🔍 PDF parser for AI data extraction — Extract Markdown, JSON (with bounding boxes), and HTML from any PDF. #1 in benchmarks (0.907 overall). Deterministic local mode + AI hybrid mode for complex ...

It is super slow, I would suggest you use PyMuPDF, it is built directly on C language and provides nearly 10x the speed. I used it in production where i had to index quite close to 33,000 files ...

See the latest release notes on NuGet and Maven Central for parser engine improvements, faster template-based extraction, and better table detection. Updated sample apps show invoice data extraction, ...

Microsoft Threat Intelligence analyzed a cryptocurrency clipper campaign that combines clipboard theft, wallet replacement, ...

Cloud image editors are now much harder to justify.