Blog overview

Denis Moldovan

Handwriting OCR vs. VLMs: What’s the difference?

Handwriting recognition is fundamentally harder than printed-text OCR. Learn why current approaches fail, how OCR and VLMs compare, and why word-level bounding boxes matter for real-world extraction.

Austin Nguyen

Introducing agentic-usability: Measuring how well AI agents can use your SDK

Hulya Masharipov

Python PDF text extraction with PyMuPDF: Scanned PDFs, tables, and OCR

Austin Nguyen

PDF.js EventBus guide: Events, hooks, and custom pub/sub patterns

Mahmoud Elsayad

The Web SDK is now headless — For your design system and for AI agents

Recent posts

Python HTML to PDF (2026): WeasyPrint setup, Django, and a high-volume API

SDK

Hulya Masharipov

Python HTML to PDF (2026): WeasyPrint setup, Django, and a high-volume API

React to PDF: Generate PDFs from React components

SDK

Philipp Spiess

React to PDF: Generate PDFs from React components

PDF OCR on the Linux command line: OCRmyPDF, Tesseract, and Nutrient

SDK

Hulya Masharipov

PDF OCR on the Linux command line: OCRmyPDF, Tesseract, and Nutrient

Reading list

Hulya Masharipov

How to use PDF.js to highlight text programmatically

How to use PDF.js to highlight text programmatically

Hulya Masharipov

Streamlining document collaboration with real-time PDF editing in your app

Streamlining document collaboration with real-time PDF editing in your app

Sync annotations using external files

Sync annotations using external files

Using Instant layers for onsite visits

Using Instant layers for onsite visits

Nutrient for aviation

Nutrient for aviation

How to combine OCR with redaction in Java

How to combine OCR with redaction in Java

blog archive

View all blog posts