AI engineering glossary · RAG vector search
What is RAPTOR?
RAPTOR: A technique that recursively clusters chunks, summarises each cluster and repeats to form a tree of summaries, so retrieval can draw on both fine details and high-level themes. It helps with questions about whole long documents.
RAPTOR: an example
Leaf chunks of a book are summarised per chapter, then chapters per part, and the query can match any level.
Related terms
More RAG vector search terms
- Re-embedding
- Recall-latency trade-off
- Reciprocal rank fusion
- Recursive character splitting
- Reranker
- Reranking
- Rescoring
- Retrieval evaluation
Where you learn it
RAPTOR is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.