Doc AI - Batch Process task

The Doc AI - Batch Process task lets you send a single batch (asynchronous) request to the Document AI processor to process multiple documents. Document AI then starts a long-running operation (LRO) and stores the processed results in a Cloud Storage bucket. The Document AI processor is a Cloud Document AI component that performs varies document processing actions such as, classify, split, parse or analysis of a document.

Cloud Document AI is a Google Cloud service that allows you 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.

Before you begin

Ensure that you perform the following tasks in your Google Cloud project before configuring the Doc AI - Batch Process task:

  1. Enable the Cloud Document AI API (documentai.googleapis.com).

    Enable the Cloud Document AI API

  2. Create an authentication profile. Apigee Integration uses an authentication profile to connect to an authentication endpoint for the Doc AI - Batch Process task.

Configure the Doc AI - Batch Process task

  1. In the Apigee UI, select your Apigee Organization.
  2. Click Develop > Integrations.
  3. Select an existing integration or create a new integration by clicking Create Integration.

    If you are creating a new integration:

    1. Enter a name and description in the Create Integration dialog.
    2. Select a Region for the integration from the list of supported regions.
    3. Click Create.

    This opens the integration in the integration designer.

  4. In the integration designer navigation bar, click +Add a task/trigger > Tasks to view the list of available tasks.
  5. Click and place the Doc AI - Batch Process element in the integration designer.
  6. Click the Doc AI - Batch Process element on the designer to view the Doc AI - Batch Process task configuration pane.
  7. Go to Authentication, and select an existing authentication profile that you want to use.

    Optional. If you have not created an authentication profile prior to configuring the task, Click + New authentication profile and follow the steps as mentioned in Create a new authentication profile.

  8. Go to Task Input, and configure the displayed inputs fields using the following Task input parameters table.

    Changes to the inputs fields are saved automatically.

Task input parameters

The following table describes the input parameters of the Doc AI - Batch Process task:

Property Data type Description
Region String Cloud Document AI location for the processor. For example: us - United States.
ProjectsId String Your Google Cloud project ID.
ProcessorsIdString The ID of your custom processor.
Request JSON See request JSON structure.

Task output

The Doc AI - Batch Process task returns the name of your long-running operation (LRO), similar to the following sample output:

{
    "name": "projects/[PROJECT_ID]/locations/[LOCATION]/operations/[OPERATION_ID]"
}

Error handling strategy

An error handling strategy for a task specifies the action to take if the task fails due to a temporary error. For information about how to use an error handling strategy, and to know about the different types of error handling strategies, see Error handling strategies.

What's next

  1. Add edges and edge conditions.
  2. Test and publish your integration.
  3. Configure a trigger.
  4. Add a Data Mapping task.
  5. See all tasks for Google Cloud services.