# Training with Large PDF FIles

**URL:** <https://community.openai.com/t/training-with-large-pdf-files/46994>\
**Category:** API\
**Created:** [February 3, 2023, 2:20pm UTC](https://community.openai.com/t/training-with-large-pdf-files/46994 "2023-02-03T14:20:24Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![SomebodySysop](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/somebodysysop/32/17613_2.png) [@SomebodySysop](https://community.openai.com/u/SomebodySysop)\
**Post date:** [April 29, 2023, 5:39pm UTC](https://community.openai.com/t/training-with-large-pdf-files/46994/7 "2023-04-29T17:39:03Z")

</div>

Here is an excellent tutorial which covers all the questions posed: [GPT-4 Tutorial: How to Chat With Multiple PDF Files (~1000 pages of Tesla's 10-K Annual Reports) - YouTube](https://youtu.be/Ix9WIZpArm0)

In addition, I have discovered that when you break a document down into multiple chunks, you should have a strategy for maintaining a contextual relationship between the source document and it’s chunks:

 ![Chunking and Summarization](https://us1.discourse-cdn.com/openai1/original/3X/0/4/049e826b29944b2d57ef6249a246e2ef6d2652eb.jpeg)

---

_[View the full topic](https://community.openai.com/t/training-with-large-pdf-files/46994)._