docling Option to disable image extraction/merging

I'm playing around with the library, and having some pretty nice results with it! However, in my tests it often recognizes large pieces as an image, and then doesn't return the text and/or tables within that image (probably because it merges it into the biggest found layout item that is detected).

I think it would be a nice option to be able to disable the image extraction/merging.

Nov 05 '24 08:11 jerbob92

@cau-git Hello can you please assign this to me?

Dec 06 '24 15:12 BelaidCH

@jerbob92 @BelaidCH we have a version in the works that will enable to get the in-picture content out, it will be released by end of next week. I will post instructions how to test it if you want to help with that.

Dec 07 '24 09:12 cau-git

Sure! Would be great to test it out!

Dec 09 '24 19:12 jerbob92

Yes it would be great!

Dec 10 '24 10:12 BelaidCH

This has since been implemented and is ready to use.

May 23 '25 08:05 cau-git