AI engineering glossary · RAG vector search
What is recall-latency trade-off?
Recall-latency trade-off: The tension in approximate search where raising accuracy, by searching more of the index, increases query time. Tuning parameters such as efSearch or nprobe moves along this curve, and choices depend on the product's latency budget.
Recall-latency trade-off: an example
Recall of 95% at 4 ms may become 99% at 12 ms after raising the search effort.
Related terms
More RAG vector search terms
- Reciprocal rank fusion
- Recursive character splitting
- Reranker
- Reranking
- Rescoring
- Retrieval evaluation
- Retrieval-augmented generation
- Retriever
Where you learn it
Recall-latency trade-off is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.