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

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

A singleton resource of DataStore. If it's empty when DataStore is created and DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED, the default parser will default to digital parser.

Defined Under Namespace

Classes: ChunkingConfig, ParsingConfig, ParsingConfigOverridesEntry

Instance Attribute Summary collapse

Instance Attribute Details

#chunking_config ⇒ ::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ChunkingConfig

Returns Whether chunking mode is enabled.

Returns:



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
98
99
100
101
102
103
104
105
106
107
108
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
 
# File 'proto_docs/google/cloud/discoveryengine/v1/document_processing_config.rb', line 61

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

  # Configuration for chunking config.
  # @!attribute [rw] layout_based_chunking_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ChunkingConfig::LayoutBasedChunkingConfig]
  #     Configuration for the layout based chunking.
  class ChunkingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Configuration for the layout based chunking.
    # @!attribute [rw] chunk_size
    #   @return [::Integer]
    #     The token size limit for each chunk.
    #
    #     Supported values: 100-500 (inclusive).
    #     Default value: 500.
    # @!attribute [rw] include_ancestor_headings
    #   @return [::Boolean]
    #     Whether to include appending different levels of headings to chunks
    #     from the middle of the document to prevent context loss.
    #
    #     Default value: False.
    class LayoutBasedChunkingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # Related configurations applied to a specific type of document parser.
  # @!attribute [rw] digital_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::DigitalParsingConfig]
  #     Configurations applied to digital parser.
  # @!attribute [rw] ocr_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::OcrParsingConfig]
  #     Configurations applied to OCR parser. Currently it only applies to
  #     PDFs.
  # @!attribute [rw] layout_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::LayoutParsingConfig]
  #     Configurations applied to layout parser.
  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.
    class LayoutParsingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # @!attribute [rw] key
  #   @return [::String]
  # @!attribute [rw] value
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig]
  class ParsingConfigOverridesEntry
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#default_parsing_config ⇒ ::Google::Cloud::DiscoveryEngine::V1::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:



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
98
99
100
101
102
103
104
105
106
107
108
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
 
# File 'proto_docs/google/cloud/discoveryengine/v1/document_processing_config.rb', line 61

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

  # Configuration for chunking config.
  # @!attribute [rw] layout_based_chunking_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ChunkingConfig::LayoutBasedChunkingConfig]
  #     Configuration for the layout based chunking.
  class ChunkingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Configuration for the layout based chunking.
    # @!attribute [rw] chunk_size
    #   @return [::Integer]
    #     The token size limit for each chunk.
    #
    #     Supported values: 100-500 (inclusive).
    #     Default value: 500.
    # @!attribute [rw] include_ancestor_headings
    #   @return [::Boolean]
    #     Whether to include appending different levels of headings to chunks
    #     from the middle of the document to prevent context loss.
    #
    #     Default value: False.
    class LayoutBasedChunkingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # Related configurations applied to a specific type of document parser.
  # @!attribute [rw] digital_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::DigitalParsingConfig]
  #     Configurations applied to digital parser.
  # @!attribute [rw] ocr_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::OcrParsingConfig]
  #     Configurations applied to OCR parser. Currently it only applies to
  #     PDFs.
  # @!attribute [rw] layout_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::LayoutParsingConfig]
  #     Configurations applied to layout parser.
  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.
    class LayoutParsingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # @!attribute [rw] key
  #   @return [::String]
  # @!attribute [rw] value
  #   @return [::Google::Cloud::DiscoveryEngine::V1::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.



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
98
99
100
101
102
103
104
105
106
107
108
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
 
# File 'proto_docs/google/cloud/discoveryengine/v1/document_processing_config.rb', line 61

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

  # Configuration for chunking config.
  # @!attribute [rw] layout_based_chunking_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ChunkingConfig::LayoutBasedChunkingConfig]
  #     Configuration for the layout based chunking.
  class ChunkingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Configuration for the layout based chunking.
    # @!attribute [rw] chunk_size
    #   @return [::Integer]
    #     The token size limit for each chunk.
    #
    #     Supported values: 100-500 (inclusive).
    #     Default value: 500.
    # @!attribute [rw] include_ancestor_headings
    #   @return [::Boolean]
    #     Whether to include appending different levels of headings to chunks
    #     from the middle of the document to prevent context loss.
    #
    #     Default value: False.
    class LayoutBasedChunkingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # Related configurations applied to a specific type of document parser.
  # @!attribute [rw] digital_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::DigitalParsingConfig]
  #     Configurations applied to digital parser.
  # @!attribute [rw] ocr_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::OcrParsingConfig]
  #     Configurations applied to OCR parser. Currently it only applies to
  #     PDFs.
  # @!attribute [rw] layout_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::LayoutParsingConfig]
  #     Configurations applied to layout parser.
  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.
    class LayoutParsingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # @!attribute [rw] key
  #   @return [::String]
  # @!attribute [rw] value
  #   @return [::Google::Cloud::DiscoveryEngine::V1::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::V1::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 layout parsing are supported.
  • docx: Override parsing config for DOCX files, only digital parsing and layout parsing are supported.
  • pptx: Override parsing config for PPTX files, only digital parsing and layout parsing are supported.
  • xlsm: Override parsing config for XLSM files, only digital parsing and layout parsing are supported.
  • xlsx: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.

Returns:

  • (::Google::Protobuf::Map{::String => ::Google::Cloud::DiscoveryEngine::V1::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 layout parsing are supported.
    • docx: Override parsing config for DOCX files, only digital parsing and layout parsing are supported.
    • pptx: Override parsing config for PPTX files, only digital parsing and layout parsing are supported.
    • xlsm: Override parsing config for XLSM files, only digital parsing and layout parsing are supported.
    • xlsx: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.


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
98
99
100
101
102
103
104
105
106
107
108
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
 
# File 'proto_docs/google/cloud/discoveryengine/v1/document_processing_config.rb', line 61

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

  # Configuration for chunking config.
  # @!attribute [rw] layout_based_chunking_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ChunkingConfig::LayoutBasedChunkingConfig]
  #     Configuration for the layout based chunking.
  class ChunkingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Configuration for the layout based chunking.
    # @!attribute [rw] chunk_size
    #   @return [::Integer]
    #     The token size limit for each chunk.
    #
    #     Supported values: 100-500 (inclusive).
    #     Default value: 500.
    # @!attribute [rw] include_ancestor_headings
    #   @return [::Boolean]
    #     Whether to include appending different levels of headings to chunks
    #     from the middle of the document to prevent context loss.
    #
    #     Default value: False.
    class LayoutBasedChunkingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # Related configurations applied to a specific type of document parser.
  # @!attribute [rw] digital_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::DigitalParsingConfig]
  #     Configurations applied to digital parser.
  # @!attribute [rw] ocr_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::OcrParsingConfig]
  #     Configurations applied to OCR parser. Currently it only applies to
  #     PDFs.
  # @!attribute [rw] layout_parsing_config
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig::LayoutParsingConfig]
  #     Configurations applied to layout parser.
  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.
    class LayoutParsingConfig
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # @!attribute [rw] key
  #   @return [::String]
  # @!attribute [rw] value
  #   @return [::Google::Cloud::DiscoveryEngine::V1::DocumentProcessingConfig::ParsingConfig]
  class ParsingConfigOverridesEntry
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end