Behind almost every "AI-powered search" and RAG feature sits the same quiet workhorse: similarity search over vectors. If you're building anything that finds relevant content by meaning rather than exact keywords, you need to understand vectors — and, importantly, when you do and don't need a dedicated database for them.
An embedding is a list of numbers — a vector — that captures the meaning of a piece of text (or an image, or audio). An embedding model turns "cancel my subscription" and "how do I stop being billed" into vectors that sit close together, even though they share almost no words.
That closeness is the whole trick. Meaning becomes geometry: similar concepts land near each other in a high-dimensional space, and "find related content" becomes "find nearby vectors."
Once your content is stored as vectors, retrieval is straightforward in principle:
The challenge is doing step 2 fast when you have millions of vectors. Comparing against every one is too slow, so vector indexes use approximate nearest neighbor (ANN) algorithms that trade a tiny bit of accuracy for enormous speed.
This is the question that matters, and the honest answer is: usually not at first.
If you already run **PostgreSQL** — and with **Supabase** you do — the **pgvector** extension adds vector columns and ANN indexing right inside your existing database. That means:
For most products up to millions of vectors, pgvector is not a compromise — it's the pragmatic right answer.
Graduate to a specialized vector store when you hit real limits:
Even then, keep the metadata your app relies on in Postgres; let the vector store do only what it's uniquely good at.
The database is rarely the hard part — retrieval quality is. A few things move it more than your choice of engine:
Start simple with pgvector, measure retrieval quality on real queries, and scale the infrastructure only when the numbers demand it. If you're building AI search or RAG and want it fast and accurate without over-engineering the stack, talk to us.
Originally published on the Doktouri Agency blog. We build web, mobile, SaaS, and AI products — let's talk.