HackerTrans
TopNewTrendsCommentsPastAskShowJobs

chiccomagnus

no profile record

Submissions

[untitled]

1 points·by chiccomagnus·11 месяцев назад·0 comments

comments

chiccomagnus
·в прошлом году·discuss
IMHO, your article is missing an important point: 90% of implementations today flatten documents to plain text before chunking them. Why not consider the visual appearance that the human gave to the document? Using layout information combined with semantics, you can increase rag performances by +160% (tested via benchmarks), so why do most of us only use text?

Note: multimodal ≠ layout
chiccomagnus
·в прошлом году·discuss
How does credits works?
chiccomagnus
·в прошлом году·discuss
If you don't want to reinvent the wheel, we have built exactly that, goggle "Preprocess"
chiccomagnus
·в прошлом году·discuss
Have you compared this solution with tools like Preprocess, Reducto, etc.. ? I'm curious about the performance gain you can achieve with your approach
chiccomagnus
·2 года назад·discuss
It seems it tries to always extract tables even if the content is just text. Is not working and at a similar price you can get high performing solutions like preprocess.co and similars.
chiccomagnus
·2 года назад·discuss
I'm curious to know how you handle the chunking of complex documents
chiccomagnus
·2 года назад·discuss
If for "documents" you mean PDF, Word, Powerpoints, Excel you should try preprocess.co

If that’s not what you meant, can you please clarify?
chiccomagnus
·2 года назад·discuss
Do you use naive chunking? Have you tried something else?
chiccomagnus
·2 года назад·discuss
By chance, have you tried preprocess.co for text extraction + chucking?