- 2.58.0 (latest)
- 2.57.0
- 2.56.0
- 2.55.0
- 2.53.0
- 2.52.0
- 2.51.0
- 2.50.0
- 2.49.0
- 2.48.0
- 2.47.0
- 2.46.0
- 2.45.0
- 2.44.0
- 2.43.0
- 2.41.0
- 2.40.0
- 2.39.0
- 2.38.0
- 2.37.0
- 2.36.0
- 2.35.0
- 2.34.0
- 2.33.0
- 2.32.0
- 2.31.0
- 2.28.0
- 2.27.0
- 2.26.0
- 2.25.0
- 2.24.0
- 2.23.0
- 2.22.0
- 2.21.0
- 2.20.0
- 2.19.0
- 2.18.0
- 2.17.0
- 2.16.0
- 2.15.0
- 2.13.0
- 2.12.0
- 2.11.0
- 2.10.0
- 2.9.0
- 2.8.0
- 2.7.5
- 2.6.2
- 2.5.1
- 2.4.3
- 2.3.1
- 2.2.1
- 2.1.9
The interfaces provided are listed below, along with usage samples.
DocumentUnderstandingServiceClient
Service Description: 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.
Sample for DocumentUnderstandingServiceClient:
try (DocumentUnderstandingServiceClient documentUnderstandingServiceClient =
DocumentUnderstandingServiceClient.create()) {
ProcessDocumentRequest request =
ProcessDocumentRequest.newBuilder()
.setParent("parent-995424086")
.setInputConfig(InputConfig.newBuilder().build())
.setOutputConfig(OutputConfig.newBuilder().build())
.setDocumentType("documentType-1473196299")
.setTableExtractionParams(TableExtractionParams.newBuilder().build())
.setFormExtractionParams(FormExtractionParams.newBuilder().build())
.setEntityExtractionParams(EntityExtractionParams.newBuilder().build())
.setOcrParams(OcrParams.newBuilder().build())
.setAutomlParams(AutoMlParams.newBuilder().build())
.build();
Document response = documentUnderstandingServiceClient.processDocument(request);
}
Classes
AutoMlParams
Parameters to control AutoML model prediction behavior.
Protobuf type google.cloud.documentai.v1beta2.AutoMlParams
AutoMlParams.Builder
Parameters to control AutoML model prediction behavior.
Protobuf type google.cloud.documentai.v1beta2.AutoMlParams
BatchProcessDocumentsRequest
Request to batch process documents as an asynchronous operation. The output is written to Cloud Storage as JSON in the [Document] format.
Protobuf type google.cloud.documentai.v1beta2.BatchProcessDocumentsRequest
BatchProcessDocumentsRequest.Builder
Request to batch process documents as an asynchronous operation. The output is written to Cloud Storage as JSON in the [Document] format.
Protobuf type google.cloud.documentai.v1beta2.BatchProcessDocumentsRequest
BatchProcessDocumentsResponse
Response to an batch document processing request. This is returned in the LRO Operation after the operation is complete.
Protobuf type google.cloud.documentai.v1beta2.BatchProcessDocumentsResponse
BatchProcessDocumentsResponse.Builder
Response to an batch document processing request. This is returned in the LRO Operation after the operation is complete.
Protobuf type google.cloud.documentai.v1beta2.BatchProcessDocumentsResponse
BoundingPoly
A bounding polygon for the detected image annotation.
Protobuf type google.cloud.documentai.v1beta2.BoundingPoly
BoundingPoly.Builder
A bounding polygon for the detected image annotation.
Protobuf type google.cloud.documentai.v1beta2.BoundingPoly
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.
Protobuf type google.cloud.documentai.v1beta2.Document
Document.Builder
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.
Protobuf type google.cloud.documentai.v1beta2.Document
Document.Entity
A phrase in the text that is a known entity type, such as a person, an organization, or location.
Protobuf type google.cloud.documentai.v1beta2.Document.Entity
Document.Entity.Builder
A phrase in the text that is a known entity type, such as a person, an organization, or location.
Protobuf type google.cloud.documentai.v1beta2.Document.Entity
Document.EntityRelation
Relationship between Entities.
Protobuf type google.cloud.documentai.v1beta2.Document.EntityRelation
Document.EntityRelation.Builder
Relationship between Entities.
Protobuf type google.cloud.documentai.v1beta2.Document.EntityRelation
Document.Label
Label attaches schema information and/or other metadata to segments within a Document. Multiple Labels on a single field can denote either different labels, different instances of the same label created at different times, or some combination of both.
Protobuf type google.cloud.documentai.v1beta2.Document.Label
Document.Label.Builder
Label attaches schema information and/or other metadata to segments within a Document. Multiple Labels on a single field can denote either different labels, different instances of the same label created at different times, or some combination of both.
Protobuf type google.cloud.documentai.v1beta2.Document.Label
Document.Page
A page in a Document.
Protobuf type google.cloud.documentai.v1beta2.Document.Page
Document.Page.Block
A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Block
Document.Page.Block.Builder
A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Block
Document.Page.Builder
A page in a Document.
Protobuf type google.cloud.documentai.v1beta2.Document.Page
Document.Page.DetectedLanguage
Detected language for a structural component.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.DetectedLanguage
Document.Page.DetectedLanguage.Builder
Detected language for a structural component.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.DetectedLanguage
Document.Page.Dimension
Dimension for the page.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Dimension
Document.Page.Dimension.Builder
Dimension for the page.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Dimension
Document.Page.FormField
A form field detected on the page.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.FormField
Document.Page.FormField.Builder
A form field detected on the page.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.FormField
Document.Page.Layout
Visual element describing a layout unit on a page.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Layout
Document.Page.Layout.Builder
Visual element describing a layout unit on a page.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Layout
Document.Page.Line
A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Line
Document.Page.Line.Builder
A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Line
Document.Page.Paragraph
A collection of lines that a human would perceive as a paragraph.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Paragraph
Document.Page.Paragraph.Builder
A collection of lines that a human would perceive as a paragraph.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Paragraph
Document.Page.Table
A table representation similar to HTML table structure.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Table
Document.Page.Table.Builder
A table representation similar to HTML table structure.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Table
Document.Page.Table.TableCell
A cell representation inside the table.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Table.TableCell
Document.Page.Table.TableCell.Builder
A cell representation inside the table.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Table.TableCell
Document.Page.Table.TableRow
A row of table cells.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Table.TableRow
Document.Page.Table.TableRow.Builder
A row of table cells.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Table.TableRow
Document.Page.Token
A detected token.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Token
Document.Page.Token.Builder
A detected token.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Token
Document.Page.Token.DetectedBreak
Detected break at the end of a Token.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Token.DetectedBreak
Document.Page.Token.DetectedBreak.Builder
Detected break at the end of a Token.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.Token.DetectedBreak
Document.Page.VisualElement
Detected non-text visual elements e.g. checkbox, signature etc. on the page.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.VisualElement
Document.Page.VisualElement.Builder
Detected non-text visual elements e.g. checkbox, signature etc. on the page.
Protobuf type google.cloud.documentai.v1beta2.Document.Page.VisualElement
Document.PageAnchor
Referencing elements in Document.pages.
Protobuf type google.cloud.documentai.v1beta2.Document.PageAnchor
Document.PageAnchor.Builder
Referencing elements in Document.pages.
Protobuf type google.cloud.documentai.v1beta2.Document.PageAnchor
Document.PageAnchor.PageRef
Represents a weak reference to a page element within a document.
Protobuf type google.cloud.documentai.v1beta2.Document.PageAnchor.PageRef
Document.PageAnchor.PageRef.Builder
Represents a weak reference to a page element within a document.
Protobuf type google.cloud.documentai.v1beta2.Document.PageAnchor.PageRef
Document.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.
Protobuf type google.cloud.documentai.v1beta2.Document.ShardInfo
Document.ShardInfo.Builder
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.
Protobuf type google.cloud.documentai.v1beta2.Document.ShardInfo
Document.Style
Annotation for common text style attributes. This adheres to CSS conventions as much as possible.
Protobuf type google.cloud.documentai.v1beta2.Document.Style
Document.Style.Builder
Annotation for common text style attributes. This adheres to CSS conventions as much as possible.
Protobuf type google.cloud.documentai.v1beta2.Document.Style
Document.Style.FontSize
Font size with unit.
Protobuf type google.cloud.documentai.v1beta2.Document.Style.FontSize
Document.Style.FontSize.Builder
Font size with unit.
Protobuf type google.cloud.documentai.v1beta2.Document.Style.FontSize
Document.TextAnchor
Text reference indexing into the Document.text.
Protobuf type google.cloud.documentai.v1beta2.Document.TextAnchor
Document.TextAnchor.Builder
Text reference indexing into the Document.text.
Protobuf type google.cloud.documentai.v1beta2.Document.TextAnchor
Document.TextAnchor.TextSegment
A text segment in the 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
Protobuf type google.cloud.documentai.v1beta2.Document.TextAnchor.TextSegment
Document.TextAnchor.TextSegment.Builder
A text segment in the 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
Protobuf type google.cloud.documentai.v1beta2.Document.TextAnchor.TextSegment
DocumentAiProto
DocumentProto
DocumentUnderstandingServiceClient
Service Description: 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.
This class provides the ability to make remote calls to the backing service through method calls that map to API methods. Sample code to get started:
try (DocumentUnderstandingServiceClient documentUnderstandingServiceClient =
DocumentUnderstandingServiceClient.create()) {
ProcessDocumentRequest request =
ProcessDocumentRequest.newBuilder()
.setParent("parent-995424086")
.setInputConfig(InputConfig.newBuilder().build())
.setOutputConfig(OutputConfig.newBuilder().build())
.setDocumentType("documentType-1473196299")
.setTableExtractionParams(TableExtractionParams.newBuilder().build())
.setFormExtractionParams(FormExtractionParams.newBuilder().build())
.setEntityExtractionParams(EntityExtractionParams.newBuilder().build())
.setOcrParams(OcrParams.newBuilder().build())
.setAutomlParams(AutoMlParams.newBuilder().build())
.build();
Document response = documentUnderstandingServiceClient.processDocument(request);
}
Note: close() needs to be called on the DocumentUnderstandingServiceClient object to clean up resources such as threads. In the example above, try-with-resources is used, which automatically calls close().
The surface of this class includes several types of Java methods for each of the API's methods:
- A "flattened" method. With this type of method, the fields of the request type have been converted into function parameters. It may be the case that not all fields are available as parameters, and not every API method will have a flattened method entry point.
- A "request object" method. This type of method only takes one parameter, a request object, which must be constructed before the call. Not every API method will have a request object method.
- A "callable" method. This type of method takes no parameters and returns an immutable API callable object, which can be used to initiate calls to the service.
See the individual methods for example code.
Many parameters require resource names to be formatted in a particular way. To assist with these names, this class includes a format method for each type of name, and additionally a parse method to extract the individual identifiers contained within names that are returned.
This class can be customized by passing in a custom instance of DocumentUnderstandingServiceSettings to create(). For example:
To customize credentials:
DocumentUnderstandingServiceSettings documentUnderstandingServiceSettings =
DocumentUnderstandingServiceSettings.newBuilder()
.setCredentialsProvider(FixedCredentialsProvider.create(myCredentials))
.build();
DocumentUnderstandingServiceClient documentUnderstandingServiceClient =
DocumentUnderstandingServiceClient.create(documentUnderstandingServiceSettings);
To customize the endpoint:
DocumentUnderstandingServiceSettings documentUnderstandingServiceSettings =
DocumentUnderstandingServiceSettings.newBuilder().setEndpoint(myEndpoint).build();
DocumentUnderstandingServiceClient documentUnderstandingServiceClient =
DocumentUnderstandingServiceClient.create(documentUnderstandingServiceSettings);
Please refer to the GitHub repository's samples for more quickstart code snippets.
DocumentUnderstandingServiceGrpc
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.
DocumentUnderstandingServiceGrpc.DocumentUnderstandingServiceBlockingStub
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.
DocumentUnderstandingServiceGrpc.DocumentUnderstandingServiceFutureStub
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.
DocumentUnderstandingServiceGrpc.DocumentUnderstandingServiceImplBase
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.
DocumentUnderstandingServiceGrpc.DocumentUnderstandingServiceStub
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.
DocumentUnderstandingServiceSettings
Settings class to configure an instance of DocumentUnderstandingServiceClient.
The default instance has everything set to sensible defaults:
- The default service address (documentai.googleapis.com) and default port (443) are used.
- Credentials are acquired automatically through Application Default Credentials.
- Retries are configured for idempotent methods but not for non-idempotent methods.
The builder of this class is recursive, so contained classes are themselves builders. When build() is called, the tree of builders is called to create the complete settings object.
For example, to set the total timeout of processDocument to 30 seconds:
DocumentUnderstandingServiceSettings.Builder documentUnderstandingServiceSettingsBuilder =
DocumentUnderstandingServiceSettings.newBuilder();
documentUnderstandingServiceSettingsBuilder
.processDocumentSettings()
.setRetrySettings(
documentUnderstandingServiceSettingsBuilder
.processDocumentSettings()
.getRetrySettings()
.toBuilder()
.setTotalTimeout(Duration.ofSeconds(30))
.build());
DocumentUnderstandingServiceSettings documentUnderstandingServiceSettings =
documentUnderstandingServiceSettingsBuilder.build();
DocumentUnderstandingServiceSettings.Builder
Builder for DocumentUnderstandingServiceSettings.
EntityExtractionParams
Parameters to control entity extraction behavior.
Protobuf type google.cloud.documentai.v1beta2.EntityExtractionParams
EntityExtractionParams.Builder
Parameters to control entity extraction behavior.
Protobuf type google.cloud.documentai.v1beta2.EntityExtractionParams
FormExtractionParams
Parameters to control form extraction behavior.
Protobuf type google.cloud.documentai.v1beta2.FormExtractionParams
FormExtractionParams.Builder
Parameters to control form extraction behavior.
Protobuf type google.cloud.documentai.v1beta2.FormExtractionParams
GcsDestination
The Google Cloud Storage location where the output file will be written to.
Protobuf type google.cloud.documentai.v1beta2.GcsDestination
GcsDestination.Builder
The Google Cloud Storage location where the output file will be written to.
Protobuf type google.cloud.documentai.v1beta2.GcsDestination
GcsSource
The Google Cloud Storage location where the input file will be read from.
Protobuf type google.cloud.documentai.v1beta2.GcsSource
GcsSource.Builder
The Google Cloud Storage location where the input file will be read from.
Protobuf type google.cloud.documentai.v1beta2.GcsSource
GeometryProto
InputConfig
The desired input location and metadata.
Protobuf type google.cloud.documentai.v1beta2.InputConfig
InputConfig.Builder
The desired input location and metadata.
Protobuf type google.cloud.documentai.v1beta2.InputConfig
KeyValuePairHint
User-provided hint for key value pair.
Protobuf type google.cloud.documentai.v1beta2.KeyValuePairHint
KeyValuePairHint.Builder
User-provided hint for key value pair.
Protobuf type google.cloud.documentai.v1beta2.KeyValuePairHint
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.
Protobuf type google.cloud.documentai.v1beta2.NormalizedVertex
NormalizedVertex.Builder
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.
Protobuf type google.cloud.documentai.v1beta2.NormalizedVertex
OcrParams
Parameters to control Optical Character Recognition (OCR) behavior.
Protobuf type google.cloud.documentai.v1beta2.OcrParams
OcrParams.Builder
Parameters to control Optical Character Recognition (OCR) behavior.
Protobuf type google.cloud.documentai.v1beta2.OcrParams
OperationMetadata
Contains metadata for the BatchProcessDocuments operation.
Protobuf type google.cloud.documentai.v1beta2.OperationMetadata
OperationMetadata.Builder
Contains metadata for the BatchProcessDocuments operation.
Protobuf type google.cloud.documentai.v1beta2.OperationMetadata
OutputConfig
The desired output location and metadata.
Protobuf type google.cloud.documentai.v1beta2.OutputConfig
OutputConfig.Builder
The desired output location and metadata.
Protobuf type google.cloud.documentai.v1beta2.OutputConfig
ProcessDocumentRequest
Request to process one document.
Protobuf type google.cloud.documentai.v1beta2.ProcessDocumentRequest
ProcessDocumentRequest.Builder
Request to process one document.
Protobuf type google.cloud.documentai.v1beta2.ProcessDocumentRequest
ProcessDocumentResponse
Response to a single document processing request.
Protobuf type google.cloud.documentai.v1beta2.ProcessDocumentResponse
ProcessDocumentResponse.Builder
Response to a single document processing request.
Protobuf type google.cloud.documentai.v1beta2.ProcessDocumentResponse
TableBoundHint
A hint for a table bounding box on the page for table parsing.
Protobuf type google.cloud.documentai.v1beta2.TableBoundHint
TableBoundHint.Builder
A hint for a table bounding box on the page for table parsing.
Protobuf type google.cloud.documentai.v1beta2.TableBoundHint
TableExtractionParams
Parameters to control table extraction behavior.
Protobuf type google.cloud.documentai.v1beta2.TableExtractionParams
TableExtractionParams.Builder
Parameters to control table extraction behavior.
Protobuf type google.cloud.documentai.v1beta2.TableExtractionParams
Vertex
A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
Protobuf type google.cloud.documentai.v1beta2.Vertex
Vertex.Builder
A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
Protobuf type google.cloud.documentai.v1beta2.Vertex
Interfaces
AutoMlParamsOrBuilder
BatchProcessDocumentsRequestOrBuilder
BatchProcessDocumentsResponseOrBuilder
BoundingPolyOrBuilder
Document.EntityOrBuilder
Document.EntityRelationOrBuilder
Document.LabelOrBuilder
Document.Page.BlockOrBuilder
Document.Page.DetectedLanguageOrBuilder
Document.Page.DimensionOrBuilder
Document.Page.FormFieldOrBuilder
Document.Page.LayoutOrBuilder
Document.Page.LineOrBuilder
Document.Page.ParagraphOrBuilder
Document.Page.Table.TableCellOrBuilder
Document.Page.Table.TableRowOrBuilder
Document.Page.TableOrBuilder
Document.Page.Token.DetectedBreakOrBuilder
Document.Page.TokenOrBuilder
Document.Page.VisualElementOrBuilder
Document.PageAnchor.PageRefOrBuilder
Document.PageAnchorOrBuilder
Document.PageOrBuilder
Document.ShardInfoOrBuilder
Document.Style.FontSizeOrBuilder
Document.StyleOrBuilder
Document.TextAnchor.TextSegmentOrBuilder
Document.TextAnchorOrBuilder
DocumentOrBuilder
EntityExtractionParamsOrBuilder
FormExtractionParamsOrBuilder
GcsDestinationOrBuilder
GcsSourceOrBuilder
InputConfigOrBuilder
KeyValuePairHintOrBuilder
NormalizedVertexOrBuilder
OcrParamsOrBuilder
OperationMetadataOrBuilder
OutputConfigOrBuilder
ProcessDocumentRequestOrBuilder
ProcessDocumentResponseOrBuilder
TableBoundHintOrBuilder
TableExtractionParamsOrBuilder
VertexOrBuilder
Enums
Document.Label.SourceCase
Document.Page.Layout.Orientation
Detected human reading orientation.
Protobuf enum google.cloud.documentai.v1beta2.Document.Page.Layout.Orientation
Document.Page.Token.DetectedBreak.Type
Enum to denote the type of break found.
Protobuf enum
google.cloud.documentai.v1beta2.Document.Page.Token.DetectedBreak.Type
Document.PageAnchor.PageRef.LayoutType
The type of layout that is being referenced.
Protobuf enum
google.cloud.documentai.v1beta2.Document.PageAnchor.PageRef.LayoutType
Document.SourceCase
InputConfig.SourceCase
OperationMetadata.State
Protobuf enum google.cloud.documentai.v1beta2.OperationMetadata.State