AI engineering glossary · RAG vector search
What is metadata filtering?
Metadata filtering: Restricting a vector search to records whose metadata matches conditions, such as a date range, language or department. It narrows the candidate set to relevant, permitted items and can be applied before or after the similarity search.
Metadata filtering: an example
A query for 'leave policy' is limited to chunks where department = 'HR' and year >= 2024.
Related terms
More RAG vector search terms
- Multi-hop retrieval
- Multi-query retrieval
- Multi-tenancy
- Multi-vector retrieval
- Multimodal retrieval
- Nearest neighbour search
- nprobe
- Parent-document retrieval
Where you learn it
Metadata filtering is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.