Starstruk Logo MarkStarstruk

megaparse-v0.0.22

The-Vibe-Company/megaparsemegaparse-v0.0.22Jul 30, 2024by StanGirard

AI Summary

This release introduces core infrastructure such as base loader classes and a main MegaParse class, while significantly enhancing document parsing capabilities. It adds support for Unstructured Parser, improves table and image handling, and includes metadata extraction features like Table of Contents (TOC) and hyperlinks for Docx files.

Key Highlights

  • Introduction of base loader classes and the main MegaParse class
  • Support for Unstructured Parser
  • Improved Table and Image Parsing
  • Enhanced Docx support with Table of Contents (TOC) and Hyperlinks
  • Updated instructions for installing dependencies like poppler and tesseract

New Features

  • Instructions for installing poppler and tesseract
  • MegaParse class added to __init__.py
  • Support for Unstructured Parser
  • Improved Table and Image Parsing
  • Table of Contents (TOC) and Hyperlinks for Docx
  • Base loader
  • Base loader class
  • Updated benchmark results in README.md

Full Release Notes

## [0.0.22](https://github.com/QuivrHQ/MegaParse/compare/megaparse-v0.0.21...megaparse-v0.0.22) (2024-07-24)


### Features

* Add instructions for installing poppler and tesseract ([#10](https://github.com/QuivrHQ/MegaParse/issues/10)) ([3399552](https://github.com/QuivrHQ/MegaParse/commit/3399552bc8be705f6d34306743388a96d099eebc))
* Add MegaParse class to __init__.py ([84c0d64](https://github.com/QuivrHQ/MegaParse/commit/84c0d648ef1ddf048ec911210d89be155443dc72))
* Add support for Unstructured Parser, improve Table and Image Parsing, and add TOC and Hyperlinks for Docx ([#9](https://github.com/QuivrHQ/MegaParse/issues/9)) ([4934776](https://github.com/QuivrHQ/MegaParse/commit/493477672cef9fe22b0ab56ced1d5572104e1914))
* base loader ([#65](https://github.com/QuivrHQ/MegaParse/issues/65)) ([eb8149f](https://github.com/QuivrHQ/MegaParse/commit/eb8149f05ec2793f59fd87109a1aba8095f6f1d0))
* base loader class ([#64](https://github.com/QuivrHQ/MegaParse/issues/64)) ([801a026](https://github.com/QuivrHQ/MegaParse/commit/801a026e4b3411f8ac85171a6928e3d17c027648))
* Update benchmark results in README.md ([#15](https://github.com/QuivrHQ/MegaParse/issues/15)) ([1dfcb4c](https://github.com/QuivrHQ/MegaParse/commit/1dfcb4ce19467f7fb8137e10e5f5fbf35e563df0))


### Bug Fixes

* add __init__.py ([a5b8de9](https://github.com/QuivrHQ/MegaParse/commit/a5b8de9e1e01ef681ac2ef59a6e111ae7bd6cf70))
* change name ([6b36437](https://github.com/QuivrHQ/MegaParse/commit/6b36437787f048d36d69c3b06c2d59f7dc7a741f))
* PR Comments ([a0ab0ba](https://github.com/QuivrHQ/MegaParse/commit/a0ab0baa5dd9aae644baef55348f1af28a6776a7))
* remove nest asycio ([22195a2](https://github.com/QuivrHQ/MegaParse/commit/22195a27e9dc3583bf1fbde2a95e9fbecc8d96a4))
* use aload_data ([e5c73fe](https://github.com/QuivrHQ/MegaParse/commit/e5c73fefcbf09bb12810adc6d4412f7742c42089))