Class CfnFlowVersionPropsMixin.VectorSearchBedrockRerankingConfigurationProperty

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

Inheritance

object

CfnFlowVersionPropsMixin.VectorSearchBedrockRerankingConfigurationProperty

Implements

CfnFlowVersionPropsMixin.IVectorSearchBedrockRerankingConfigurationProperty

Inherited Members

object.GetType()

object.MemberwiseClone()

object.ToString()

object.Equals(object)

object.Equals(object, object)

object.ReferenceEquals(object, object)

object.GetHashCode()

Namespace: Amazon.CDK.Mixins.Preview.AWS.Bedrock.Mixins

Assembly: Amazon.CDK.Mixins.Preview.dll

Syntax (csharp)

public class CfnFlowVersionPropsMixin.VectorSearchBedrockRerankingConfigurationProperty : CfnFlowVersionPropsMixin.IVectorSearchBedrockRerankingConfigurationProperty

Syntax (vb)

Public Class CfnFlowVersionPropsMixin.VectorSearchBedrockRerankingConfigurationProperty Implements CfnFlowVersionPropsMixin.IVectorSearchBedrockRerankingConfigurationProperty

Remarks

This enables more sophisticated relevance ranking using large language models.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-flowversion-vectorsearchbedrockrerankingconfiguration.html

ExampleMetadata: fixture=_generated

Examples

// The code below shows an example of how to instantiate this type.
             // The values are placeholders you should change.
             using Amazon.CDK.Mixins.Preview.AWS.Bedrock.Mixins;

             var additionalModelRequestFields;

             var vectorSearchBedrockRerankingConfigurationProperty = new VectorSearchBedrockRerankingConfigurationProperty {
                 MetadataConfiguration = new MetadataConfigurationForRerankingProperty {
                     SelectionMode = "selectionMode",
                     SelectiveModeConfiguration = new RerankingMetadataSelectiveModeConfigurationProperty {
                         FieldsToExclude = new [] { new FieldForRerankingProperty {
                             FieldName = "fieldName"
                         } },
                         FieldsToInclude = new [] { new FieldForRerankingProperty {
                             FieldName = "fieldName"
                         } }
                     }
                 },
                 ModelConfiguration = new VectorSearchBedrockRerankingModelConfigurationProperty {
                     AdditionalModelRequestFields = additionalModelRequestFields,
                     ModelArn = "modelArn"
                 },
                 NumberOfRerankedResults = 123
             };

Synopsis

Constructors

VectorSearchBedrockRerankingConfigurationProperty()

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

Properties

MetadataConfiguration	Configuration for how document metadata should be used during the reranking process.
ModelConfiguration	Configuration for the Amazon Bedrock foundation model used for reranking.
NumberOfRerankedResults	The maximum number of results to rerank.

Constructors

VectorSearchBedrockRerankingConfigurationProperty()

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

public VectorSearchBedrockRerankingConfigurationProperty()

Remarks

This enables more sophisticated relevance ranking using large language models.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-flowversion-vectorsearchbedrockrerankingconfiguration.html

ExampleMetadata: fixture=_generated

Examples

// The code below shows an example of how to instantiate this type.
             // The values are placeholders you should change.
             using Amazon.CDK.Mixins.Preview.AWS.Bedrock.Mixins;

             var additionalModelRequestFields;

             var vectorSearchBedrockRerankingConfigurationProperty = new VectorSearchBedrockRerankingConfigurationProperty {
                 MetadataConfiguration = new MetadataConfigurationForRerankingProperty {
                     SelectionMode = "selectionMode",
                     SelectiveModeConfiguration = new RerankingMetadataSelectiveModeConfigurationProperty {
                         FieldsToExclude = new [] { new FieldForRerankingProperty {
                             FieldName = "fieldName"
                         } },
                         FieldsToInclude = new [] { new FieldForRerankingProperty {
                             FieldName = "fieldName"
                         } }
                     }
                 },
                 ModelConfiguration = new VectorSearchBedrockRerankingModelConfigurationProperty {
                     AdditionalModelRequestFields = additionalModelRequestFields,
                     ModelArn = "modelArn"
                 },
                 NumberOfRerankedResults = 123
             };

Properties

MetadataConfiguration

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

public object? MetadataConfiguration { get; set; }

Property Value

object

Remarks

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

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-flowversion-vectorsearchbedrockrerankingconfiguration.html#cfn-bedrock-flowversion-vectorsearchbedrockrerankingconfiguration-metadataconfiguration

Type union: either IResolvable or CfnFlowVersionPropsMixin.IMetadataConfigurationForRerankingProperty

ModelConfiguration

Configuration for the Amazon Bedrock foundation model used for reranking.

public object? ModelConfiguration { get; set; }

Property Value

object

Remarks

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

Type union: either IResolvable or CfnFlowVersionPropsMixin.IVectorSearchBedrockRerankingModelConfigurationProperty

NumberOfRerankedResults

The maximum number of results to rerank.

public double? NumberOfRerankedResults { get; set; }

Property Value

double?

Remarks

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.

Implements

CfnFlowVersionPropsMixin.IVectorSearchBedrockRerankingConfigurationProperty