# LlamaParse strange document segmentation

**URL:** <https://community.deeplearning.ai/t/llamaparse-strange-document-segmentation/782167>\
**Category:** Event-Driven Agentic Document Workflows\
**Created:** [March 8, 2025, 1:50pm UTC](https://community.deeplearning.ai/t/llamaparse-strange-document-segmentation/782167 "2025-03-08T13:50:01Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![msmelo](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/msmelo/32/88956_2.png) [@msmelo](https://community.deeplearning.ai/u/msmelo)\
**Post date:** [March 8, 2025, 1:50pm UTC](https://community.deeplearning.ai/t/llamaparse-strange-document-segmentation/782167/1 "2025-03-08T13:50:01Z")

</div>

This is more of a LlamaParse quirk than a problem with the central learning points in the Event-Driven Agentic Document course, but if you look closely into the slicing LlamaParse does of the resumé you see this:

 ![image](https://global.discourse-cdn.com/dlai/original/3X/3/7/37da641de669ac548b19abb8a485bc621ea02cb8.png)  
Notice the two lines in the red boxes: LlamaParse moved them to be bullets of the **next** section (when they were really the last bullets of the **previous** one), presumably just because of a page break.

This probably means that the vector indexes produced will not be ideal, right?

Is this a bug in LlamaParse? Or a limitation of the layout of the specific resumé PDF being used? Any way to work around it?