Cloud Document AI API Connector Overview
Stay organized with collections
Save and categorize content based on your preferences.
The Workflows connector defines the built-in
functions that can be used to access other Google Cloud products within a
workflow.
This page provides an overview of the individual connector.
There is no need to import or load connector libraries in a workflow—connectors
work out of the box when used in a call step.
Cloud Document AI API
Service to parse structured information from unstructured or semi-structured documents using state-of-the-art Google AI such as natural language, computer vision, translation, and AutoML.
To learn more, see the Cloud Document AI API documentation.
Cloud Document AI connector sample
Module: googleapis.documentai.v1.projects.locations
| Functions |
fetchProcessorTypes |
Fetches processor types. Note that we do not use ListProcessorTypes here
because it is not paginated. |
get |
Gets information about a location. |
list |
Lists information about the supported locations for this service. |
Module: googleapis.documentai.v1.projects.locations.operations
| Functions |
cancel |
Starts asynchronous cancellation on a long-running operation. The server
makes a best effort to cancel the operation, but success is not
guaranteed. If the server doesn't support this method, it returns
google.rpc.Code.UNIMPLEMENTED. Clients can use Operations.GetOperation
or other methods to check whether the cancellation succeeded or whether
the operation completed despite cancellation. On successful
cancellation, the operation is not deleted; instead, it becomes an
operation with an Operation.error value with a google.rpc.Status.code of
1, corresponding to Code.CANCELLED. |
get |
Gets the latest state of a long-running operation. Clients can use this
method to poll the operation result at intervals as recommended by the
API service. |
list |
Lists operations that match the specified filter in the request. If the
server doesn't support this method, it returns UNIMPLEMENTED. NOTE:
the name binding allows API services to override the binding to use
different resource name schemes, such as users/*/operations. To
override the binding, API services can add a binding such as
"/v1/{name=users/*}/operations" to their service configuration. For
backwards compatibility, the default name includes the operations
collection id, however overriding users must ensure the name binding is
the parent resource, without the operations collection id. |
Module: googleapis.documentai.v1.projects.locations.processorTypes
| Functions |
get |
Gets a processor type detail. |
list |
Lists the processor types that exist. |
Module: googleapis.documentai.v1.projects.locations.processors
| Functions |
batchProcess |
LRO endpoint to batch process many documents. The output is written to
Cloud Storage as JSON in the [Document] format. |
create |
Creates a processor from the type processor that the user chose. The
processor will be at "ENABLED" state by default after its creation. |
delete |
Deletes the processor, unloads all deployed model artifacts if it was
enabled and then deletes all artifacts associated with this processor. |
disable |
Disables a processor |
enable |
Enables a processor |
get |
Gets a processor detail. |
list |
Lists all processors which belong to this project. |
process |
Processes a single document. |
setDefaultProcessorVersion |
Set the default (active) version of a Processor that will be used in
ProcessDocument and BatchProcessDocuments. |
Module: googleapis.documentai.v1.projects.locations.processors.humanReviewConfig
| Functions |
reviewDocument |
Send a document for Human Review. The input document should be processed
by the specified processor. |
Module: googleapis.documentai.v1.projects.locations.processors.processorVersions
| Functions |
batchProcess |
LRO endpoint to batch process many documents. The output is written to
Cloud Storage as JSON in the [Document] format. |
delete |
Deletes the processor version, all artifacts under the processor version
will be deleted. |
deploy |
Deploys the processor version. |
get |
Gets a processor version detail. |
list |
Lists all versions of a processor. |
process |
Processes a single document. |
undeploy |
Undeploys the processor version. |
Module: googleapis.documentai.v1.projects.operations
| Functions |
get |
Gets the latest state of a long-running operation. Clients can use this
method to poll the operation result at intervals as recommended by the
API service. |
Module: googleapis.documentai.v1beta2.projects.documents
| Functions |
batchProcess |
LRO endpoint to batch process many documents. The output is written to
Cloud Storage as JSON in the [Document] format. |
process |
Processes a single document. |
Module: googleapis.documentai.v1beta2.projects.locations.documents
| Functions |
batchProcess |
LRO endpoint to batch process many documents. The output is written to
Cloud Storage as JSON in the [Document] format. |
process |
Processes a single document. |
Module: googleapis.documentai.v1beta2.projects.locations.operations
| Functions |
get |
Gets the latest state of a long-running operation. Clients can use this
method to poll the operation result at intervals as recommended by the
API service. |
Module: googleapis.documentai.v1beta2.projects.operations
| Functions |
get |
Gets the latest state of a long-running operation. Clients can use this
method to poll the operation result at intervals as recommended by the
API service. |
Module: googleapis.documentai.v1beta3.projects.locations
| Functions |
fetchProcessorTypes |
Fetches processor types. Note that we do not use ListProcessorTypes here
because it is not paginated. |
get |
Gets information about a location. |
list |
Lists information about the supported locations for this service. |
Module: googleapis.documentai.v1beta3.projects.locations.operations
| Functions |
cancel |
Starts asynchronous cancellation on a long-running operation. The server
makes a best effort to cancel the operation, but success is not
guaranteed. If the server doesn't support this method, it returns
google.rpc.Code.UNIMPLEMENTED. Clients can use Operations.GetOperation
or other methods to check whether the cancellation succeeded or whether
the operation completed despite cancellation. On successful
cancellation, the operation is not deleted; instead, it becomes an
operation with an Operation.error value with a google.rpc.Status.code of
1, corresponding to Code.CANCELLED. |
get |
Gets the latest state of a long-running operation. Clients can use this
method to poll the operation result at intervals as recommended by the
API service. |
list |
Lists operations that match the specified filter in the request. If the
server doesn't support this method, it returns UNIMPLEMENTED. NOTE:
the name binding allows API services to override the binding to use
different resource name schemes, such as users/*/operations. To
override the binding, API services can add a binding such as
"/v1/{name=users/*}/operations" to their service configuration. For
backwards compatibility, the default name includes the operations
collection id, however overriding users must ensure the name binding is
the parent resource, without the operations collection id. |
Module: googleapis.documentai.v1beta3.projects.locations.processorTypes
| Functions |
get |
Gets a processor type detail. |
list |
Lists the processor types that exist. |
Module: googleapis.documentai.v1beta3.projects.locations.processors
| Functions |
batchProcess |
LRO endpoint to batch process many documents. The output is written to
Cloud Storage as JSON in the [Document] format. |
create |
Creates a processor from the type processor that the user chose. The
processor will be at "ENABLED" state by default after its creation. |
delete |
Deletes the processor, unloads all deployed model artifacts if it was
enabled and then deletes all artifacts associated with this processor. |
disable |
Disables a processor |
enable |
Enables a processor |
get |
Gets a processor detail. |
list |
Lists all processors which belong to this project. |
process |
Processes a single document. |
setDefaultProcessorVersion |
Set the default (active) version of a Processor that will be used in
ProcessDocument and BatchProcessDocuments. |
Module: googleapis.documentai.v1beta3.projects.locations.processors.humanReviewConfig
| Functions |
reviewDocument |
Send a document for Human Review. The input document should be processed
by the specified processor. |
Module: googleapis.documentai.v1beta3.projects.locations.processors.processorVersions
| Functions |
batchProcess |
LRO endpoint to batch process many documents. The output is written to
Cloud Storage as JSON in the [Document] format. |
delete |
Deletes the processor version, all artifacts under the processor version
will be deleted. |
deploy |
Deploys the processor version. |
evaluateProcessorVersion |
Evaluates a ProcessorVersion against annotated documents, producing an
Evaluation. |
get |
Gets a processor version detail. |
list |
Lists all versions of a processor. |
process |
Processes a single document. |
train |
Trains a new processor version. Operation metadata is returned as
cloud_documentai_core.TrainProcessorVersionMetadata. |
undeploy |
Undeploys the processor version. |
Module: googleapis.documentai.v1beta3.projects.locations.processors.processorVersions.evaluations
| Functions |
get |
Retrieves a specific evaluation. |
list |
Retrieves a set of evaluations for a given processor version. |
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2026-07-22 UTC.
[null,null,["Last updated 2026-07-22 UTC."],[],[]]