This is the new AWS CloudFormation Template Reference Guide. Please update your bookmarks and links. For help getting started with CloudFormation, see the AWS CloudFormation User Guide.
AWS::Bedrock::Flow VectorSearchBedrockRerankingConfiguration
Configuration for using Amazon Bedrock foundation models to rerank Knowledge Base vector search results. This enables more sophisticated relevance ranking using large language models.
Syntax
To declare this entity in your AWS CloudFormation template, use the following syntax:
JSON
{ "MetadataConfiguration" :
MetadataConfigurationForReranking
, "ModelConfiguration" :VectorSearchBedrockRerankingModelConfiguration
, "NumberOfRerankedResults" :Number
}
YAML
MetadataConfiguration:
MetadataConfigurationForReranking
ModelConfiguration:VectorSearchBedrockRerankingModelConfiguration
NumberOfRerankedResults:Number
Properties
MetadataConfiguration
-
Configuration for how document metadata should be used during the reranking process. This determines which metadata fields are included when reordering search results.
Required: No
Type: MetadataConfigurationForReranking
Update requires: No interruption
ModelConfiguration
-
Configuration for the Amazon Bedrock foundation model used for reranking. This includes the model ARN and any additional request fields required by the model.
Required: Yes
Type: VectorSearchBedrockRerankingModelConfiguration
Update requires: No interruption
NumberOfRerankedResults
-
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.
Required: No
Type: Number
Minimum:
1
Maximum:
100
Update requires: No interruption