Pull Requests Unstructured-IO/unstructured

fix: derive crop box from coordinate extent in `save_elements`

#4371 opened 2026-06-09 23:54 by badGarnet

feat: Implement PDF heading hierarchy inference for category_depth

#4369 opened 2026-06-09 20:56 by ylcnymn

fix: drop processing instructions in HTML parser

#4361 opened 2026-06-05 11:50 by assinscreedFC

feat: derive category_depth from heading level in the v2 (ontology) HTML parser (ML-1328)

#4360 opened 2026-06-04 20:30 by qued

Optimize XLSX subtable detection memory usage

#4357 opened 2026-06-01 15:17 by CyMule

feat: expose layout confidence metadata

#4356 opened 2026-05-26 18:32 by RitwijParmar

Fix br tail text handling in HTML tables

#4351 opened 2026-05-12 18:31 by dsolankii

fix: Support text partitioning from ZipExtFile objects

#4350 opened 2026-05-11 21:06 by dsolankii

fix: avoid false-positive Title classification for long no-space text

#4348 opened 2026-04-28 20:44 by claytonlin1110

fix: prefer embedded PDF text over OCR for hi_res table tokens

#4347 opened 2026-04-28 20:26 by claytonlin1110

fix(html): enable huge_tree on HTMLParser so deeply nested HTML partitions

#4340 opened 2026-04-16 22:57 by CrepuscularIRIS

feat: add clean_newline utility for hyphenated line breaks (#2513)

#4339 opened 2026-04-16 12:38 by DevAbdullah90

fix: convert Tesseract language codes for PaddleOCR in OCRAgent.get_agent()

#4329 opened 2026-04-09 10:45 by Mustafa-Shoukat1

feat: add AG2 multi-agent document processing example

#4326 opened 2026-04-07 18:49 by faridun-ag2

feat: infer hierarchical heading levels (H1-H6) for PDFs (#4204)

#4325 opened 2026-04-07 17:52 by statxc

feat: add support python3.14

#4312 opened 2026-04-01 10:05 by FomalhautWeisszwerg

refactor: don't import unstructured-inference via partition.pdf

#4284 opened 2026-03-16 13:48 by artdent

fix: improve multi-column layout sorting for academic papers (#4104)

#4283 opened 2026-03-16 00:07 by Gopesh111

refactor: replace deprecated decorators in partition_image with apply_metadata

#4271 opened 2026-03-02 12:55 by HemantSudarshan

fix: add 'el' and 'gr' as Greek language code aliases for Tesseract OCR

#4270 opened 2026-02-27 18:45 by s0wa48

fix: handle list output from group_bullet_paragraph in element apply()

#4253 opened 2026-02-21 20:04 by s0wa48

Simple typo fix

#4251 opened 2026-02-20 08:06 by rchen19

Feat: embedding model voyage 4 family

#4234 opened 2026-02-11 18:12 by fzowl

feat: add XLSM (Excel Macro-Enabled Workbook) parsing support

#4227 opened 2026-02-08 16:51 by longway-code

Add AgentMarket - B2A Marketplace

#4225 opened 2026-02-03 17:14 by stromfee

docs: fix redundant whitespace in pyenv command in README

#4224 opened 2026-02-03 13:38 by longway-code

Fix FutureWarning: Add test to verify bytes are wrapped in BytesIO for read_excel

#4213 opened 2026-01-27 12:59 by Achieve3318

⚡️ Speed up function `merge_out_layout_with_ocr_layout` by 30%

#4212 opened 2026-01-27 02:31 by aseembits93

feat: chunking by character and title now isolates tables

#4197 opened 2026-01-15 19:26 by badGarnet

fix: NameError: LayoutElements not defined in paddle_ocr.py

#4195 opened 2026-01-15 16:18 by mohansinghi