AI & LLMs
Vector Database
A database built to store embeddings and quickly find the ones most similar to a query vector.
Reviewed by the RadarTrek editorial team · June 2026
A vector database stores embeddings alongside the original text and lets you run similarity search — "find the chunks whose vectors are closest to this query's vector" — at speed across thousands or millions of records. Postgres with the pgvector extension is a common, simple choice; purpose-built options exist for larger scale.
Why it matters
- —A vector database is the retrieval half of any RAG system — without it, semantic search doesn't scale.
- —pgvector lets you add vector search to a database you may already be running, with no new infrastructure.
- —Similarity search quality depends on both the embedding model and how documents were chunked before storage.
Where to learn this
🎓
Supabase pgvector — Your First Semantic Search
RAG and Vector Search course
This is the exact lesson that covers this term in depth — with examples, diagrams, and a hands-on exercise.