You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Documents often contain nested lists and the nesting bears some meaning - see the TOC for the Docling Usage page for example:
Table of contents
Conversion
-- Convert a single document
-- CLI
-- Advanced options
--- Adjust pipeline features
---- Control PDF table extraction options
---- Provide specific artifacts path
--- Impose limits on the document size
--- Convert from binary PDF streams
--- Limit resource usage
Chunking
At the moment, all of these items would be recognised as a single group with the same level 2 depth.
For a well formatted document, would be great to recognise the actual levels of nesting, which is easy for DOCX (as it is encoded in styles) and a bit less easy for PDF, where visual alignment is sometimes the only indicator.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Documents often contain nested lists and the nesting bears some meaning - see the TOC for the Docling Usage page for example:
Table of contents
-- Convert a single document
-- CLI
-- Advanced options
--- Adjust pipeline features
---- Control PDF table extraction options
---- Provide specific artifacts path
--- Impose limits on the document size
--- Convert from binary PDF streams
--- Limit resource usage
At the moment, all of these items would be recognised as a single group with the same level 2 depth.
For a well formatted document, would be great to recognise the actual levels of nesting, which is easy for DOCX (as it is encoded in styles) and a bit less easy for PDF, where visual alignment is sometimes the only indicator.
Appreciate your thoughts on this - many thanks
Beta Was this translation helpful? Give feedback.
All reactions