Class: Google::Cloud::DocumentAI::V1beta3::ProcessOptions::LayoutConfig::ChunkingConfig

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb

Overview

Serving config for chunking.

Instance Attribute Summary collapse

Instance Attribute Details

#breakpoint_percentile_threshold::Integer

Returns Optional. The percentile of cosine dissimilarity that must be exceeded between a group of tokens and the next. The smaller this number is, the more chunks will be generated.

Returns:

  • (::Integer)

    Optional. The percentile of cosine dissimilarity that must be exceeded between a group of tokens and the next. The smaller this number is, the more chunks will be generated.



79
80
81
82
# File 'proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb', line 79

class ChunkingConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#chunk_size::Integer

Returns Optional. The chunk sizes to use when splitting documents, in order of level.

Returns:

  • (::Integer)

    Optional. The chunk sizes to use when splitting documents, in order of level.



79
80
81
82
# File 'proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb', line 79

class ChunkingConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#include_ancestor_headings::Boolean

Returns Optional. Whether or not to include ancestor headings when splitting.

Returns:

  • (::Boolean)

    Optional. Whether or not to include ancestor headings when splitting.



79
80
81
82
# File 'proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb', line 79

class ChunkingConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#semantic_chunking_group_size::Boolean

Returns Optional. The number of tokens to group together when evaluating semantic similarity.

Returns:

  • (::Boolean)

    Optional. The number of tokens to group together when evaluating semantic similarity.



79
80
81
82
# File 'proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb', line 79

class ChunkingConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end