Support for table parsing using GMFT and Azure Document Intelligence#120

Merged

snexus merged 22 commits intomainfrom

Oct 8, 2024

Commits on Aug 3, 2024

Initial approach with gmft
DL
committed
Refactor gmft parser
DL
committed

Commits on Aug 5, 2024

Commits on Aug 7, 2024

Add bbox to the gmft parser
DL
committed

Commits on Aug 9, 2024

Don't embed text which intersects with tables
DL
committed

Commits on Aug 10, 2024

Improve table parsing performance
DL
committed

Commits on Aug 14, 2024

Initinal implementation of image parser
DL
committed

Commits on Aug 15, 2024

Integrate image parser with the main parser
DL
committed

Commits on Aug 19, 2024

Add support for Gemini Gemini PRO image parser
DL
committed

Commits on Aug 20, 2024

Add test template for table and graph parsing
DL
committed

Commits on Aug 25, 2024

Update env template
DL
committed

Commits on Aug 30, 2024

Merge fixes from conversation history
DL
committed

Commits on Sep 7, 2024

Initial implementation of azure doc intelligence parser
DL
committed

Commits on Sep 8, 2024

Commits on Sep 11, 2024

Add parallelization to azuredocint_parser
DL
committed

Commits on Oct 4, 2024

Introduce filter to limit search to a single file. Streamline the interface
DL
committed

Commits on Oct 6, 2024

Add better caption support for Azure Doc Intelligence
DL
committed

Commits on Oct 8, 2024