interface VectorSearchRerankingConfigurationProperty
| Language | Type name |
|---|---|
.NET | Amazon.CDK.Mixins.Preview.AWS.Bedrock.Mixins.CfnFlowPropsMixin.VectorSearchRerankingConfigurationProperty |
Go | github.com/aws/aws-cdk-go/awscdkmixinspreview/v2/awsbedrock/mixins#CfnFlowPropsMixin_VectorSearchRerankingConfigurationProperty |
Java | software.amazon.awscdk.mixins.preview.services.bedrock.mixins.CfnFlowPropsMixin.VectorSearchRerankingConfigurationProperty |
Python | aws_cdk.mixins_preview.aws_bedrock.mixins.CfnFlowPropsMixin.VectorSearchRerankingConfigurationProperty |
TypeScript | @aws-cdk/mixins-preview » aws_bedrock » mixins » CfnFlowPropsMixin » VectorSearchRerankingConfigurationProperty |
Configuration for reranking vector search results to improve relevance.
Reranking applies additional relevance models to reorder the initial vector search results based on more sophisticated criteria.
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 vectorSearchRerankingConfigurationProperty: bedrock_mixins.CfnFlowPropsMixin.VectorSearchRerankingConfigurationProperty = {
bedrockRerankingConfiguration: {
metadataConfiguration: {
selectionMode: 'selectionMode',
selectiveModeConfiguration: {
fieldsToExclude: [{
fieldName: 'fieldName',
}],
fieldsToInclude: [{
fieldName: 'fieldName',
}],
},
},
modelConfiguration: {
additionalModelRequestFields: additionalModelRequestFields,
modelArn: 'modelArn',
},
numberOfRerankedResults: 123,
},
type: 'type',
};
Properties
| Name | Type | Description |
|---|---|---|
| bedrock | IResolvable | Vector | Configuration for using Amazon Bedrock foundation models to rerank search results. |
| type? | string | The type of reranking to apply to vector search results. |
bedrockRerankingConfiguration?
Type:
IResolvable | Vector
(optional)
Configuration for using Amazon Bedrock foundation models to rerank search results.
This is required when the reranking type is set to BEDROCK.
type?
Type:
string
(optional)
The type of reranking to apply to vector search results.
Currently, the only supported value is BEDROCK, which uses Amazon Bedrock foundation models for reranking.

.NET
Go
Java
Python
TypeScript