[martincollignon]

Have you tried https://github.com/VikParuchuri/marker ?

[mkaszkowiak]

For my use case, overall Marker seems to work pretty well - but it has issues with tables. Merged cells, misplaced headers, and so forth. I'm currently extracting Polish PDFs that are //not// scanned

When compared to Azure Document Intelligence, Marker is really cheap when self-hosted (assuming you fall under the license requirements), but it does not produce high quality data. YMMV.

[vikp]

Working on improving tables soon (I'm the author of marker)

[mkaszkowiak]

Glad to hear that :) Thanks for developing Marker!

[chandrai]

2nd that. Marker work pretty well as async internal service for us! Thanks!

[cpursley]

Yeah, the header stuff (and empty cells) for tables needs some work.

[cpursley]

Maker worked pretty well for me in my limited testing. They also have a hosted solution:

https://www.datalab.to