Skip to content

KnowledgeBaseVectorSearchConfiguration

Structure Class

KnowledgeBaseVectorSearchConfiguration dataclass

Bases: _SerdeShape

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

Attributes

filter class-attribute instance-attribute
filter: RetrievalFilter | None = ...

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

implicit_filter_configuration class-attribute instance-attribute
implicit_filter_configuration: ImplicitFilterConfiguration | None = ...

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.

number_of_results class-attribute instance-attribute
number_of_results: int | None = ...

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

override_search_type class-attribute instance-attribute
override_search_type: str | None = ...

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.

reranking_configuration class-attribute instance-attribute
reranking_configuration: VectorSearchRerankingConfiguration | None = ...

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.