, under the src/main/resources directory, to enable and configure the Titan Embedding model:

spring.ai.bedrock.aws.region=eu-central-1
spring.ai.bedrock.aws.access-key=${AWS_ACCESS_KEY_ID}
spring.ai.bedrock.aws.secret-key=${AWS_SECRET_ACCESS_KEY}

spring.ai.model.embedding=bedrock-titan

将 regions、access-key 和 secret-key 替换为 AWS 凭证。

replace the regions, access-key and secret-key with your AWS credentials.

这将创建一个` EmbeddingController 实现，你可以将其注入到你的类中。这是一个使用聊天模型进行文本生成的简单 @Controller `类的示例。

This will create a EmbeddingController implementation that you can inject into your class. Here is an example of a simple @Controller class that uses the chat model for text generations.

@RestController
public class EmbeddingController {

    private final EmbeddingModel embeddingModel;

    @Autowired
    public EmbeddingController(EmbeddingModel embeddingModel) {
        this.embeddingModel = embeddingModel;
    }

    @GetMapping("/ai/embedding")
    public Map embed(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        EmbeddingResponse embeddingResponse = this.embeddingModel.embedForResponse(List.of(message));
        return Map.of("embedding", embeddingResponse);
    }
}

Manual Configuration

` BedrockTitanEmbeddingModel 实现了 EmbeddingModel 并使用 Low-level TitanEmbeddingBedrockApi Client `连接到Bedrock Titan服务。

The BedrockTitanEmbeddingModel implements the EmbeddingModel and uses the Low-level TitanEmbeddingBedrockApi Client to connect to the Bedrock Titan service.

将 spring-ai-bedrock 依赖项添加到项目的 Maven pom.xml 文件：

Add the spring-ai-bedrock dependency to your project’s Maven pom.xml file:

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-bedrock</artifactId>
</dependency>

或添加到 Gradle build.gradle 构建文件中。

or to your Gradle build.gradle build file.

dependencies {
    implementation 'org.springframework.ai:spring-ai-bedrock'
}

  1. 参见 Dependency Management 部分，将 Spring AI BOM 添加到你的构建文件中。

Refer to the Dependency Management section to add the Spring AI BOM to your build file.

接下来，创建一个` BedrockTitanEmbeddingModel `并将其用于文本嵌入：

Next, create an BedrockTitanEmbeddingModel and use it for text embeddings:

var titanEmbeddingApi = new TitanEmbeddingBedrockApi(
	TitanEmbeddingModel.TITAN_EMBED_IMAGE_V1.id(), Region.US_EAST_1.id());

var embeddingModel = new BedrockTitanEmbeddingModel(this.titanEmbeddingApi);

EmbeddingResponse embeddingResponse = this.embeddingModel
	.embedForResponse(List.of("Hello World")); // NOTE titan does not support batch embedding.

Low-level TitanEmbeddingBedrockApi Client

TitanEmbeddingBedrockApi 提供轻量级 Java 客户端，在 AWS Bedrock Titan Embedding models 上。

The TitanEmbeddingBedrockApi provides is lightweight Java client on top of AWS Bedrock Titan Embedding models.

下方的类图阐释了 TitanEmbeddingBedrockApi 接口和构建模块：

Following class diagram illustrates the TitanEmbeddingBedrockApi interface and building blocks:

bedrock titan embedding low level api

TitanEmbeddingBedrockApi 支持 amazon.titan-embed-image-v1 和 amazon.titan-embed-image-v1 模型，用于单一和批量嵌入计算。

The TitanEmbeddingBedrockApi supports the amazon.titan-embed-image-v1 and amazon.titan-embed-image-v1 models for single and batch embedding computation.

下面是一个简单的片段，说明如何以编程方式使用 API：

Here is a simple snippet how to use the api programmatically:

TitanEmbeddingBedrockApi titanEmbedApi = new TitanEmbeddingBedrockApi(
		TitanEmbeddingModel.TITAN_EMBED_TEXT_V1.id(), Region.US_EAST_1.id());

TitanEmbeddingRequest request = TitanEmbeddingRequest.builder()
	.withInputText("I like to eat apples.")
	.build();

TitanEmbeddingResponse response = this.titanEmbedApi.embedding(this.request);

要嵌入图像，需要将其转换为 base64 格式：

To embed an image you need to convert it into base64 format:

TitanEmbeddingBedrockApi titanEmbedApi = new TitanEmbeddingBedrockApi(
		TitanEmbeddingModel.TITAN_EMBED_IMAGE_V1.id(), Region.US_EAST_1.id());

byte[] image = new DefaultResourceLoader()
	.getResource("classpath:/spring_framework.png")
	.getContentAsByteArray();


TitanEmbeddingRequest request = TitanEmbeddingRequest.builder()
	.withInputImage(Base64.getEncoder().encodeToString(this.image))
	.build();

TitanEmbeddingResponse response = this.titanEmbedApi.embedding(this.request);