Class: Google::Cloud::DocumentAI::V1beta3::Dataset

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

Overview

A singleton resource under a Processor which configures a collection of documents.

Defined Under Namespace

Modules: State Classes: DocumentWarehouseConfig, GCSManagedConfig, SpannerIndexingConfig, UnmanagedDatasetConfig

Instance Attribute Summary collapse

Instance Attribute Details

#document_warehouse_config ⇒ ::Google::Cloud::DocumentAI::V1beta3::Dataset::DocumentWarehouseConfig

Deprecated.

This field is deprecated and may be removed in the next major version update.

Returns Optional. Deprecated. Warehouse-based dataset configuration is not supported.

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
 
# File 'proto_docs/google/cloud/documentai/v1beta3/dataset.rb', line 61

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

  # Configuration specific to the Cloud Storage-based implementation.
  # @!attribute [rw] gcs_prefix
  #   @return [::Google::Cloud::DocumentAI::V1beta3::GcsPrefix]
  #     Required. The Cloud Storage URI (a directory) where the documents
  #     belonging to the dataset must be stored.
  class GCSManagedConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to the Document AI Warehouse-based implementation.
  # @!attribute [r] collection
  #   @return [::String]
  #     Output only. The collection in Document AI Warehouse associated with the
  #     dataset.
  # @!attribute [r] schema
  #   @return [::String]
  #     Output only. The schema in Document AI Warehouse associated with the
  #     dataset.
  class DocumentWarehouseConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to an unmanaged dataset.
  class UnmanagedDatasetConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to spanner-based indexing.
  class SpannerIndexingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Different states of a dataset.
  module State
    # Default unspecified enum, should not be used.
    STATE_UNSPECIFIED = 0

    # Dataset has not been initialized.
    UNINITIALIZED = 1

    # Dataset is being initialized.
    INITIALIZING = 2

    # Dataset has been initialized.
    INITIALIZED = 3
  end
end

#gcs_managed_config ⇒ ::Google::Cloud::DocumentAI::V1beta3::Dataset::GCSManagedConfig

Returns Optional. User-managed Cloud Storage dataset configuration. Use this configuration if the dataset documents are stored under a user-managed Cloud Storage location.

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
 
# File 'proto_docs/google/cloud/documentai/v1beta3/dataset.rb', line 61

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

  # Configuration specific to the Cloud Storage-based implementation.
  # @!attribute [rw] gcs_prefix
  #   @return [::Google::Cloud::DocumentAI::V1beta3::GcsPrefix]
  #     Required. The Cloud Storage URI (a directory) where the documents
  #     belonging to the dataset must be stored.
  class GCSManagedConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to the Document AI Warehouse-based implementation.
  # @!attribute [r] collection
  #   @return [::String]
  #     Output only. The collection in Document AI Warehouse associated with the
  #     dataset.
  # @!attribute [r] schema
  #   @return [::String]
  #     Output only. The schema in Document AI Warehouse associated with the
  #     dataset.
  class DocumentWarehouseConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to an unmanaged dataset.
  class UnmanagedDatasetConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to spanner-based indexing.
  class SpannerIndexingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Different states of a dataset.
  module State
    # Default unspecified enum, should not be used.
    STATE_UNSPECIFIED = 0

    # Dataset has not been initialized.
    UNINITIALIZED = 1

    # Dataset is being initialized.
    INITIALIZING = 2

    # Dataset has been initialized.
    INITIALIZED = 3
  end
end

#name ⇒ ::String

Returns Dataset resource name. Format: projects/{project}/locations/{location}/processors/{processor}/dataset.

Returns:

  • (::String) —

    Dataset resource name. Format: projects/{project}/locations/{location}/processors/{processor}/dataset



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
 
# File 'proto_docs/google/cloud/documentai/v1beta3/dataset.rb', line 61

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

  # Configuration specific to the Cloud Storage-based implementation.
  # @!attribute [rw] gcs_prefix
  #   @return [::Google::Cloud::DocumentAI::V1beta3::GcsPrefix]
  #     Required. The Cloud Storage URI (a directory) where the documents
  #     belonging to the dataset must be stored.
  class GCSManagedConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to the Document AI Warehouse-based implementation.
  # @!attribute [r] collection
  #   @return [::String]
  #     Output only. The collection in Document AI Warehouse associated with the
  #     dataset.
  # @!attribute [r] schema
  #   @return [::String]
  #     Output only. The schema in Document AI Warehouse associated with the
  #     dataset.
  class DocumentWarehouseConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to an unmanaged dataset.
  class UnmanagedDatasetConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to spanner-based indexing.
  class SpannerIndexingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Different states of a dataset.
  module State
    # Default unspecified enum, should not be used.
    STATE_UNSPECIFIED = 0

    # Dataset has not been initialized.
    UNINITIALIZED = 1

    # Dataset is being initialized.
    INITIALIZING = 2

    # Dataset has been initialized.
    INITIALIZED = 3
  end
end

#satisfies_pzi ⇒ ::Boolean (readonly)

Returns Output only. Reserved for future use.

Returns:

  • (::Boolean) —

    Output only. Reserved for future use.



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
 
# File 'proto_docs/google/cloud/documentai/v1beta3/dataset.rb', line 61

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

  # Configuration specific to the Cloud Storage-based implementation.
  # @!attribute [rw] gcs_prefix
  #   @return [::Google::Cloud::DocumentAI::V1beta3::GcsPrefix]
  #     Required. The Cloud Storage URI (a directory) where the documents
  #     belonging to the dataset must be stored.
  class GCSManagedConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to the Document AI Warehouse-based implementation.
  # @!attribute [r] collection
  #   @return [::String]
  #     Output only. The collection in Document AI Warehouse associated with the
  #     dataset.
  # @!attribute [r] schema
  #   @return [::String]
  #     Output only. The schema in Document AI Warehouse associated with the
  #     dataset.
  class DocumentWarehouseConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to an unmanaged dataset.
  class UnmanagedDatasetConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to spanner-based indexing.
  class SpannerIndexingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Different states of a dataset.
  module State
    # Default unspecified enum, should not be used.
    STATE_UNSPECIFIED = 0

    # Dataset has not been initialized.
    UNINITIALIZED = 1

    # Dataset is being initialized.
    INITIALIZING = 2

    # Dataset has been initialized.
    INITIALIZED = 3
  end
end

#satisfies_pzs ⇒ ::Boolean (readonly)

Returns Output only. Reserved for future use.

Returns:

  • (::Boolean) —

    Output only. Reserved for future use.



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
 
# File 'proto_docs/google/cloud/documentai/v1beta3/dataset.rb', line 61

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

  # Configuration specific to the Cloud Storage-based implementation.
  # @!attribute [rw] gcs_prefix
  #   @return [::Google::Cloud::DocumentAI::V1beta3::GcsPrefix]
  #     Required. The Cloud Storage URI (a directory) where the documents
  #     belonging to the dataset must be stored.
  class GCSManagedConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to the Document AI Warehouse-based implementation.
  # @!attribute [r] collection
  #   @return [::String]
  #     Output only. The collection in Document AI Warehouse associated with the
  #     dataset.
  # @!attribute [r] schema
  #   @return [::String]
  #     Output only. The schema in Document AI Warehouse associated with the
  #     dataset.
  class DocumentWarehouseConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to an unmanaged dataset.
  class UnmanagedDatasetConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to spanner-based indexing.
  class SpannerIndexingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Different states of a dataset.
  module State
    # Default unspecified enum, should not be used.
    STATE_UNSPECIFIED = 0

    # Dataset has not been initialized.
    UNINITIALIZED = 1

    # Dataset is being initialized.
    INITIALIZING = 2

    # Dataset has been initialized.
    INITIALIZED = 3
  end
end

#spanner_indexing_config ⇒ ::Google::Cloud::DocumentAI::V1beta3::Dataset::SpannerIndexingConfig

Returns Optional. A lightweight indexing source with low latency and high reliability, but lacking advanced features like CMEK and content-based search.

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
 
# File 'proto_docs/google/cloud/documentai/v1beta3/dataset.rb', line 61

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

  # Configuration specific to the Cloud Storage-based implementation.
  # @!attribute [rw] gcs_prefix
  #   @return [::Google::Cloud::DocumentAI::V1beta3::GcsPrefix]
  #     Required. The Cloud Storage URI (a directory) where the documents
  #     belonging to the dataset must be stored.
  class GCSManagedConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to the Document AI Warehouse-based implementation.
  # @!attribute [r] collection
  #   @return [::String]
  #     Output only. The collection in Document AI Warehouse associated with the
  #     dataset.
  # @!attribute [r] schema
  #   @return [::String]
  #     Output only. The schema in Document AI Warehouse associated with the
  #     dataset.
  class DocumentWarehouseConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to an unmanaged dataset.
  class UnmanagedDatasetConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to spanner-based indexing.
  class SpannerIndexingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Different states of a dataset.
  module State
    # Default unspecified enum, should not be used.
    STATE_UNSPECIFIED = 0

    # Dataset has not been initialized.
    UNINITIALIZED = 1

    # Dataset is being initialized.
    INITIALIZING = 2

    # Dataset has been initialized.
    INITIALIZED = 3
  end
end

#state ⇒ ::Google::Cloud::DocumentAI::V1beta3::Dataset::State

Returns Required. State of the dataset. Ignored when updating dataset.

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
 
# File 'proto_docs/google/cloud/documentai/v1beta3/dataset.rb', line 61

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

  # Configuration specific to the Cloud Storage-based implementation.
  # @!attribute [rw] gcs_prefix
  #   @return [::Google::Cloud::DocumentAI::V1beta3::GcsPrefix]
  #     Required. The Cloud Storage URI (a directory) where the documents
  #     belonging to the dataset must be stored.
  class GCSManagedConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to the Document AI Warehouse-based implementation.
  # @!attribute [r] collection
  #   @return [::String]
  #     Output only. The collection in Document AI Warehouse associated with the
  #     dataset.
  # @!attribute [r] schema
  #   @return [::String]
  #     Output only. The schema in Document AI Warehouse associated with the
  #     dataset.
  class DocumentWarehouseConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to an unmanaged dataset.
  class UnmanagedDatasetConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to spanner-based indexing.
  class SpannerIndexingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Different states of a dataset.
  module State
    # Default unspecified enum, should not be used.
    STATE_UNSPECIFIED = 0

    # Dataset has not been initialized.
    UNINITIALIZED = 1

    # Dataset is being initialized.
    INITIALIZING = 2

    # Dataset has been initialized.
    INITIALIZED = 3
  end
end

#unmanaged_dataset_config ⇒ ::Google::Cloud::DocumentAI::V1beta3::Dataset::UnmanagedDatasetConfig

Returns Optional. Unmanaged dataset configuration. Use this configuration if the dataset documents are managed by the document service internally (not user-managed).

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
 
# File 'proto_docs/google/cloud/documentai/v1beta3/dataset.rb', line 61

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

  # Configuration specific to the Cloud Storage-based implementation.
  # @!attribute [rw] gcs_prefix
  #   @return [::Google::Cloud::DocumentAI::V1beta3::GcsPrefix]
  #     Required. The Cloud Storage URI (a directory) where the documents
  #     belonging to the dataset must be stored.
  class GCSManagedConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to the Document AI Warehouse-based implementation.
  # @!attribute [r] collection
  #   @return [::String]
  #     Output only. The collection in Document AI Warehouse associated with the
  #     dataset.
  # @!attribute [r] schema
  #   @return [::String]
  #     Output only. The schema in Document AI Warehouse associated with the
  #     dataset.
  class DocumentWarehouseConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to an unmanaged dataset.
  class UnmanagedDatasetConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration specific to spanner-based indexing.
  class SpannerIndexingConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Different states of a dataset.
  module State
    # Default unspecified enum, should not be used.
    STATE_UNSPECIFIED = 0

    # Dataset has not been initialized.
    UNINITIALIZED = 1

    # Dataset is being initialized.
    INITIALIZING = 2

    # Dataset has been initialized.
    INITIALIZED = 3
  end
end