Class: Google::Cloud::DocumentAI::V1beta3::ProcessOptions

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

Options for Process API

Defined Under Namespace

Classes: IndividualPageSelector, LayoutConfig

Instance Attribute Summary collapse

Instance Attribute Details

#from_end::Integer

Returns Only process certain pages from the end, same as above.

Returns:

  • (::Integer)

    Only process certain pages from the end, same as above.



50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
# File 'proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb', line 50

class ProcessOptions
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Serving config for layout parser processor.
  # @!attribute [rw] chunking_config
  #   @return [::Google::Cloud::DocumentAI::V1beta3::ProcessOptions::LayoutConfig::ChunkingConfig]
  #     Optional. Config for chunking in layout parser processor.
  class LayoutConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Serving config for chunking.
    # @!attribute [rw] chunk_size
    #   @return [::Integer]
    #     Optional. The chunk sizes to use when splitting documents, in order of
    #     level.
    # @!attribute [rw] include_ancestor_headings
    #   @return [::Boolean]
    #     Optional. Whether or not to include ancestor headings when splitting.
    # @!attribute [rw] semantic_chunking_group_size
    #   @return [::Boolean]
    #     Optional. The number of tokens to group together when evaluating
    #     semantic similarity.
    # @!attribute [rw] breakpoint_percentile_threshold
    #   @return [::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.
    class ChunkingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # A list of individual page numbers.
  # @!attribute [rw] pages
  #   @return [::Array<::Integer>]
  #     Optional. Indices of the pages (starting from 1).
  class IndividualPageSelector
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#from_start::Integer

Returns Only process certain pages from the start. Process all if the document has fewer pages.

Returns:

  • (::Integer)

    Only process certain pages from the start. Process all if the document has fewer pages.



50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
# File 'proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb', line 50

class ProcessOptions
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Serving config for layout parser processor.
  # @!attribute [rw] chunking_config
  #   @return [::Google::Cloud::DocumentAI::V1beta3::ProcessOptions::LayoutConfig::ChunkingConfig]
  #     Optional. Config for chunking in layout parser processor.
  class LayoutConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Serving config for chunking.
    # @!attribute [rw] chunk_size
    #   @return [::Integer]
    #     Optional. The chunk sizes to use when splitting documents, in order of
    #     level.
    # @!attribute [rw] include_ancestor_headings
    #   @return [::Boolean]
    #     Optional. Whether or not to include ancestor headings when splitting.
    # @!attribute [rw] semantic_chunking_group_size
    #   @return [::Boolean]
    #     Optional. The number of tokens to group together when evaluating
    #     semantic similarity.
    # @!attribute [rw] breakpoint_percentile_threshold
    #   @return [::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.
    class ChunkingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # A list of individual page numbers.
  # @!attribute [rw] pages
  #   @return [::Array<::Integer>]
  #     Optional. Indices of the pages (starting from 1).
  class IndividualPageSelector
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#individual_page_selector::Google::Cloud::DocumentAI::V1beta3::ProcessOptions::IndividualPageSelector

Returns Which pages to process (1-indexed).

Returns:



50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
# File 'proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb', line 50

class ProcessOptions
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Serving config for layout parser processor.
  # @!attribute [rw] chunking_config
  #   @return [::Google::Cloud::DocumentAI::V1beta3::ProcessOptions::LayoutConfig::ChunkingConfig]
  #     Optional. Config for chunking in layout parser processor.
  class LayoutConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Serving config for chunking.
    # @!attribute [rw] chunk_size
    #   @return [::Integer]
    #     Optional. The chunk sizes to use when splitting documents, in order of
    #     level.
    # @!attribute [rw] include_ancestor_headings
    #   @return [::Boolean]
    #     Optional. Whether or not to include ancestor headings when splitting.
    # @!attribute [rw] semantic_chunking_group_size
    #   @return [::Boolean]
    #     Optional. The number of tokens to group together when evaluating
    #     semantic similarity.
    # @!attribute [rw] breakpoint_percentile_threshold
    #   @return [::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.
    class ChunkingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # A list of individual page numbers.
  # @!attribute [rw] pages
  #   @return [::Array<::Integer>]
  #     Optional. Indices of the pages (starting from 1).
  class IndividualPageSelector
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#layout_config::Google::Cloud::DocumentAI::V1beta3::ProcessOptions::LayoutConfig

Optional. Only applicable to LAYOUT_PARSER_PROCESSOR. Returns error if set on other processor types.

Returns:



50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
# File 'proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb', line 50

class ProcessOptions
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Serving config for layout parser processor.
  # @!attribute [rw] chunking_config
  #   @return [::Google::Cloud::DocumentAI::V1beta3::ProcessOptions::LayoutConfig::ChunkingConfig]
  #     Optional. Config for chunking in layout parser processor.
  class LayoutConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Serving config for chunking.
    # @!attribute [rw] chunk_size
    #   @return [::Integer]
    #     Optional. The chunk sizes to use when splitting documents, in order of
    #     level.
    # @!attribute [rw] include_ancestor_headings
    #   @return [::Boolean]
    #     Optional. Whether or not to include ancestor headings when splitting.
    # @!attribute [rw] semantic_chunking_group_size
    #   @return [::Boolean]
    #     Optional. The number of tokens to group together when evaluating
    #     semantic similarity.
    # @!attribute [rw] breakpoint_percentile_threshold
    #   @return [::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.
    class ChunkingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # A list of individual page numbers.
  # @!attribute [rw] pages
  #   @return [::Array<::Integer>]
  #     Optional. Indices of the pages (starting from 1).
  class IndividualPageSelector
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#ocr_config::Google::Cloud::DocumentAI::V1beta3::OcrConfig

Only applicable to OCR_PROCESSOR and FORM_PARSER_PROCESSOR. Returns error if set on other processor types.

Returns:



50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
# File 'proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb', line 50

class ProcessOptions
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Serving config for layout parser processor.
  # @!attribute [rw] chunking_config
  #   @return [::Google::Cloud::DocumentAI::V1beta3::ProcessOptions::LayoutConfig::ChunkingConfig]
  #     Optional. Config for chunking in layout parser processor.
  class LayoutConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Serving config for chunking.
    # @!attribute [rw] chunk_size
    #   @return [::Integer]
    #     Optional. The chunk sizes to use when splitting documents, in order of
    #     level.
    # @!attribute [rw] include_ancestor_headings
    #   @return [::Boolean]
    #     Optional. Whether or not to include ancestor headings when splitting.
    # @!attribute [rw] semantic_chunking_group_size
    #   @return [::Boolean]
    #     Optional. The number of tokens to group together when evaluating
    #     semantic similarity.
    # @!attribute [rw] breakpoint_percentile_threshold
    #   @return [::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.
    class ChunkingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # A list of individual page numbers.
  # @!attribute [rw] pages
  #   @return [::Array<::Integer>]
  #     Optional. Indices of the pages (starting from 1).
  class IndividualPageSelector
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#schema_override::Google::Cloud::DocumentAI::V1beta3::DocumentSchema

Optional. Override the schema of the ProcessorVersion. Will return an Invalid Argument error if this field is set when the underlying ProcessorVersion doesn't support schema override.

Returns:



50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
# File 'proto_docs/google/cloud/documentai/v1beta3/document_processor_service.rb', line 50

class ProcessOptions
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Serving config for layout parser processor.
  # @!attribute [rw] chunking_config
  #   @return [::Google::Cloud::DocumentAI::V1beta3::ProcessOptions::LayoutConfig::ChunkingConfig]
  #     Optional. Config for chunking in layout parser processor.
  class LayoutConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Serving config for chunking.
    # @!attribute [rw] chunk_size
    #   @return [::Integer]
    #     Optional. The chunk sizes to use when splitting documents, in order of
    #     level.
    # @!attribute [rw] include_ancestor_headings
    #   @return [::Boolean]
    #     Optional. Whether or not to include ancestor headings when splitting.
    # @!attribute [rw] semantic_chunking_group_size
    #   @return [::Boolean]
    #     Optional. The number of tokens to group together when evaluating
    #     semantic similarity.
    # @!attribute [rw] breakpoint_percentile_threshold
    #   @return [::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.
    class ChunkingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # A list of individual page numbers.
  # @!attribute [rw] pages
  #   @return [::Array<::Integer>]
  #     Optional. Indices of the pages (starting from 1).
  class IndividualPageSelector
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end