This module integrates Google Cloud's Document AI with Drupal, allowing you to automatically extract text and structured data from various document formats like PDFs and images using OCR. It seamlessly works with Drupal's AI module, making it ideal for content management, form processing, and creating searchable archives.
AI Document OCR Provider
Google Document AI provider for Drupal's AI module
The AI Document OCR Provider module integrates Google Cloud's powerful Document AI service with Drupal's AI module, enabling automated text extraction from PDF files, images, and other document formats through optical character recognition (OCR).
Key Features
- Seamless AI Module Integration: Works as a provider plugin for Drupal's AI module ecosystem
- Google Document AI Powered: Leverages Google Cloud's advanced OCR and document understanding technology
- Multiple Format Support: Process PDFs, JPEG, PNG, GIF, TIFF, BMP, and WebP files
- Structured Data Extraction: Extract not just text, but also document structure, paragraphs, and layout information
- Dynamic Processor Management: Automatically loads available processors from your Google Cloud project
- Secure Credential Storage: Integrates with Drupal's Key module for secure service account management
- User-Friendly Configuration: Simple setup with AJAX-powered processor selection
Perfect For
- Content Management: Extract text from uploaded documents for indexing and search
- Form Processing: OCR invoices, forms, and structured documents
- Digital Archive Processing: Convert scanned documents to searchable text
- Accessibility Enhancement: Generate text alternatives for image-based content
- Automated Workflows: Build AI-powered content processing pipelines
Requirements
- Drupal 10.0+ or 11.0+
- AI module
- Google Cloud account with Document AI API access
- Key module (recommended for secure credential storage)
- PHP 8.1+
Quick Setup
- Enable the module
- Create Google Cloud service account with Document AI access
- Store credentials securely using Key module
- Configure the provider at
Configuration > AI > AI Providers > Document OCR - Select your region and processor - available processors load automatically!
Developer Friendly
Built with modern Drupal standards - clean code, proper dependency injection, comprehensive documentation, and follows AI module conventions for easy integration with existing projects.
Transform your document processing workflows with the power of Google's AI technology, seamlessly integrated into your Drupal site.
Depends on
Dependencies of the latest stable release
No dependencies recorded for this project.
Required by
Tracked projects that depend on this one
No tracked projects depend on this one yet.
Activity
Release Timeline
Releases
| Version | Type | Core | Notes | Release date | |
|---|---|---|---|---|---|
| 1.0.0-beta3 | Pre-release | 10–11 | Drupal 12 and use AiGuardrailHelper. | Jun 9, 2026 | |
| 1.0.0-beta2 | Pre-release | 10–11 | ai_automators is a submodule of the ai module, it should be referenced as ai:ai_automators. | Sep 1, 2025 | |
| 1.0.0-beta1 | Pre-release | 10–11 | AI Document OCR Provider | Sep 1, 2025 | |
| 1.0.x-dev | Dev | 10–11 | Aug 31, 2025 |