AI engineering glossary · RAG vector search
What is semantic cache?
Semantic cache: A cache that returns a stored answer when a new question is close enough in meaning, by embedding similarity, to an earlier one. It saves model calls, but a loose threshold can return a wrong answer to a subtly different question.
Semantic cache: an example
'How do I reset my password?' reuses the cached answer to 'Steps to change my password' at similarity 0.95.
Related terms
More RAG vector search terms
- Semantic chunking
- Sentence window retrieval
- Similarity threshold
- Small-to-big retrieval
- Sparse retrieval
- Structure-aware chunking
- Synthetic test set
- Table extraction
Where you learn it
Semantic cache is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.