# Vector Database

> A vector database is a storage system optimised for indexing and querying high-dimensional embedding vectors using approximate nearest neighbour search.

Category: Architecture
Source: https://impetora.com/glossary/vector-database
Part of: Impetora AI consulting glossary (https://impetora.com/glossary)

## What is Vector Database?

Vector databases use indexes such as HNSW, IVF, or product quantisation to find the most similar vectors to a query in sub-linear time. They typically also support metadata filtering, hybrid search combining sparse and dense retrieval, and multi-tenant isolation. Examples include Postgres with the pgvector extension, Elasticsearch, OpenSearch, Weaviate, Qdrant, Pinecone, and Milvus. The choice depends on operational fit, residency, and existing data infrastructure rather than benchmark micro-differences.

## How does Vector Database apply to enterprise AI?

Enterprise RAG systems live or die by retrieval quality. Vector database choice has direct implications for EU data residency, encryption at rest, and recovery objectives.

## Related terms

- [Embedding](https://impetora.com/glossary/embedding) - An embedding is a dense numerical vector that represents a piece of content (text, image, audio) in a way that semantically similar items end up close together in the vector space.
- [RAG (Retrieval-Augmented Generation)](https://impetora.com/glossary/rag) - Retrieval-Augmented Generation (RAG) is an architecture pattern that grounds a language model's output in retrieved source documents rather than relying on the model's parametric memory alone.
- [Data Residency](https://impetora.com/glossary/data-residency) - Data residency is the requirement that personal or regulated data stays within a specified geographic region throughout processing, storage, and backup.
- [Observability](https://impetora.com/glossary/observability) - Observability for AI is the ability to understand what an AI system did, why it did it, and at what cost, by inspecting its inputs, outputs, intermediate steps, and metrics.

## External references

- [pgvector](https://github.com/pgvector/pgvector)

---

Impetora is a custom AI consultancy and solutions partner for enterprises in regulated industries. Submit a project at https://impetora.com/intake.