Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Learn about text chunking techniques for Retrieval Augmented Generation (RAG) in this 17-minute technical video that demonstrates hands-on implementation using LangChain and LlamaIndex. Explore different chunking methods including fixed-size, recursive, document/code, and semantic chunking to optimize the ingestion of text into Vector Databases for RAG pipelines. Starting with a RAG refresher, dive into the importance of proper text segmentation for improving retrieval accuracy and reducing hallucinations in Large Language Models. Follow along with practical examples and understand when to use each chunking strategy for different types of content, from standard documents to programming code. Master essential concepts for building more effective RAG applications while learning from an experienced Machine Learning researcher with 15 years of software engineering background.
Syllabus
- Intro
- RAG refresher
- Ingestion in RAG
- What is Chunking?
- Why Chunking?
- Fixed-Size Chunking
- Recursive Chunking
- Document / Code Chunking
- Semantic Chunking
- Conclusion
Taught by
AI Bites