Data / Knowledge library
Qdrant
vector similarity search with payload filtering
Why learn Qdrant?
Useful for semantic retrieval where metadata constraints matter. Embedding quality and measured recall remain separate from database availability.
Where it came from
Qdrant stores vectors and associated payloads for similarity search. Its interfaces support managing collections and combining vector queries with structured filters.
Build your understanding
Work through these exercises in order. Try the task before opening a reference.
- Create a collection with the correct vector dimension.
- Insert vectors with document metadata.
- Run a nearest-neighbor query with a filter.
- Compare approximate results with a small exact baseline.
- Test deletion and isolation between document groups.
Documentation and sources
- Official documentation (qdrant.tech)
Catalog research notes
- Research snapshot: September 9, 2026. This entry summarizes the linked primary documentation; it does not assert a latest release version.