# Vector Database

> A place to keep embeddings and find the closest ones fast.

**Field:** Artificial Intelligence  
**Category:** Retrieval & Search  
**Also known as:** Vector DB, Vector Store

## Think of it like

Think of it like a big room of books. Books about the same thing sit side by side.

## Definition

A vector database stores embeddings and finds the ones closest to a query, fast. Each row holds a vector, the text it came from and tags like a date or an owner. An index lets a search over millions of rows take a few milliseconds. Most also let you filter by those tags. Some are stand-alone products, and many plain databases now do vector search too.

## Example

Lucy's team puts 300,000 help answers into a vector database. A customer asks a question. In 20 milliseconds, it sends back the 10 closest answers.

## Why it matters

It is the store behind most AI search and RAG systems. It turns embeddings into something you can query.

## Common mistake

Adding a new database when the one you have can already do vector search. Many teams do not need a second system.

## Three principles

- **Stores vectors and text.** Plus tags.
- **Finds the closest fast.** Through an index.
- **Often a feature.** Not always a new system.

## Related terms

- [Vector Index](https://learn.benibix.com/term/ai/vector-index)
- [Embedding (AI)](https://learn.benibix.com/term/ai/embedding)
- [Metadata Filtering](https://learn.benibix.com/term/ai/metadata-filtering)
- [Database](https://learn.benibix.com/term/development/database)
- [pgvector](https://learn.benibix.com/term/ai/pgvector)
- [Pinecone](https://learn.benibix.com/term/ai/pinecone)
- [Chroma (Vector Database)](https://learn.benibix.com/term/ai/chroma)

## Told apart from

- [FAISS vs Vector Database](https://learn.benibix.com/compare/faiss-vs-vector-database): People think FAISS is a vector database, and it is not. FAISS is a library: the fast search part, built into your own program. A vector database is a whole system around that part. It adds storage, updates, filters, backups and users. Pick FAISS to build it yourself, and a database to have it done.

![Documents pass through an embedding model and are stored as rows of vector, text and tags. A question is turned into a vector too, and the closest rows come back.](https://learn.benibix.com/diagrams/rt-vector-database.svg)

---

Source: https://learn.benibix.com/term/ai/vector-database
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
