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
Sometimes when a PDF is parsed, things don't come out quite right, like lists not being recognised properly or OCR missing some text. We have some documents where it is important that all the content is correct and it is fine for us to fix it manually.
Currently, we fix them by exporting to Markdown and manually editing the content. The downside is that we lose all the docling information in the process.
Is there a better way to correct a Docling document while preserving its structure? We could also export it to markdown and include all the necessary docling information in custom tags, but that feels more like a workaround.
Would love to hear any tips and tricks!
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
Uh oh!
There was an error while loading. Please reload this page.
-
Sometimes when a PDF is parsed, things don't come out quite right, like lists not being recognised properly or OCR missing some text. We have some documents where it is important that all the content is correct and it is fine for us to fix it manually.
Currently, we fix them by exporting to Markdown and manually editing the content. The downside is that we lose all the docling information in the process.
Is there a better way to correct a Docling document while preserving its structure? We could also export it to markdown and include all the necessary docling information in custom tags, but that feels more like a workaround.
Would love to hear any tips and tricks!
Thanks very much!
Beta Was this translation helpful? Give feedback.
All reactions