Creating a processor

Before you can send documents to be processed you must first create a processor. The type of processor you create affects the response fields you get back from a document.

Create a processor

Use the following sample to create a processor and custom endpoint to send requests to.

Console

  1. In the Google Cloud Console, in the Document AI section, go to the Processors page.

    Go to the Processors page

  2. Select Create processor.

  3. Click on the processor type from the list you want to create.

  4. In the side Create processor window specify a processor name.

  5. Select your region from the list.

  6. Click Create to create your processor.

Use your processor endpoint

After you create your processor you can get the custom endpoint that is generated from the process.

Console

  1. In the Google Cloud Console, in the Document AI section, go to the Processors page.

    Go to the Processors page

  2. Select the processor you want to get information about.

On the processor details page you can see the custom endpoint. It follows the format:

  • https://LOCATION-documentai.googleapis.com/v1beta3/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID

Use this endpoint or the information it contains (PROCESSOR_ID) to send requests.

Each processor page has more information about each processor and code samples showing how to send a processing request.

Solution Processor Description Public access Limited access
General Document OCR (Optical Character Recognition) Identify and extract text in different types of documents.
Form parser Extract form elements such as text and checkboxes.
Document splitter Programmatically split documents on logical boundaries.
Lending W9 parser Extract from Form W9 including name, address, TIN, etc.
1040 parser Extract from Form 1040, including name, filing status, amounts, etc.
W2 parser Extract from Form W2, including employee, employer, wages, etc.
1099-MISC parser Extract from Form 1099-MISC, including payer, recipient, amounts, etc.
Lending document splitter & classifier Identify documents in a large file and classify known lending document types.
1003 parser Extract over 50 fields from Fannie Mae Form 1003 (URLA).
Procurement Invoice parser Extract text and values from invoices such as invoice number, supplier name, invoice amount, tax amount, invoice date, due date.
Receipt parser Extract text and values from receipts such as receipt date, supplier name, total amount, and currency.
Procurement document splitter Procurement document splitter allows you to programmatically split these combined procurement documents on logical boundaries.