KnowledgeBaseVectorSearchConfiguration

The configuration details for returning the results from the knowledge base vector search.

filter

Specifies the filters to use on the metadata fields in the knowledge base data sources before returning results.

Note: This object is a Union. Only one member of this object can be specified or returned.

Required: No

implicitFilterConfiguration

Configuration for implicit filtering in Knowledge Base vector searches. This allows the system to automatically apply filters based on the query context without requiring explicit filter expressions.

Type: ImplicitFilterConfiguration object

Required: No

numberOfResults

The number of text chunks to retrieve; the number of results to return.

Type: Integer

Valid Range: Minimum value of 1. Maximum value of 100.

Required: No

overrideSearchType

By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available.

Type: String

Valid Values: HYBRID | SEMANTIC

Required: No

rerankingConfiguration

Configuration for reranking search results in Knowledge Base vector searches. Reranking improves search relevance by reordering initial vector search results using more sophisticated relevance models.

Type: VectorSearchRerankingConfiguration object

Required: No

KnowledgeBaseVectorSearchConfiguration

Contents

See Also