Overview

Document Understanding^TM Cloud APIs can be an alternative to the RPA approach. By initiating an API call, you can:

• Find out information about the project, extractors, or classifiers used within the project.
• Use the digitization APIs.
• Classify documents using specialized (Classifying a document example) and generative (Generative classifier example) models.
  Important:

  This feature is currently part of an audit process and is not to be considered part of the FedRAMP Authorization until the review is finalized. See here the full list of features currently under review.

• Extract document data using specialized (Start the extraction fields request example) and generative (Generative extractor example) models.
  Important:

  This feature is currently part of an audit process and is not to be considered part of the FedRAMP Authorization until the review is finalized. See here the full list of features currently under review.

• Validate information that was previously digitized, classified, and, or, extracted.

Depending on your use case, you can choose between using asynchronous or synchronous APIs.

Use asynchronous APIs when:

• You need to process large documents, with more than five pages.
• You need to handle multiple operations simultaneously. Asynchronous APIs allow concurrent processing and avoid idle time, leading to a higher system throughput. This means that you can send a document and move on to another task instead of waiting for the response.
• You have a large dataset that needs processing, taking significant time.

Use synchronous APIs when:

• You need to process smaller documents with maximum five pages.
• You need real-time interaction, on a request-and-reply basis, and multitasking is not needed. A synchronous API can block other operations while waiting for a response.
• You have a smaller dataset that needs processing.

The following statuses apply for asynchronous APIs:

• NotStarted: job was created and it's waiting to be processed.
• Running: job was created, was picked up, and is currently being worked on
• Failed: job finished but failed.
• Succeeded: job finished and succeeded.

Classification & Extraction APIs are available for both synchronous and asynchronous consumption. The synchronous consumption supports multi-page documents, up to 5 pages, while the asynchronous consumption posts the request via a start method and retrieves the result via polling.

Use Document Understanding Cloud APIs to access the capabilities the same way as you would via RPA. For consuming the APIs, you can use any programming/scripting language (since the calls are made using HTTP), including RPA.

You can access the APIs via Swagger: In the toolbar of the Document Understanding^TM service, look for the Rest API dropdown, and click Framework.

To try out the capabilities, use Swagger as your sandbox.

You can choose to work with a predefined or a custom build model. The custom built models are the ones created by you while using Document Understanding. A predefined model is already available to be consumed, and it includes predefined out-of-the-box models.

Important: The data received from calling the Digitization endpoint is retained for seven days. In this timeframe, the result is available via the received document ID. Afterwards, you would need to submit a new digitization request.

Important: The data received from calling the asynchronous Classification and Extraction endpoints is retained for one day (24 hours).

Depending on the operation, Document Understanding Cloud API calls use the following classes:

• Document Class for digitized documents.
• Extraction Result for extraction results.
• Classification Result for classification results.