Google Document AI integration

OCR/AI: document parsing, invoice extraction, receipt scanning, form parsing, custom processors

Help CentreConnectors

Overview

Google Document AI is Google Cloud's document processing – invoice extraction, receipt scanning, form parsing, custom processors. The Automize Document AI connector covers these.

  • Regions: Multi-region (us, eu).
  • Plans: Pay-per-page.

Setting up the connection

Auth type: OAuth 2.0 (Authorization Code).

  1. Google Cloud Console → Enable Document AI API.
  2. Service account with Document AI API User role.
  3. In Automize → Settings → Connectors → Google Doc AI. Paste credentials + project ID + processor ID + region.

Find your credentials at https://console.cloud.google.com/apis/credentials.


Rate limits

Per-processor quotas.


Data model

Document AI:

    Project ─── Processors (invoice, receipt, form, custom)
            └─ Processed Documents

Available operations

5 operations available. Click any row to jump to its detail.

OperationCategoryWhat it does
Batch ProcessGeneralProcess multiple documents asynchronously
Get OperationGeneralCheck status of a batch/async operation
List Processor TypesGeneralList available processor types (OCR, invoice, receipt, etc.)
List ProcessorsGeneralList available processors
Process DocumentGeneralProcess a document with a processor (OCR, invoice, receipt, etc.)

Operations

Batch Process

Process multiple documents asynchronously

ParameterRequiredTypeDescription
Project Id project_idYestext
Location locationYestext
Processor Id processor_idYestext
Inputdocuments inputDocumentsYestext
Documentoutputconfig documentOutputConfigYestext

Tips

  • Async – GCS input + output. For high volume.

Get Operation

Check status of a batch/async operation

ParameterRequiredTypeDescription
Project Id project_idYestext
Location locationYestext
Operation Id operation_idYestext

List Processor Types

List available processor types (OCR, invoice, receipt, etc.)

ParameterRequiredTypeDescription
Project Id project_idYestext
Location locationYestext

List Processors

List available processors

ParameterRequiredTypeDescription
Project Id project_idYestext
Location locationYestext

Tips

  • Returns project's deployed processors.

Process Document

Process a document with a processor (OCR, invoice, receipt, etc.)

ParameterRequiredTypeDescription
Project Id project_idYestext
Location locationYestext
Processor Id processor_idYestext
Rawdocument rawDocumentYestextarea
Inlinedocument inlineDocumentYestext

Tips

  • processor_id + document (base64 or GCS URI).
  • Returns extracted entities + text + form fields + tables.

FAQ

vs AWS Textract / Azure Doc Intelligence?
Google: strong on multilingual + handwriting. Azure: strong on receipts/invoices. Textract: strong on forms. Test on your docs.

Related connectors

See it working on your own data

Everything documented here ships with the platform – try the document tools free, or go live in 7 days.