Class: Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/discoveryengine/v1/document_processing_config.rb

Overview

Related configurations applied to a specific type of document parser.

Defined Under Namespace

Classes: DigitalParsingConfig, LayoutParsingConfig, OcrParsingConfig

Instance Attribute Summary collapse

Instance Attribute Details

#digital_parsing_config ⇒ ::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::DigitalParsingConfig

Returns Configurations applied to digital parser.

Note: The following fields are mutually exclusive: digital_parsing_config, ocr_parsing_config, layout_parsing_config. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns:



109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
# File 'proto_docs/google/cloud/discoveryengine/v1/document_processing_config.rb', line 109

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

  # The digital parsing configurations for documents.
  class DigitalParsingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The OCR parsing configurations for documents.
  # @!attribute [rw] enhanced_document_elements
  #   @deprecated This field is deprecated and may be removed in the next major version update.
  #   @return [::Array<::String>]
  #     [DEPRECATED] This field is deprecated. To use the additional enhanced
  #     document elements processing, please switch to `layout_parsing_config`.
  # @!attribute [rw] use_native_text
  #   @return [::Boolean]
  #     If true, will use native text instead of OCR text on pages containing
  #     native text.
  class OcrParsingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The layout parsing configurations for documents.
  # @!attribute [rw] enable_table_annotation
  #   @return [::Boolean]
  #     Optional. If true, the LLM based annotation is added to the table
  #     during parsing.
  # @!attribute [rw] enable_image_annotation
  #   @return [::Boolean]
  #     Optional. If true, the LLM based annotation is added to the image
  #     during parsing.
  # @!attribute [rw] structured_content_types
  #   @return [::Array<::String>]
  #     Optional. Contains the required structure types to extract from the
  #     document. Supported values:
  #
  #     * `shareholder-structure`
  # @!attribute [rw] exclude_html_elements
  #   @return [::Array<::String>]
  #     Optional. List of HTML elements to exclude from the parsed content.
  # @!attribute [rw] exclude_html_classes
  #   @return [::Array<::String>]
  #     Optional. List of HTML classes to exclude from the parsed content.
  # @!attribute [rw] exclude_html_ids
  #   @return [::Array<::String>]
  #     Optional. List of HTML ids to exclude from the parsed content.
  class LayoutParsingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#layout_parsing_config ⇒ ::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::LayoutParsingConfig

Returns Configurations applied to layout parser.

Note: The following fields are mutually exclusive: layout_parsing_config, digital_parsing_config, ocr_parsing_config. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns:



109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
# File 'proto_docs/google/cloud/discoveryengine/v1/document_processing_config.rb', line 109

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

  # The digital parsing configurations for documents.
  class DigitalParsingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The OCR parsing configurations for documents.
  # @!attribute [rw] enhanced_document_elements
  #   @deprecated This field is deprecated and may be removed in the next major version update.
  #   @return [::Array<::String>]
  #     [DEPRECATED] This field is deprecated. To use the additional enhanced
  #     document elements processing, please switch to `layout_parsing_config`.
  # @!attribute [rw] use_native_text
  #   @return [::Boolean]
  #     If true, will use native text instead of OCR text on pages containing
  #     native text.
  class OcrParsingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The layout parsing configurations for documents.
  # @!attribute [rw] enable_table_annotation
  #   @return [::Boolean]
  #     Optional. If true, the LLM based annotation is added to the table
  #     during parsing.
  # @!attribute [rw] enable_image_annotation
  #   @return [::Boolean]
  #     Optional. If true, the LLM based annotation is added to the image
  #     during parsing.
  # @!attribute [rw] structured_content_types
  #   @return [::Array<::String>]
  #     Optional. Contains the required structure types to extract from the
  #     document. Supported values:
  #
  #     * `shareholder-structure`
  # @!attribute [rw] exclude_html_elements
  #   @return [::Array<::String>]
  #     Optional. List of HTML elements to exclude from the parsed content.
  # @!attribute [rw] exclude_html_classes
  #   @return [::Array<::String>]
  #     Optional. List of HTML classes to exclude from the parsed content.
  # @!attribute [rw] exclude_html_ids
  #   @return [::Array<::String>]
  #     Optional. List of HTML ids to exclude from the parsed content.
  class LayoutParsingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#ocr_parsing_config ⇒ ::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::OcrParsingConfig

Returns Configurations applied to OCR parser. Currently it only applies to PDFs.

Note: The following fields are mutually exclusive: ocr_parsing_config, digital_parsing_config, layout_parsing_config. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns:



109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
# File 'proto_docs/google/cloud/discoveryengine/v1/document_processing_config.rb', line 109

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

  # The digital parsing configurations for documents.
  class DigitalParsingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The OCR parsing configurations for documents.
  # @!attribute [rw] enhanced_document_elements
  #   @deprecated This field is deprecated and may be removed in the next major version update.
  #   @return [::Array<::String>]
  #     [DEPRECATED] This field is deprecated. To use the additional enhanced
  #     document elements processing, please switch to `layout_parsing_config`.
  # @!attribute [rw] use_native_text
  #   @return [::Boolean]
  #     If true, will use native text instead of OCR text on pages containing
  #     native text.
  class OcrParsingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The layout parsing configurations for documents.
  # @!attribute [rw] enable_table_annotation
  #   @return [::Boolean]
  #     Optional. If true, the LLM based annotation is added to the table
  #     during parsing.
  # @!attribute [rw] enable_image_annotation
  #   @return [::Boolean]
  #     Optional. If true, the LLM based annotation is added to the image
  #     during parsing.
  # @!attribute [rw] structured_content_types
  #   @return [::Array<::String>]
  #     Optional. Contains the required structure types to extract from the
  #     document. Supported values:
  #
  #     * `shareholder-structure`
  # @!attribute [rw] exclude_html_elements
  #   @return [::Array<::String>]
  #     Optional. List of HTML elements to exclude from the parsed content.
  # @!attribute [rw] exclude_html_classes
  #   @return [::Array<::String>]
  #     Optional. List of HTML classes to exclude from the parsed content.
  # @!attribute [rw] exclude_html_ids
  #   @return [::Array<::String>]
  #     Optional. List of HTML ids to exclude from the parsed content.
  class LayoutParsingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end