run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 01:15:06 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Option to Force Image Conversion to Prevent White Fonting #500

New Issue
Closed
opened 2026-02-16 00:18:03 -05:00 by yindo · 1 comment
yindo commented 2026-02-16 00:18:03 -05:00
Owner
Copy Link
Copy Source

Originally created by @adreichert on GitHub (Jul 14, 2025).

Summary

In certain modes, LlamaParse extracts text from PDFs even if the text color matches the background color. Practically, this means that text written in white font on white backgrounds is extracted undesirably.

Maybe there is a mode that does this already. If not, I'd like to request an option to force the conversion of all PDF pages to images prior to extraction, which would prevent hidden text from being extracted.

Reproduction

Image

Other

  • I also tried playing with the various options, for instance, turning on high-res OCR in the custom subset. The text appeared with all choices.
Originally created by @adreichert on GitHub (Jul 14, 2025). # Summary In certain modes, LlamaParse extracts text from PDFs even if the text color matches the background color. Practically, this means that text written in white font on white backgrounds is extracted undesirably. Maybe there is a mode that does this already. If not, I'd like to request an option to force the conversion of all PDF pages to images prior to extraction, which would prevent hidden text from being extracted. # Reproduction * Go to https://cloud.llamaindex.ai/ * In the playground, parse [lincoln.pdf](https://github.com/user-attachments/files/21221675/lincoln.pdf), which contains text in white text, in balanced and premium * The text will be parsed. <img width="528" height="911" alt="Image" src="https://github.com/user-attachments/assets/f13d1880-0e97-45da-a8d8-3779726c2116" /> # Other * I also tried playing with the various options, for instance, turning on high-res OCR in the custom subset. The text appeared with all choices.
yindo added the enhancement label 2026-02-16 00:18:03 -05:00
yindo closed this issue 2026-02-16 00:18:03 -05:00
yindo commented 2026-02-16 00:18:03 -05:00
Author
Owner
Copy Link
Copy Source

@adreichert commented on GitHub (Jul 14, 2025):

NVM. I found it. "Parse with LVM". parse_mode="parse_page_with_lvm".

@adreichert commented on GitHub (Jul 14, 2025): NVM. I found it. "Parse with LVM". `parse_mode="parse_page_with_lvm".`
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label enhancement
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#500
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?