Llama parse OCR question #359

Open
opened 2026-02-16 00:17:37 -05:00 by yindo · 0 comments
Owner

Originally created by @AyushParikh on GitHub (Nov 28, 2024).

Is there a way to know which images got parsed by the OCR and which didn't?
im trying to reconstruct the pdf on frontend by putting pieces from the items and images together. But if OCR is enabled i get duplicated data for some pages since i get the image version and also the OCR parsed version,

Originally created by @AyushParikh on GitHub (Nov 28, 2024). Is there a way to know which images got parsed by the OCR and which didn't? im trying to reconstruct the pdf on frontend by putting pieces from the `items` and `images` together. But if OCR is enabled i get duplicated data for some pages since i get the image version and also the OCR parsed version,
yindo added the enhancement label 2026-02-16 00:17:37 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#359