v1.0.0

What's Changed

• feat: implement figure captioning and chunking by @hugohonda in #107
• fix: field extraction + results save dir bug by @cmaloney111 in #92
• fix: page reset in markdown comments by @hugohonda in #114
• docs: added note directing users to the new Python library by @lai-bianca in #121
• Move deprecation warning to the top by @pappacena in #133

Full Changelog: v0.3.3...v1.0.0

v0.3.3

What's Changed

• feat: add rotation detection parameter by @pappacena in #110

Full Changelog: v0.3.2...v0.3.3

v0.3.2

What's Changed

• chore: reduce number of retries for failed requests by @pappacena in #96
• Fix color space issue when saving PDF-derived images and add comprehensive color tests by @Copilot in #98
• Removed references to legacy parse functions in README by @lai-bianca in #102
• feat: add metadata to parsed document by @hugohonda in #106

Full Changelog: v0.3.1...v0.3.2

v0.3.1

Highlights

In this version, we are releasing an early preview of confidence score for field extraction. Keep in mind that this feature is in preview mode, and its behavior might change in the future.

What's Changed

• chore: remove "experimental" from confidence score parameter name by @pappacena in #78
• Update Google Drive Connector tests based on Sandip's code by @cmaloney111 in #80
• Approve integration tests when outside collaborators submit PRs from forks by @cmaloney111 in #81

Full Changelog: v0.3.0...v0.3.1

v0.3.0

• Fix bug with encoding of files when running on Windows
• Fix bounding boxes crop issues out of image limits
• Add ParseConfig option, so users can set API key and other configurations when calling parse(... config=ParseConfig()) function
• Other minor bugfixes