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
I think it would be great to support full vision based extraction. For example, running a VLM directly on pdf images is becoming more token-efficient and accurate with recent models and would love to compare that to text based extraction.
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.
-
Hey,
I think it would be great to support full vision based extraction. For example, running a VLM directly on pdf images is becoming more token-efficient and accurate with recent models and would love to compare that to text based extraction.
Beta Was this translation helpful? Give feedback.
All reactions