What is Chunking?

RAG

Chunking — The process of splitting documents into smaller pieces (chunks) for storage in a vector database. Chunk size and strategy significantly impact RAG system quality.

FAQ

What is chunking in RAG?

Splitting documents into smaller pieces before embedding them. Chunk size affects retrieval quality — too large misses details, too small loses context.

What chunk size should I use?

Start with 512-1024 tokens with 20% overlap. Adjust based on your document type and retrieval quality.

Related Terms

Learn Chunking in depth

Free hands-on course with code examples and Google Colab notebooks.

Start Course →