This project is a PDF data extraction tool and document preprocessor designed to convert PDF files into structured formats such as Markdown, JSON, and HTML. It functions as an OCR document parser for scanned files, an accessibility automator for generating PDF/UA compliant metadata, and a loader for AI orchestration frameworks like LangChain.
The software distinguishes itself through specialized handling of complex document elements, including the conversion of mathematical formulas into LaTeX and the generation of natural-language descriptions for charts and images. It utilizes recursive segmentation to determine correct reading orders in multi-column layouts and employs border-cluster detection to preserve the integrity of merged-cell tables.
Broad capabilities include optical character recognition, semantic document chunking for retrieval optimization, and noise reduction to strip headers and footers. It also features security utilities for decrypting password-protected files, sanitizing sensitive private data, and filtering invisible content to prevent prompt injection.
The project supports high-throughput batch processing and provides structure visualization tools to overlay detected semantic elements onto original documents for verification.
