nlmatics/llmsherpa

Can I get coordinates for each chunk?

YoshitakaOyama opened this issue · 7 comments

YoshitakaOyama commented

First of all, thank you for implementing such a wonderful library.

I tried using it and got some good results.

I thought it would be better if there was coordinate information for each chunk, but do you have any plans to implement it in the future?

I think it would be technically difficult to obtain data that includes coordinate information...

simon-cerda commented

I would love to have something like this, is there any update or work in progress related to this? Thanks.

ansukla commented

This is in the works and will be available soon.

  • 👍3
ansukla commented

Hello coordinates of each chunk is now available via bbox in each chunk.

  • 🎉2
YoshitakaOyama commented

Wow, thank you!!!

dalmia commented

Hey @ansukla!
Thanks for the awesome package. I tried replicating the example mentioned in the README, but the bbox comes up empty for every block (sections, chunks, tables). Is there any particular parameter that we need to set to enable the bboxes to come up? Am I missing something?

ansukla commented
dalmia commented

Got it, thank you so much @ansukla