# Vector Database

> A database optimized for storing embeddings and finding similar items quickly.

- Category: Retrieval & Grounding
- Stage: Established
- Also called: Vector store, Embedding index
- Canonical: https://www.joelcsaji.com/ai-dictionary/vector-database

## Plain English

It is a search engine for meaning-shaped numbers.

## Example

A docs assistant stores article embeddings and retrieves the closest chunks to a user's question.

## Why it matters

Vector databases became core infrastructure for RAG and semantic search products.

## Related

- [Embedding](https://www.joelcsaji.com/ai-dictionary/embedding)
- [Hybrid Search](https://www.joelcsaji.com/ai-dictionary/hybrid-search)
- [RAG](https://www.joelcsaji.com/ai-dictionary/retrieval-augmented-generation)

## Sources

- [IBM: Retrieval-Augmented Generation](https://www.ibm.com/think/topics/retrieval-augmented-generation)
- [Google Cloud Generative AI Glossary](https://docs.cloud.google.com/docs/generative-ai/glossary)