GoogleCloudPlatform/document-ai-samples
Sample applications and demos for Document AI, the end-to-end document processing platform on Google Cloud
This helps organizations automate the processing of various physical and digital documents like invoices, tax forms, and scientific papers. It takes unstructured document images or PDFs as input and extracts, classifies, and organizes key information, making it accessible for analysis or integration into other systems. It's designed for operations managers, data entry teams, and compliance officers who deal with large volumes of documents.
310 stars.
Use this if you need to automatically extract specific data, classify document types, or summarize content from diverse documents such as legal agreements, receipts, or research articles.
Not ideal if your primary need is simple OCR for basic text extraction without the need for sophisticated data understanding or document classification.
Stars
310
Forks
115
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/GoogleCloudPlatform/document-ai-samples"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
paperless-ngx/paperless-ngx
A community-supported supercharged document management system: scan, index and archive all your documents
aws-solutions/document-understanding-solution
Example of integrating & using Amazon Textract, Amazon Comprehend, Amazon Comprehend Medical,...
naiveHobo/InvoiceNet
Deep neural network to extract intelligent information from invoice documents.
aphp/edspdf
EDS-PDF is a generic, pure-Python framework for text extraction from PDF documents. It provides...
ptmrio/autorename-pdf
autorename-pdf is a highly efficient tool designed to automatically rename and archive PDF...