Please note, this video is best viewed with 1080p quality selected. You can use the player bar to navigate to chapters within the video.

Chapters

0:00 Intro

2:03 What is chunking?

3:42 Why do we chunk?

6:45 Chunking strategies

9:15 Recursive splitting

13:45 Document specific splitting

16:35 Semantic splitting

21:45 Summary

Resources

You can view or fork the code shown in this video from the Curriculum GitHub repository. 

To learn more and leave feedback:

• Atlas Vector Search Quick Start

• How to Choose the Right Chunking Strategy for Your LLM Application

• GitHub: Using Atlas Vector Search for RAG code

• What is retrieval-augmented generation (RAG)?

• Docs: Retrieval-Augmented Generation (RAG) with Atlas Vector Search

• Docs: Build a Local RAG Implementation with Atlas Vector Search

• RAG with Atlas Vector Search, LangChain, and OpenAI

• See what your peers are saying and contribute your own findings and considerations through our Community Forums.