Class: Aws::BedrockAgentRuntime::Types::KnowledgeBaseVectorSearchConfiguration

Inherits:

Struct

• Object
• Struct
• Aws::BedrockAgentRuntime::Types::KnowledgeBaseVectorSearchConfiguration

Includes:

Structure

Defined in:

lib/aws-sdk-bedrockagentruntime/types.rb

Overview

Configurations for how to perform the search query and return results. For more information, see [Query configurations].

This data type is used in the following API operations:

• Retrieve request][2

  – in the ‘vectorSearchConfiguration` field

• RetrieveAndGenerate request][3

  – in the

  ‘vectorSearchConfiguration` field

[1]: docs.aws.amazon.com/bedrock/latest/userguide/kb-test-config.html [2]: docs.aws.amazon.com/bedrock/latest/APIReference/API_agent-runtime_Retrieve.html#API_agent-runtime_Retrieve_RequestSyntax [3]: docs.aws.amazon.com/bedrock/latest/APIReference/API_agent-runtime_RetrieveAndGenerate.html#API_agent-runtime_RetrieveAndGenerate_RequestSyntax

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[:filter]

Instance Attribute Summary

• #filter ⇒ Types::RetrievalFilter

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

• #implicit_filter_configuration ⇒ Types::ImplicitFilterConfiguration

  Settings for implicit filtering.

• #number_of_results ⇒ Integer

  The number of source chunks to retrieve.

• #override_search_type ⇒ String

  By default, Amazon Bedrock decides a search strategy for you.

• #reranking_configuration ⇒ Types::VectorSearchRerankingConfiguration

  Contains configurations for reranking the retrieved results.

Instance Attribute Details

#filter ⇒ Types::RetrievalFilter

Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see [Query configurations].

[1]: docs.aws.amazon.com/bedrock/latest/userguide/kb-test-config.html

Returns:

• (Types::RetrievalFilter)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 5064

class KnowledgeBaseVectorSearchConfiguration < Struct.new(
  :filter,
  :implicit_filter_configuration,
  :number_of_results,
  :override_search_type,
  :reranking_configuration)
  SENSITIVE = [:filter]
  include Aws::Structure
end

#implicit_filter_configuration ⇒ Types::ImplicitFilterConfiguration

Settings for implicit filtering.

Returns:

• (Types::ImplicitFilterConfiguration)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 5064

class KnowledgeBaseVectorSearchConfiguration < Struct.new(
  :filter,
  :implicit_filter_configuration,
  :number_of_results,
  :override_search_type,
  :reranking_configuration)
  SENSITIVE = [:filter]
  include Aws::Structure
end

#number_of_results ⇒ Integer

The number of source chunks to retrieve.

Returns:

• (Integer)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 5064

class KnowledgeBaseVectorSearchConfiguration < Struct.new(
  :filter,
  :implicit_filter_configuration,
  :number_of_results,
  :override_search_type,
  :reranking_configuration)
  SENSITIVE = [:filter]
  include Aws::Structure
end

#override_search_type ⇒ String

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. For more information, see [Test a knowledge base].

[1]: docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-test.html

Returns:

• (String)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 5064

class KnowledgeBaseVectorSearchConfiguration < Struct.new(
  :filter,
  :implicit_filter_configuration,
  :number_of_results,
  :override_search_type,
  :reranking_configuration)
  SENSITIVE = [:filter]
  include Aws::Structure
end

#reranking_configuration ⇒ Types::VectorSearchRerankingConfiguration

Contains configurations for reranking the retrieved results. For more information, see [Improve the relevance of query responses with a reranker model].

[1]: docs.aws.amazon.com/bedrock/latest/userguide/rerank.html

Returns:

• (Types::VectorSearchRerankingConfiguration)

# File 'lib/aws-sdk-bedrockagentruntime/types.rb', line 5064

class KnowledgeBaseVectorSearchConfiguration < Struct.new(
  :filter,
  :implicit_filter_configuration,
  :number_of_results,
  :override_search_type,
  :reranking_configuration)
  SENSITIVE = [:filter]
  include Aws::Structure
end