Vektorske baze podataka pohranjuju i učinkovito pretražuju embeddings (vektorske reprezentacije) prema sličnosti — omogućavajući semantičko pretraživanje, RAG i sustave preporuka. Oni su ključna komponenta infrastrukture za moderne AI aplikacije koje rade s embeddingima.
Što vektorske baze podataka rade
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
