Vektorske baze podatkov shranjujejo in učinkovito iskujejo embedinge (vektorske predstavitve) po podobnosti — omogočajo semantično iskanje, RAG in sisteme priporočil. So ključna infrastrukturna komponenta za moderne aplikacije umetne inteligence, ki delujejo z embedingi.
Kaj vektorske baze podatkov počnejo
VECTOR DATABASE → stores EMBEDDINGS (vectors) and searches them by SIMILARITY:
→ store millions of vectors (representing documents, images, etc.)
→ given a query vector, efficiently find the most SIMILAR vectors (nearest neighbors)
→ optimized for high-dimensional vector similarity search at scale
→ enables fast semantic similarity search over large embedding collections
