PAD

• Purpose: Guide to quickly start using the PAD (Automatic Document Processing) API.
• Description: Automates the extraction of information into structured data, applicable to forms, documents, invoices, receipts, personal identity cards, passports, driver’s licenses, and other custom documents of interest, using internal AI/ML models.

Prerequisites

• Is necessary to already have an API Credentials from your organization
• Your account should have at least the roles: pad and usage.

PAD flow

Tip

For more detailed information about schemas, please refer to the API schemas in the wiki section.

Basic data extraction flow from a document:

1. The client sends a POST request to the PAD API at the /analyze endpoint.
2. The PAD API creates a log USAGE record of the request.
3. The PAD API applies validations to the incoming data.
4. The PAD API performs JSON parsing of the validated data.
5. The PAD API sends a success response back to the client.

Usage

Files formats allowed	Files Maximum size
PDF	500 MB
Images format: PNG, BMP, JPEG/JPG, HEIF, TIFF	500 MB

Limitations

• PDF documents with passwords are not supported.
• URL path with security are not allowed.
• The model personal_docs can validate any kind of passports around the world, personal ID and driver licenses from United States, India, Europe, Australia and Canada for other countries is possible can’t get all the expected fields for this scenario please create a support ticket to create a custom model, remember to give to us documents examples.

Resources

PAD API Schemas Get more in details of the API schemas

Authentication Quickstart guide about authentication service

Postman Collection Click here to download the collection!

Need help? Feel free to contact us to get additional assistance or if you want to share your feedback