Unstructured, June 2026 new features

3 releases · 1 product

May 2026 Jul 2026

unstructured

unstructured 0.23.1

- feat: extract filled AcroForm field text in PDF partitioning

UpdateJun 11

Source ↗

unstructured

unstructured 0.23.0

- fix: stop decimating embedded text on dense PDF pages - fix: keep extracted text aligned with rotated PDF page images in hi_res - feat: add enrichment origins metadata field

UpdateJun 10

Source ↗

unstructured

unstructured 0.22.32

- fix(hi_res): recover text inside PDF figure overlays

UpdateJun 8

Source ↗