AI engineering glossary · RAG vector search
What is recursive character splitting?
Recursive character splitting: A chunking method that tries to split on the largest natural separator first, such as blank lines, then single newlines, then sentences, then spaces, moving to smaller separators only while a piece is still too long. It keeps paragraphs and sentences together whenever possible.
Recursive character splitting: an example
Separators are tried in order: paragraph break, newline, full stop, space; a 900-token section is split at paragraph breaks into two 450-token chunks.
Related terms
More RAG vector search terms
- Reranker
- Reranking
- Rescoring
- Retrieval evaluation
- Retrieval-augmented generation
- Retriever
- Scalar quantisation
- Score fusion
Where you learn it
Recursive character splitting is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.