Class: Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/discoveryengine/v1beta/document_processing_config.rb

Overview

A singleton resource of DataStore. It's empty when DataStore is created, which defaults to digital parser. The first call to [DataStoreService.UpdateDocumentProcessingConfig][] method will initialize the config.

Defined Under Namespace

Classes: ParsingConfig, ParsingConfigOverridesEntry

Instance Attribute Summary collapse

Instance Attribute Details

#default_parsing_config ⇒ ::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig

Returns Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.

Returns:



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
94
95
96
97
 
# File 'proto_docs/google/cloud/discoveryengine/v1beta/document_processing_config.rb', line 51

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

  # Related configurations applied to a specific type of document parser.
  # @!attribute [rw] digital_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig::DigitalParsingConfig]
  #     Configurations applied to digital parser.
  # @!attribute [rw] ocr_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig::OcrParsingConfig]
  #     Configurations applied to OCR parser. Currently it only applies to
  #     PDFs.
  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
  end

  # @!attribute [rw] key
  #   @return [::String]
  # @!attribute [rw] value
  #   @return [::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig]
  class ParsingConfigOverridesEntry
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#name ⇒ ::String

Returns The full resource name of the Document Processing Config. Format: projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig.

Returns:

  • (::String) —

    The full resource name of the Document Processing Config. Format: projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig.



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
94
95
96
97
 
# File 'proto_docs/google/cloud/discoveryengine/v1beta/document_processing_config.rb', line 51

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

  # Related configurations applied to a specific type of document parser.
  # @!attribute [rw] digital_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig::DigitalParsingConfig]
  #     Configurations applied to digital parser.
  # @!attribute [rw] ocr_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig::OcrParsingConfig]
  #     Configurations applied to OCR parser. Currently it only applies to
  #     PDFs.
  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
  end

  # @!attribute [rw] key
  #   @return [::String]
  # @!attribute [rw] value
  #   @return [::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig]
  class ParsingConfigOverridesEntry
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#parsing_config_overrides ⇒ ::Google::Protobuf::Map{::String => ::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig}

Returns Map from file type to override the default parsing configuration based on the file type. Supported keys:

  • pdf: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported.
  • html: Override parsing config for HTML files, only digital parsing and or layout parsing are supported.
  • docx: Override parsing config for DOCX files, only digital parsing and or layout parsing are supported.

Returns:

  • (::Google::Protobuf::Map{::String => ::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig}) —

    Map from file type to override the default parsing configuration based on the file type. Supported keys:

    • pdf: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported.
    • html: Override parsing config for HTML files, only digital parsing and or layout parsing are supported.
    • docx: Override parsing config for DOCX files, only digital parsing and or layout parsing are supported.


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
94
95
96
97
 
# File 'proto_docs/google/cloud/discoveryengine/v1beta/document_processing_config.rb', line 51

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

  # Related configurations applied to a specific type of document parser.
  # @!attribute [rw] digital_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig::DigitalParsingConfig]
  #     Configurations applied to digital parser.
  # @!attribute [rw] ocr_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig::OcrParsingConfig]
  #     Configurations applied to OCR parser. Currently it only applies to
  #     PDFs.
  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
  end

  # @!attribute [rw] key
  #   @return [::String]
  # @!attribute [rw] value
  #   @return [::Google::Cloud::DiscoveryEngine::V1beta::DocumentProcessingConfig::ParsingConfig]
  class ParsingConfigOverridesEntry
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end