# RAG - Parsing and Chunking the text

**URL:** <https://community.deeplearning.ai/t/rag-parsing-and-chunking-the-text/629376>\
**Category:** AI Discussions\
**Tags:** langchain, ai-discussions\
**Created:** [May 17, 2024, 11:21am UTC](https://community.deeplearning.ai/t/rag-parsing-and-chunking-the-text/629376 "2024-05-17T11:21:28Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![satyanarayana1](https://avatars.discourse-cdn.com/v4/letter/s/439d5e/32.png) [@satyanarayana1](https://community.deeplearning.ai/u/satyanarayana1)\
**Post date:** [May 17, 2024, 11:21am UTC](https://community.deeplearning.ai/t/rag-parsing-and-chunking-the-text/629376/1 "2024-05-17T11:21:28Z")

</div>

Hi,

I am looking at the strategy to be used to read the pdf and word documents and store it vector database and retrieve the same through LLM.

Any view on the procedure to be used that is libraries the pdf and word document has tables and images.