Classes
AutoMlParams
Parameters to control AutoML model prediction behavior.
BatchProcessDocumentsRequest
Request to batch process documents as an asynchronous operation. The output is written to Cloud Storage as JSON in the [Document] format.
BatchProcessDocumentsResponse
Response to an batch document processing request. This is returned in the LRO Operation after the operation is complete.
BoundingPoly
A bounding polygon for the detected image annotation.
Document
Document represents the canonical document resource in Document Understanding AI. It is an interchange format that provides insights into documents and allows for collaboration between users and Document Understanding AI to iterate and optimize for quality.
Document.Types
Container for nested types declared in the Document message type.
Document.Types.Entity
A phrase in the text that is a known entity type, such as a person, an organization, or location.
Document.Types.EntityRelation
Relationship between [Entities][google.cloud.documentai.v1beta2.Document.Entity].
Document.Types.Label
Label attaches schema information and/or other metadata to segments within a [Document][google.cloud.documentai.v1beta2.Document]. Multiple [Label][google.cloud.documentai.v1beta2.Document.Label]s on a single field can denote either different labels, different instances of the same label created at different times, or some combination of both.
Document.Types.Page
A page in a [Document][google.cloud.documentai.v1beta2.Document].
Document.Types.Page.Types
Container for nested types declared in the Page message type.
Document.Types.Page.Types.Block
A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.
Document.Types.Page.Types.DetectedLanguage
Detected language for a structural component.
Document.Types.Page.Types.Dimension
Dimension for the page.
Document.Types.Page.Types.FormField
A form field detected on the page.
Document.Types.Page.Types.Layout
Visual element describing a layout unit on a page.
Document.Types.Page.Types.Layout.Types
Container for nested types declared in the Layout message type.
Document.Types.Page.Types.Line
A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.
Document.Types.Page.Types.Paragraph
A collection of lines that a human would perceive as a paragraph.
Document.Types.Page.Types.Table
A table representation similar to HTML table structure.
Document.Types.Page.Types.Table.Types
Container for nested types declared in the Table message type.
Document.Types.Page.Types.Table.Types.TableCell
A cell representation inside the table.
Document.Types.Page.Types.Table.Types.TableRow
A row of table cells.
Document.Types.Page.Types.Token
A detected token.
Document.Types.Page.Types.Token.Types
Container for nested types declared in the Token message type.
Document.Types.Page.Types.Token.Types.DetectedBreak
Detected break at the end of a [Token][google.cloud.documentai.v1beta2.Document.Page.Token].
Document.Types.Page.Types.Token.Types.DetectedBreak.Types
Container for nested types declared in the DetectedBreak message type.
Document.Types.Page.Types.VisualElement
Detected non-text visual elements e.g. checkbox, signature etc. on the page.
Document.Types.PageAnchor
Referencing elements in [Document.pages][google.cloud.documentai.v1beta2.Document.pages].
Document.Types.PageAnchor.Types
Container for nested types declared in the PageAnchor message type.
Document.Types.PageAnchor.Types.PageRef
Represents a weak reference to a page element within a document.
Document.Types.PageAnchor.Types.PageRef.Types
Container for nested types declared in the PageRef message type.
Document.Types.ShardInfo
For a large document, sharding may be performed to produce several document shards. Each document shard contains this field to detail which shard it is.
Document.Types.Style
Annotation for common text style attributes. This adheres to CSS conventions as much as possible.
Document.Types.Style.Types
Container for nested types declared in the Style message type.
Document.Types.Style.Types.FontSize
Font size with unit.
Document.Types.TextAnchor
Text reference indexing into the [Document.text][google.cloud.documentai.v1beta2.Document.text].
Document.Types.TextAnchor.Types
Container for nested types declared in the TextAnchor message type.
Document.Types.TextAnchor.Types.TextSegment
A text segment in the [Document.text][google.cloud.documentai.v1beta2.Document.text]. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See [ShardInfo.text_offset][google.cloud.documentai.v1beta2.Document.ShardInfo.text_offset]
DocumentUnderstandingService
Service to parse structured information from unstructured or semi-structured documents using state-of-the-art Google AI such as natural language, computer vision, and translation.
DocumentUnderstandingService.DocumentUnderstandingServiceBase
Base class for server-side implementations of DocumentUnderstandingService
DocumentUnderstandingService.DocumentUnderstandingServiceClient
Client for DocumentUnderstandingService
DocumentUnderstandingServiceClient
DocumentUnderstandingService client wrapper, for convenient use.
DocumentUnderstandingServiceClientBuilder
Builder class for DocumentUnderstandingServiceClient to provide simple configuration of credentials, endpoint etc.
DocumentUnderstandingServiceClientImpl
DocumentUnderstandingService client wrapper implementation, for convenient use.
DocumentUnderstandingServiceSettings
Settings for DocumentUnderstandingServiceClient instances.
EntityExtractionParams
Parameters to control entity extraction behavior.
FormExtractionParams
Parameters to control form extraction behavior.
GcsDestination
The Google Cloud Storage location where the output file will be written to.
GcsSource
The Google Cloud Storage location where the input file will be read from.
InputConfig
The desired input location and metadata.
KeyValuePairHint
User-provided hint for key value pair.
NormalizedVertex
A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
OcrParams
Parameters to control Optical Character Recognition (OCR) behavior.
OperationMetadata
Contains metadata for the BatchProcessDocuments operation.
OperationMetadata.Types
Container for nested types declared in the OperationMetadata message type.
OutputConfig
The desired output location and metadata.
ProcessDocumentRequest
Request to process one document.
ProcessDocumentResponse
Response to a single document processing request.
TableBoundHint
A hint for a table bounding box on the page for table parsing.
TableExtractionParams
Parameters to control table extraction behavior.
Vertex
A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
Enums
Document.SourceOneofCase
Enum of possible cases for the "source" oneof.
Document.Types.Label.SourceOneofCase
Enum of possible cases for the "source" oneof.
Document.Types.Page.Types.Layout.Types.Orientation
Detected human reading orientation.
Document.Types.Page.Types.Token.Types.DetectedBreak.Types.Type
Enum to denote the type of break found.
Document.Types.PageAnchor.Types.PageRef.Types.LayoutType
The type of layout that is being referenced.
InputConfig.SourceOneofCase
Enum of possible cases for the "source" oneof.
OperationMetadata.Types.State
OutputConfig.DestinationOneofCase
Enum of possible cases for the "destination" oneof.