AI engineering glossary · RAG vector search
What is late interaction?
Late interaction: A retrieval design that keeps one vector per token for queries and documents, and scores a pair by matching each query token to its best document token and summing. It is more expressive than a single vector while allowing precomputed document representations.
Late interaction: an example
A query of 8 tokens is matched against each document's stored token vectors and the 8 best matches are added up.
Related terms
More RAG vector search terms
- Layout-aware parsing
- Learned sparse retrieval
- LLM-as-judge
- Locality-sensitive hashing
- M parameter
- Maximal marginal relevance
- Metadata filtering
- Multi-hop retrieval
Where you learn it
Late interaction is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.