AI engineering glossary · RAG vector search
What is semantic chunking?
Semantic chunking: A chunking approach that embeds neighbouring sentences and starts a new chunk where the similarity between them drops sharply, signalling a topic change. Chunks then follow meaning rather than length, though it costs extra embedding computation and results vary with the threshold.
Semantic chunking: an example
Sentences about loan eligibility are grouped together; when the text moves to repayment, similarity falls below 0.6 and a new chunk starts.
Related terms
More RAG vector search terms
- Sentence window retrieval
- Similarity threshold
- Small-to-big retrieval
- Sparse retrieval
- Structure-aware chunking
- Synthetic test set
- Table extraction
- Text extraction
Where you learn it
Semantic chunking is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.