Releases: opendatalab/PDF-Extract-Kit
Releases · opendatalab/PDF-Extract-Kit
PDF-Extract-Kit-1.0.0-released
What's Changed
- @wangbinDL refactored the code for pdf-extract-kit-0.1.1 to support modular operations, allowing users to more conveniently and flexibly select and combine the models they need.
- @wangbinDL added demos for formula recognition, formula detection, and layout detection.
- @wangbinDL added documentation for PDF-Extract-Kit-1.0.
- @JulioZhao97 introduced a new layout detection model (LayoutLMv3).
- @wufan-tb added OCR support.
New Contributors
- @JulioZhao97 made their first contribution with the addition of the LayoutLMv3 model.
Contributors
wufan-tb, JulioZhao97, and wangbinDL
Assets 2
PDF-Extract-Kit-0.1.1-released
What's Changed
- Update license from Apache 2.0 to AGPL-3.0 by @wangbinDL
- Add MinerU technical report bibtex by @wangbinDL
Version 0.1.1 is the stable release preceding the major architectural changes in PDF-Extract-Kit 1.0.0. While the upcoming 1.0.0 version introduces a more streamlined and intuitive user experience, it involves substantial modifications. Users who prefer the stability and familiarity of the previous version are encouraged to continue using 0.1.1.
Contributors
wangbinDL
Assets 2
PDF-Extract-Kit-0.1.0-released
What's Changed
- add eval table by @ouyanglinke in #1
- modifying readme by @ouyanglinke in #3
- modify readme by @ouyanglinke in #4
- adding license in README. adding model checkpoint version info. by @ouyanglinke in #6
- adding validation by @ouyanglinke in #17
- update readme by @wangbinDL in #34
- update code explaination, remove some personal information by @wufan-tb in #35
- adding category mapping intro into validation readme by @ouyanglinke in #40
- resolve #36: add google colab link by @zhchbin in #44
- Add the table recognition by StructEqTable model by @sky-fly97 in #58
- Refine Table Recognition Tutorial by @wangbinDL in #70
- fix & refactor & docs：update ocr logic and installation guides by @myhloli in #88
- fix(ocr): Solve the issue of missing some lines and spans due to adhesion during OCR by @myhloli in #92
- feat: add batch-size parameter and garbage collection by @jorgeolothar in #89
- dev to main by @myhloli in #124
New Contributors
- @ouyanglinke made their first contribution in #1
- @wufan-tb made their first contribution in #35
- @zhchbin made their first contribution in #44
- @jorgeolothar made their first contribution in #89
Full Changelog: https://github.com/opendatalab/PDF-Extract-Kit/commits/PDF-Extract-Kit-0.1.0-released
Contributors
zhchbin, jorgeolothar, and 5 other contributors