AI engineering glossary · RAG vector search
What is dense retrieval?
Dense retrieval: Finding documents by comparing the dense embedding of a query with dense embeddings of documents, so matches are based on meaning. It handles paraphrases well but can miss exact identifiers or rare terms.
Dense retrieval: an example
The query 'how to reset my password' retrieves an article titled 'Recover account access' with no shared keywords.
Related terms
More RAG vector search terms
- DiskANN
- Document loader
- Domain adaptation of embeddings
- efConstruction
- efSearch
- Embedding
- Embedding cache
- Embedding drift
Where you learn it
Dense retrieval is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.