Package Classes (3.0.0)

Service to call Document AI to process documents according to the processor's definition. Processors are built using state-of-the-art Google AI such as natural language, computer vision, and translation to extract structured information from unstructured or semi-structured documents.

Service to call Document AI to process documents according to the processor's definition. Processors are built using state-of-the-art Google AI such as natural language, computer vision, and translation to extract structured information from unstructured or semi-structured documents.

A pager for iterating through list_evaluations requests.

This class thinly wraps an initial ListEvaluationsResponse object, and provides an __aiter__ method to iterate through its evaluations field.

If there are more pages, the __aiter__ method will make additional ListEvaluations requests and continue to iterate through the evaluations field on the corresponding responses.

All the usual ListEvaluationsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_evaluations requests.

This class thinly wraps an initial ListEvaluationsResponse object, and provides an __iter__ method to iterate through its evaluations field.

If there are more pages, the __iter__ method will make additional ListEvaluations requests and continue to iterate through the evaluations field on the corresponding responses.

All the usual ListEvaluationsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processor_types requests.

This class thinly wraps an initial ListProcessorTypesResponse object, and provides an __aiter__ method to iterate through its processor_types field.

If there are more pages, the __aiter__ method will make additional ListProcessorTypes requests and continue to iterate through the processor_types field on the corresponding responses.

All the usual ListProcessorTypesResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processor_types requests.

This class thinly wraps an initial ListProcessorTypesResponse object, and provides an __iter__ method to iterate through its processor_types field.

If there are more pages, the __iter__ method will make additional ListProcessorTypes requests and continue to iterate through the processor_types field on the corresponding responses.

All the usual ListProcessorTypesResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processor_versions requests.

This class thinly wraps an initial ListProcessorVersionsResponse object, and provides an __aiter__ method to iterate through its processor_versions field.

If there are more pages, the __aiter__ method will make additional ListProcessorVersions requests and continue to iterate through the processor_versions field on the corresponding responses.

All the usual ListProcessorVersionsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processor_versions requests.

This class thinly wraps an initial ListProcessorVersionsResponse object, and provides an __iter__ method to iterate through its processor_versions field.

If there are more pages, the __iter__ method will make additional ListProcessorVersions requests and continue to iterate through the processor_versions field on the corresponding responses.

All the usual ListProcessorVersionsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processors requests.

This class thinly wraps an initial ListProcessorsResponse object, and provides an __aiter__ method to iterate through its processors field.

If there are more pages, the __aiter__ method will make additional ListProcessors requests and continue to iterate through the processors field on the corresponding responses.

All the usual ListProcessorsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processors requests.

This class thinly wraps an initial ListProcessorsResponse object, and provides an __iter__ method to iterate through its processors field.

If there are more pages, the __iter__ method will make additional ListProcessors requests and continue to iterate through the processors field on the corresponding responses.

All the usual ListProcessorsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

Encodes the detailed information of a barcode.

The common config to specify a set of documents used as input.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

The long-running operation metadata for BatchProcessDocuments.

The status of a each individual document in the batch process.

Possible states of the batch processing operation.

Request message for BatchProcessDocuments.

The abstract base class for a message.

Response message for BatchProcessDocuments.

A bounding polygon for the detected image annotation.

The common metadata for long running operations.

State of the longrunning operation.

Request message for the CreateProcessor method. Notice this request is sent to a regionalized backend service. If the ProcessorType isn't available in that region, the creation fails.

The long-running operation metadata for the DeleteProcessor method.

Request message for the DeleteProcessor method.

The long-running operation metadata for the DeleteProcessorVersion method.

Request message for the DeleteProcessorVersion method.

The long-running operation metadata for the DeployProcessorVersion method.

Request message for the DeployProcessorVersion method.

Response message for the DeployProcessorVersion method.

The long-running operation metadata for the DisableProcessor method.

Request message for the DisableProcessor method.

Response message for the DisableProcessor method. Intentionally empty proto for adding fields in future.

Document represents the canonical document resource in Document AI. It is an interchange format that provides insights into documents and allows for collaboration between users and Document AI to iterate and optimize for quality.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Represents the chunks that the document is divided into.

Represents a chunk.

Represents the page footer associated with the chunk.

Represents the page header associated with the chunk.

Represents where the chunk starts and ends in the document.

Represents the parsed layout of a document as a collection of blocks that the document is divided into.

Represents a block. A block could be one of the various types (text, table, list) supported.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Represents a list type block.

Represents an entry in the list.

Represents where the block starts and ends in the document.

Represents a table type block.

Represents a cell in a table row.

Represents a row in a table.

Represents a text type block.

An entity that could be a phrase in the text or a property that belongs to the document. It is a known entity type, such as a person, an organization, or location.

Parsed and normalized entity value.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Relationship between Entities.

A page in a Document.

A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.

A detected barcode.

Detected language for a structural component.

Dimension for the page.

A form field detected on the page.

Rendered image contents for this page.

Image quality scores for the page image.

Image Quality Defects

Visual element describing a layout unit on a page.

Detected human reading orientation.

A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.

Representation for transformation matrix, intended to be compatible and used with OpenCV format for image manipulation.

A collection of lines that a human would perceive as a paragraph.

A detected symbol.

A table representation similar to HTML table structure.

A cell representation inside the table.

A row of table cells.

A detected token.

Detected break at the end of a Token.

Enum to denote the type of break found.

Font and other text style attributes.

Detected non-text visual elements e.g. checkbox, signature etc. on the page.

Referencing the visual context of the entity in the Document.pages. Page anchors can be cross-page, consist of multiple bounding polygons and optionally reference specific layout element types.

Represents a weak reference to a page element within a document.

The type of layout that is being referenced.

Structure to identify provenance relationships between annotations in different revisions.

If a processor or agent does an explicit operation on existing elements.

The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.

Contains past or forward revisions of this document.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Human Review information of the document.

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.

Annotation for common text style attributes. This adheres to CSS conventions as much as possible.

Font size with unit.

Text reference indexing into the Document.text.

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

This message is used for text changes aka. OCR corrections.

Config that controls the output of documents. All documents will be written as a JSON file.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

The configuration used when outputting documents.

The sharding config for the output document.

The schema defines the output of the processed document by a processor.

EntityType is the wrapper of a label of the corresponding model with detailed attributes and limitations for entity-based processors. Multiple types can also compose a dependency tree to represent nested types.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Defines the a list of enum values.

Defines properties that can be part of the entity type.

Types of occurrences of the entity type in the document. This represents the number of instances, not mentions, of an entity. For example, a bank statement might only have one account_number, but this account number can be mentioned in several places on the document. In this case, the account_number is considered a REQUIRED_ONCE entity type. If, on the other hand, we expect a bank statement to contain the status of multiple different accounts for the customers, the occurrence type is set to REQUIRED_MULTIPLE.

Metadata for global schema behavior.

The long-running operation metadata for the EnableProcessor method.

Request message for the EnableProcessor method.

Response message for the EnableProcessor method. Intentionally empty proto for adding fields in future.

Metadata of the EvaluateProcessorVersion method.

Evaluates the given ProcessorVersion against the supplied documents.

Response of the EvaluateProcessorVersion method.

An evaluation of a ProcessorVersion's performance.

Evaluations metrics, at a specific confidence level.

Evaluation counters for the documents that were used.

The abstract base class for a message.

Evaluation metrics, either in aggregate or about a specific entity.

Metrics across multiple confidence levels.

A type that determines how metrics should be interpreted.

Gives a short summary of an evaluation, and links to the evaluation itself.

Request message for the FetchProcessorTypes method. Some processor types may require the project be added to an allowlist.

Response message for the FetchProcessorTypes method.

Specifies a document stored on Cloud Storage.

Specifies a set of documents on Cloud Storage.

Specifies all documents on Cloud Storage with a common prefix.

Retrieves a specific Evaluation.

Request message for the GetProcessor method.

Request message for the GetProcessorType method.

Request message for the GetProcessorVersion method.

The status of human review on a processed document.

The final state of human review on a processed document.

Retrieves a list of evaluations for a given ProcessorVersion.

The response from ListEvaluations.

Request message for the ListProcessorTypes method. Some processor types may require the project be added to an allowlist.

Response message for the ListProcessorTypes method.

Request message for list all processor versions belongs to a processor.

Response message for the ListProcessorVersions method.

Request message for list all processors belongs to a project.

Response message for the ListProcessors method.

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.

Config for Document OCR.

Hints for OCR Engine

Configurations for premium OCR features.

Options for Process API

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

A list of individual page numbers.

Serving config for layout parser processor.

Serving config for chunking.

Request message for the ProcessDocument method.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

The abstract base class for a message.

Response message for the ProcessDocument method.

The first-class citizen for Document AI. Each processor defines how to extract structural information from a document.

The possible states of the processor.

A processor type is responsible for performing a certain document understanding task on a certain type of document.

The location information about where the processor is available.

A processor version is an implementation of a processor. Each processor can have multiple versions, pretrained by Google internally or uptrained by the customer. A processor can only have one default version at a time. Its document-processing behavior is defined by that version.

Information about the upcoming deprecation of this processor version.

Information about Generative AI model-based processor versions.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Information for a custom Generative AI model created by the user. These are created with Create New Version in either the Call foundation model or Fine tuning tabs.

The type of custom model created by the user.

Information for a pretrained Google-managed foundation model.

The possible model types of the processor version.

The possible states of the processor version.

Contains the alias and the aliased resource name of processor version.

Payload message of raw document content (bytes).

The long-running operation metadata for the ReviewDocument method.

Request message for the ReviewDocument method.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

The priority level of the human review task.

Response message for the ReviewDocument method.

Possible states of the review operation.

The long-running operation metadata for the SetDefaultProcessorVersion method.

Request message for the SetDefaultProcessorVersion method.

Response message for the SetDefaultProcessorVersion method.

The metadata that represents a processor version being created.

The dataset validation information. This includes any and all errors with documents and the dataset.

Request message for the TrainProcessorVersion method.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Options to control the training of the Custom Document Extraction (CDE) Processor.

Training Method for CDE. TRAINING_METHOD_UNSPECIFIED will fall back to MODEL_BASED.

Options to control foundation model tuning of the processor.

The input data used to train a new ProcessorVersion.

The response for TrainProcessorVersion.

The long-running operation metadata for the UndeployProcessorVersion method.

Request message for the UndeployProcessorVersion method.

Response message for the UndeployProcessorVersion method.

A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.

Service to call Document AI to process documents according to the processor's definition. Processors are built using state-of-the-art Google AI such as natural language, computer vision, and translation to extract structured information from unstructured or semi-structured documents.

Service to call Document AI to process documents according to the processor's definition. Processors are built using state-of-the-art Google AI such as natural language, computer vision, and translation to extract structured information from unstructured or semi-structured documents.

A pager for iterating through list_evaluations requests.

This class thinly wraps an initial ListEvaluationsResponse object, and provides an __aiter__ method to iterate through its evaluations field.

If there are more pages, the __aiter__ method will make additional ListEvaluations requests and continue to iterate through the evaluations field on the corresponding responses.

All the usual ListEvaluationsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_evaluations requests.

This class thinly wraps an initial ListEvaluationsResponse object, and provides an __iter__ method to iterate through its evaluations field.

If there are more pages, the __iter__ method will make additional ListEvaluations requests and continue to iterate through the evaluations field on the corresponding responses.

All the usual ListEvaluationsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processor_types requests.

This class thinly wraps an initial ListProcessorTypesResponse object, and provides an __aiter__ method to iterate through its processor_types field.

If there are more pages, the __aiter__ method will make additional ListProcessorTypes requests and continue to iterate through the processor_types field on the corresponding responses.

All the usual ListProcessorTypesResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processor_types requests.

This class thinly wraps an initial ListProcessorTypesResponse object, and provides an __iter__ method to iterate through its processor_types field.

If there are more pages, the __iter__ method will make additional ListProcessorTypes requests and continue to iterate through the processor_types field on the corresponding responses.

All the usual ListProcessorTypesResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processor_versions requests.

This class thinly wraps an initial ListProcessorVersionsResponse object, and provides an __aiter__ method to iterate through its processor_versions field.

If there are more pages, the __aiter__ method will make additional ListProcessorVersions requests and continue to iterate through the processor_versions field on the corresponding responses.

All the usual ListProcessorVersionsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processor_versions requests.

This class thinly wraps an initial ListProcessorVersionsResponse object, and provides an __iter__ method to iterate through its processor_versions field.

If there are more pages, the __iter__ method will make additional ListProcessorVersions requests and continue to iterate through the processor_versions field on the corresponding responses.

All the usual ListProcessorVersionsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processors requests.

This class thinly wraps an initial ListProcessorsResponse object, and provides an __aiter__ method to iterate through its processors field.

If there are more pages, the __aiter__ method will make additional ListProcessors requests and continue to iterate through the processors field on the corresponding responses.

All the usual ListProcessorsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_processors requests.

This class thinly wraps an initial ListProcessorsResponse object, and provides an __iter__ method to iterate through its processors field.

If there are more pages, the __iter__ method will make additional ListProcessors requests and continue to iterate through the processors field on the corresponding responses.

All the usual ListProcessorsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

Service to call Cloud DocumentAI to manage document collection (dataset).

Service to call Cloud DocumentAI to manage document collection (dataset).

A pager for iterating through list_documents requests.

This class thinly wraps an initial ListDocumentsResponse object, and provides an __aiter__ method to iterate through its document_metadata field.

If there are more pages, the __aiter__ method will make additional ListDocuments requests and continue to iterate through the document_metadata field on the corresponding responses.

All the usual ListDocumentsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

A pager for iterating through list_documents requests.

This class thinly wraps an initial ListDocumentsResponse object, and provides an __iter__ method to iterate through its document_metadata field.

If there are more pages, the __iter__ method will make additional ListDocuments requests and continue to iterate through the document_metadata field on the corresponding responses.

All the usual ListDocumentsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

Encodes the detailed information of a barcode.

Dataset documents that the batch operation will be applied to.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

List of individual DocumentIds.

The status of each individual document in the batch delete process.

Response of the delete documents operation.

The common config to specify a set of documents used as input.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

The long-running operation metadata for BatchProcessDocuments.

The status of a each individual document in the batch process.

Possible states of the batch processing operation.

Request message for BatchProcessDocuments.

The message for input config in batch process.

The output configuration in the BatchProcessDocuments method.

The abstract base class for a message.

Response message for BatchProcessDocuments.

A bounding polygon for the detected image annotation.

The common metadata for long running operations.

State of the longrunning operation.

Request message for the CreateProcessor method. Notice this request is sent to a regionalized backend service. If the ProcessorType isn't available in that region, the creation fails.

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

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Configuration specific to the Document AI Warehouse-based implementation.

Configuration specific to the Cloud Storage-based implementation.

Configuration specific to spanner-based indexing.

Different states of a dataset.

Configuration specific to an unmanaged dataset.

Dataset Schema.

Documents belonging to a dataset will be split into different groups referred to as splits: train, test.

The long-running operation metadata for the DeleteProcessor method.

Request message for the DeleteProcessor method.

The long-running operation metadata for the DeleteProcessorVersion method.

Request message for the DeleteProcessorVersion method.

The long-running operation metadata for the DeployProcessorVersion method.

Request message for the DeployProcessorVersion method.

Response message for the DeployProcessorVersion method.

The long-running operation metadata for the DisableProcessor method.

Request message for the DisableProcessor method.

Response message for the DisableProcessor method. Intentionally empty proto for adding fields in future.

Document represents the canonical document resource in Document AI. It is an interchange format that provides insights into documents and allows for collaboration between users and Document AI to iterate and optimize for quality.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Represents the chunks that the document is divided into.

Represents a chunk.

Represents the page footer associated with the chunk.

Represents the page header associated with the chunk.

Represents where the chunk starts and ends in the document.

Represents the parsed layout of a document as a collection of blocks that the document is divided into.

Represents a block. A block could be one of the various types (text, table, list) supported.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Represents a list type block.

Represents an entry in the list.

Represents where the block starts and ends in the document.

Represents a table type block.

Represents a cell in a table row.

Represents a row in a table.

Represents a text type block.

An entity that could be a phrase in the text or a property that belongs to the document. It is a known entity type, such as a person, an organization, or location.

Parsed and normalized entity value.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Relationship between Entities.

A page in a Document.

A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.

A detected barcode.

Detected language for a structural component.

Dimension for the page.

A form field detected on the page.

Rendered image contents for this page.

Image quality scores for the page image.

Image Quality Defects

Visual element describing a layout unit on a page.

Detected human reading orientation.

A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.

Representation for transformation matrix, intended to be compatible and used with OpenCV format for image manipulation.

A collection of lines that a human would perceive as a paragraph.

A detected symbol.

A table representation similar to HTML table structure.

A cell representation inside the table.

A row of table cells.

A detected token.

Detected break at the end of a Token.

Enum to denote the type of break found.

Font and other text style attributes.

Detected non-text visual elements e.g. checkbox, signature etc. on the page.

Referencing the visual context of the entity in the Document.pages. Page anchors can be cross-page, consist of multiple bounding polygons and optionally reference specific layout element types.

Represents a weak reference to a page element within a document.

The type of layout that is being referenced.

Structure to identify provenance relationships between annotations in different revisions.

If a processor or agent does an explicit operation on existing elements.

The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.

Contains past or forward revisions of this document.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Human Review information of the document.

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.

Annotation for common text style attributes. This adheres to CSS conventions as much as possible.

Font size with unit.

Text reference indexing into the Document.text.

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

This message is used for text changes aka. OCR corrections.

Document Identifier.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Identifies a document uniquely within the scope of a dataset in the user-managed Cloud Storage option.

Identifies a document uniquely within the scope of a dataset in unmanaged option.

Describes the labeling status of a document.

Metadata about a document.

Config that controls the output of documents. All documents will be written as a JSON file.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

The configuration used when outputting documents.

The sharding config for the output document.

Range of pages present in a document.

The schema defines the output of the processed document by a processor.

EntityType is the wrapper of a label of the corresponding model with detailed attributes and limitations for entity-based processors. Multiple types can also compose a dependency tree to represent nested types.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Defines the a list of enum values.

Defines properties that can be part of the entity type.

Types of occurrences of the entity type in the document. This represents the number of instances, not mentions, of an entity. For example, a bank statement might only have one account_number, but this account number can be mentioned in several places on the document. In this case, the account_number is considered a REQUIRED_ONCE entity type. If, on the other hand, we expect a bank statement to contain the status of multiple different accounts for the customers, the occurrence type is set to REQUIRED_MULTIPLE.

Metadata for global schema behavior.

The long-running operation metadata for the EnableProcessor method.

Request message for the EnableProcessor method.

Response message for the EnableProcessor method. Intentionally empty proto for adding fields in future.

Metadata about an entity type.

Metadata of the EvaluateProcessorVersion method.

Evaluates the given ProcessorVersion against the supplied documents.

Response of the EvaluateProcessorVersion method.

An evaluation of a ProcessorVersion's performance.

Evaluations metrics, at a specific confidence level.

Evaluation counters for the documents that were used.

The abstract base class for a message.

Evaluation metrics, either in aggregate or about a specific entity.

Metrics across multiple confidence levels.

A type that determines how metrics should be interpreted.

Gives a short summary of an evaluation, and links to the evaluation itself.

Request message for the FetchProcessorTypes method. Some processor types may require the project be added to an allowlist.

Response message for the FetchProcessorTypes method.

Metadata for how this field value is extracted.

Specifies a document stored on Cloud Storage.

Specifies a set of documents on Cloud Storage.

Specifies all documents on Cloud Storage with a common prefix.

Request for GetDatasetSchema.

Retrieves a specific Evaluation.

Request message for the GetProcessor method.

Request message for the GetProcessorType method.

Request message for the GetProcessorVersion method.

The status of human review on a processed document.

The final state of human review on a processed document.

Metadata of the import document operation.

The validation status of each import config. Status is set to an error if there are no documents to import in the import_config, or OK if the operation will try to proceed with at least one document.

The status of each individual document in the import process.

Config for importing documents. Each batch can have its own dataset split type.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

The config for auto-split.

Response of the import document operation.

The long-running operation metadata for the ImportProcessorVersion method.

The request message for the ImportProcessorVersion method.

The Document AI Service Agent <https://cloud.google.com/iam/docs/service-agents> of the destination project must have Document AI Editor role <https://cloud.google.com/document-ai/docs/access-control/iam-roles> on the source project.

The destination project is specified as part of the parent field. The source project is specified as part of the source or external_processor_version_source field.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

The external source processor version.

The response message for the ImportProcessorVersion method.

Retrieves a list of evaluations for a given ProcessorVersion.

The response from ListEvaluations.

Request message for the ListProcessorTypes method. Some processor types may require the project be added to an allowlist.

Response message for the ListProcessorTypes method.

Request message for list all processor versions belongs to a processor.

Response message for the ListProcessorVersions method.

Request message for list all processors belongs to a project.

Response message for the ListProcessors method.

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.

Config for Document OCR.

Hints for OCR Engine

Configurations for premium OCR features.

Options for Process API

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

A list of individual page numbers.

Serving config for layout parser processor.

Serving config for chunking.

Request message for the ProcessDocument method.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

The abstract base class for a message.

Response message for the ProcessDocument method.

The first-class citizen for Document AI. Each processor defines how to extract structural information from a document.

The possible states of the processor.

A processor type is responsible for performing a certain document understanding task on a certain type of document.

The location information about where the processor is available.

A processor version is an implementation of a processor. Each processor can have multiple versions, pretrained by Google internally or uptrained by the customer. A processor can only have one default version at a time. Its document-processing behavior is defined by that version.

Information about the upcoming deprecation of this processor version.

Information about Generative AI model-based processor versions.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Information for a custom Generative AI model created by the user. These are created with Create New Version in either the Call foundation model or Fine tuning tabs.

The type of custom model created by the user.

Information for a pretrained Google-managed foundation model.

The possible model types of the processor version.

The possible states of the processor version.

Contains the alias and the aliased resource name of processor version.

Metadata about a property.

Payload message of raw document content (bytes).

The long-running operation metadata for the ReviewDocument method.

State of the long-running operation.

Request message for the ReviewDocument method.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

The priority level of the human review task.

Response message for the ReviewDocument method.

Possible states of the review operation.

The revision reference specifies which revision on the document to read.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Some predefined revision cases.

The long-running operation metadata for the SetDefaultProcessorVersion method.

Request message for the SetDefaultProcessorVersion method.

Response message for the SetDefaultProcessorVersion method.

Metadata for document summarization.

The Format enum.

The Length enum.

The metadata that represents a processor version being created.

The dataset validation information. This includes any and all errors with documents and the dataset.

Request message for the TrainProcessorVersion method.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Options to control the training of the Custom Document Extraction (CDE) Processor.

Training Method for CDE. TRAINING_METHOD_UNSPECIFIED will fall back to MODEL_BASED.

Options to control foundation model tuning of the processor.

The input data used to train a new ProcessorVersion.

The response for TrainProcessorVersion.

The long-running operation metadata for the UndeployProcessorVersion method.

Request message for the UndeployProcessorVersion method.

Response message for the UndeployProcessorVersion method.

Request for UpdateDatasetSchema.

A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.

API documentation for documentai_v1.services.document_processor_service.pagers module.

API documentation for documentai_v1beta3.services.document_processor_service.pagers module.

API documentation for documentai_v1beta3.services.document_service.pagers module.