Vector Databases

What is Vector Databases?

Vector databases store content not as plain text but as an embedding, namely a row of numbers that captures the meaning of a passage. A search then compares not letters but the distance between these points, finding matches that are similar in substance even when not a single word lines up literally. They form the backbone of semantic search and, in retrieval-augmented generation, deliver exactly the passages the model leans on. Whether as a standalone system like Qdrant or as the pgvector extension right inside Postgres, the principle stays the same.

select id, content
from documents
order by embedding <=> '[0.12, -0.04, 0.88]'
limit 5;