GuidesUnderstanding AI

Vector database: what it is for

By the Banzai Labs teamUpdated on 3 min read

EmbeddingThe nearestThree passagesYou search for a meaning, not a word
The question becomes a vector; the database returns the nearest passages.

What it does

A classic database answers “which rows contain this word?”. A vector database answers “which texts mean roughly the same thing?”.

  1. 1IndexEach passage becomes an embedding, stored with its text and metadata.
  2. 2QueryThe question becomes a vector with the same model.
  3. 3FilterLanguage, customer, date: narrow down before comparing.
  4. 4ReturnThe nearest passages, with their score.

The options

Option When to choose it
pgvector (PostgreSQL) Your data is already there, reasonable volume
Qdrant, Weaviate Large volumes, rich filters, self-hosting possible
Pinecone Managed service, no server to maintain
Chroma Prototype, local tests

Common mistakes

  • Passages that are too long, which dilute the meaning.
  • Forgetting metadata, then being unable to filter.
  • Changing embedding model without re-indexing everything.

How it all fits together: RAG, AI on your documents.

Frequently asked questions

Do you need a dedicated database?
Not necessarily. If your data already lives in PostgreSQL, the pgvector extension is enough for many projects. A dedicated database makes sense with large volumes or advanced search needs.
Is the search exact?
Usually approximate: an index such as HNSW finds very close neighbours very fast, without guaranteeing the absolute closest. In practice the gap is minimal.
Can you filter by language or by customer?
Yes. Each vector carries metadata (language, customer, date) that filters the search. It is essential so that two customers’ data never mix.

Read next

All guides