Layout, OCR, tables, and classification usually live in four different tools, and field extraction happens somewhere else again. This document AI interface puts them in one task.
Annotators draw bounding boxes around document elements, select text spans and words backed by hOCR positions, mark up table rows and columns with per-cell labels and merged cells, classify the document and each page, and link related regions, such as a caption to its figure. An extraction panel binds labeled regions to named fields so you can preview the structured record before saving.
Works on PDFs and single-page images. The region labels, document types, and page types are parameters you replace with your own.
Draw regions on a document, set reading order, and fix table structure while the DocLang XML updates beside you. Docling predictions load in for correction, so your annotators fix conversions instead of building them from scratch.