interface VectorSearchBedrockRerankingConfigurationProperty

Language	Type name
.NET	`Amazon.CDK.Mixins.Preview.AWS.Bedrock.Mixins.CfnFlowPropsMixin.VectorSearchBedrockRerankingConfigurationProperty`
Go	`github.com/aws/aws-cdk-go/awscdkmixinspreview/v2/awsbedrock/mixins#CfnFlowPropsMixin_VectorSearchBedrockRerankingConfigurationProperty`
Java	`software.amazon.awscdk.mixins.preview.services.bedrock.mixins.CfnFlowPropsMixin.VectorSearchBedrockRerankingConfigurationProperty`
Python	`aws_cdk.mixins_preview.aws_bedrock.mixins.CfnFlowPropsMixin.VectorSearchBedrockRerankingConfigurationProperty`
TypeScript	`@aws-cdk/mixins-preview` » `aws_bedrock` » `mixins` » `CfnFlowPropsMixin` » `VectorSearchBedrockRerankingConfigurationProperty`

Configuration for using Amazon Bedrock foundation models to rerank Knowledge Base vector search results.

This enables more sophisticated relevance ranking using large language models.

Example

// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { mixins as bedrock_mixins } from '@aws-cdk/mixins-preview/aws-bedrock';

declare const additionalModelRequestFields: any;
const vectorSearchBedrockRerankingConfigurationProperty: bedrock_mixins.CfnFlowPropsMixin.VectorSearchBedrockRerankingConfigurationProperty = {
  metadataConfiguration: {
    selectionMode: 'selectionMode',
    selectiveModeConfiguration: {
      fieldsToExclude: [{
        fieldName: 'fieldName',
      }],
      fieldsToInclude: [{
        fieldName: 'fieldName',
      }],
    },
  },
  modelConfiguration: {
    additionalModelRequestFields: additionalModelRequestFields,
    modelArn: 'modelArn',
  },
  numberOfRerankedResults: 123,
};

Properties

Name	Type	Description
metadataConfiguration?	`IResolvable` `\|` `MetadataConfigurationForRerankingProperty`	Configuration for how document metadata should be used during the reranking process.
modelConfiguration?	`IResolvable` `\|` `VectorSearchBedrockRerankingModelConfigurationProperty`	Configuration for the Amazon Bedrock foundation model used for reranking.
numberOfRerankedResults?	`number`	The maximum number of results to rerank.

metadataConfiguration?

Type: IResolvable | MetadataConfigurationForRerankingProperty (optional)

Configuration for how document metadata should be used during the reranking process.

This determines which metadata fields are included when reordering search results.

modelConfiguration?

Type: IResolvable | VectorSearchBedrockRerankingModelConfigurationProperty (optional)

Configuration for the Amazon Bedrock foundation model used for reranking.

This includes the model ARN and any additional request fields required by the model.

numberOfRerankedResults?

Type: number (optional)

The maximum number of results to rerank.

This limits how many of the initial vector search results will be processed by the reranking model. A smaller number improves performance but may exclude potentially relevant results.

AWS CDK