# How to extract text from a PDF/DOCX uploaded via the File Node?

**URL:** <https://community.yellow.ai/t/how-to-extract-text-from-a-pdf-docx-uploaded-via-the-file-node/5654>\
**Category:** Studio\
**Created:** [December 4, 2025, 8:20pm UTC](https://community.yellow.ai/t/how-to-extract-text-from-a-pdf-docx-uploaded-via-the-file-node/5654 "2025-12-04T20:20:33Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Anjali\_Gurbani](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.yellow.ai/anjali_gurbani/32/3672_2.png) [@Anjali\_Gurbani](https://community.yellow.ai/u/Anjali_Gurbani)\
**Post date:** [December 4, 2025, 8:20pm UTC](https://community.yellow.ai/t/how-to-extract-text-from-a-pdf-docx-uploaded-via-the-file-node/5654/1 "2025-12-04T20:20:33Z")

</div>

Hi team,

What is the correct way in Yellow.ai to read and extract text from a PDF or DOCX file that a user uploads through the File Node? Are there any supported methods, sample scripts, or recommended approaches for this?