---
title: "Vector database: Definition"
description: "A data store that indexes embeddings (numerical representations of text or images) so semantically similar content can be retrieved quickly, commonly used "
canonical: https://sudosapient.si/terms/vector-database
updated: 2026-10-27
publisher: Sudo Sapient (https://sudosapient.com/)
---
# Vector database

**Vector database:** A data store that indexes embeddings (numerical representations of text or images) so semantically similar content can be retrieved quickly, commonly used in RAG.

## Why it matters

A vector database is a means, not a goal. For many first systems, a vector index inside an existing database such as Postgres with pgvector is enough. Choose a dedicated vector store when scale, latency or filtering needs demand it, and remember that chunking and metadata usually matter more than the database brand.

## Related terms

- [Retrieval-augmented generation (RAG)](https://sudosapient.si/terms/rag): A technique in which relevant documents are retrieved from a company's own data and supplied to a language model so its answer is grounded in, and can cite, those sources.
- [Embeddings](https://sudosapient.si/terms/embeddings): Numerical vectors that represent the meaning of text, images or other data so that similarity can be computed.

## In practice

In a Sudo Sapient sprint, this is a building block of AI Product Development: agents, copilots and AI-native features shipped in 6–10 weeks. [Sudo Sapient's services](https://sudosapient.com/services/) describe the scope.