Interface KnowledgeBaseVectorSearchConfiguration.Builder

All Superinterfaces:
Buildable, CopyableBuilder<KnowledgeBaseVectorSearchConfiguration.Builder,KnowledgeBaseVectorSearchConfiguration>, SdkBuilder<KnowledgeBaseVectorSearchConfiguration.Builder,KnowledgeBaseVectorSearchConfiguration>, SdkPojo
Enclosing class:
KnowledgeBaseVectorSearchConfiguration
@Mutable @NotThreadSafe public static interface KnowledgeBaseVectorSearchConfiguration.Builder extends SdkPojo, CopyableBuilder<KnowledgeBaseVectorSearchConfiguration.Builder,KnowledgeBaseVectorSearchConfiguration>

  • Method Details

    • numberOfResults

      KnowledgeBaseVectorSearchConfiguration.Builder numberOfResults(Integer numberOfResults)

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

      Parameters:
      numberOfResults - The number of text chunks to retrieve; the number of results to return.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • overrideSearchType

      KnowledgeBaseVectorSearchConfiguration.Builder overrideSearchType(String 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.

      Parameters:
      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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • overrideSearchType

      KnowledgeBaseVectorSearchConfiguration.Builder overrideSearchType(SearchType 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.

      Parameters:
      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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • filter

      KnowledgeBaseVectorSearchConfiguration.Builder filter(RetrievalFilter filter)

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

      Parameters:
      filter - Specifies the filters to use on the metadata fields in the knowledge base data sources before returning results.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • filter

      default KnowledgeBaseVectorSearchConfiguration.Builder filter(Consumer<RetrievalFilter.Builder> filter)

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

      This is a convenience method that creates an instance of the RetrievalFilter.Builder avoiding the need to create one manually via RetrievalFilter.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to filter(RetrievalFilter).

      Parameters:
      filter - a consumer that will call methods on RetrievalFilter.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • implicitFilterConfiguration

      KnowledgeBaseVectorSearchConfiguration.Builder implicitFilterConfiguration(ImplicitFilterConfiguration 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.

      Parameters:
      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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • implicitFilterConfiguration

      default KnowledgeBaseVectorSearchConfiguration.Builder implicitFilterConfiguration(Consumer<ImplicitFilterConfiguration.Builder> 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.

      This is a convenience method that creates an instance of the ImplicitFilterConfiguration.Builder avoiding the need to create one manually via ImplicitFilterConfiguration.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to implicitFilterConfiguration(ImplicitFilterConfiguration).

      Parameters:
      implicitFilterConfiguration - a consumer that will call methods on ImplicitFilterConfiguration.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • rerankingConfiguration

      KnowledgeBaseVectorSearchConfiguration.Builder rerankingConfiguration(VectorSearchRerankingConfiguration 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.

      Parameters:
      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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • rerankingConfiguration

      default KnowledgeBaseVectorSearchConfiguration.Builder rerankingConfiguration(Consumer<VectorSearchRerankingConfiguration.Builder> 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.

      This is a convenience method that creates an instance of the VectorSearchRerankingConfiguration.Builder avoiding the need to create one manually via VectorSearchRerankingConfiguration.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to rerankingConfiguration(VectorSearchRerankingConfiguration).

      Parameters:
      rerankingConfiguration - a consumer that will call methods on VectorSearchRerankingConfiguration.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also: