Docling Parse is a Python package designed to extract text, paths, and bitmap images with coordinates from programmatic PDFs. It can analyze PDFs at the character, word, and line level and can also render these elements into images. The package is easy to install using pip and can be used both programmatically and via command line.
Table of contents
Using “Docling Parse”!Introduction — what is Docling Parse?UsageConclusionUseful linksSort: