Struture not correctly detected with this pdf #102

Open
opened 2026-02-16 00:16:52 -05:00 by yindo · 0 comments
Owner

Originally created by @demysc on GitHub (May 4, 2024).

Hi,

Struture not correctly detected with this pdf https://www.inail.it/cs/internet/docs/alg-circolare-n-10-16-aprile-2024.pdf

Most sections are not correctly detected in pdf, the titles appear as inline text, next to the paragraph see screenshots
image
image

in this case the section is detected however the list items are not consistently deteted, sometimes they are interpreted as new section
image

Originally created by @demysc on GitHub (May 4, 2024). Hi, Struture not correctly detected with this pdf https://www.inail.it/cs/internet/docs/alg-circolare-n-10-16-aprile-2024.pdf Most sections are not correctly detected in pdf, the titles appear as inline text, next to the paragraph see screenshots ![image](https://github.com/run-llama/llama_parse/assets/47008987/c5c08b19-bbd8-42ba-a3f2-963d6d4f0714) ![image](https://github.com/run-llama/llama_parse/assets/47008987/76e38e95-65e5-452e-8e76-a6130c6ea7ff) in this case the section is detected however the list items are not consistently deteted, sometimes they are interpreted as new section ![image](https://github.com/run-llama/llama_parse/assets/47008987/692140a8-8d54-4cca-8a6a-7b4b8a18543d)
yindo added the pdf_debug label 2026-02-16 00:16:52 -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#102