# Vector database

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: vector DB, vector store, vector search, semantic search

A [database](https://ecosystem.samcarlton.com/database) built to store [embeddings](https://ecosystem.samcarlton.com/embedding) and quickly find the items closest in meaning to a question, not just the ones that share its exact words.

**For example:** A help center stores every article in a vector database. A customer asks about 'getting money back' and it finds the article titled 'Refund policy'.

## Connects to (11)

- [Embedding](https://ecosystem.samcarlton.com/embedding): A way of turning a piece of text into a list of numbers that captures its meaning, so software can tell which pieces of text are about…
- [Database](https://ecosystem.samcarlton.com/database): Organized storage for your app's information, such as users, orders and messages, so it can be saved and looked up later.
- [RAG](https://ecosystem.samcarlton.com/rag): Retrieval-augmented generation.
- [Similarity search](https://ecosystem.samcarlton.com/similarity-search): Finding the stored items whose vectors are closest to a query's vector, so results match by meaning rather than exact words.
- [Cosine similarity](https://ecosystem.samcarlton.com/cosine-similarity): A common way to measure how alike two vectors are by the angle between them.
- [Hybrid search](https://ecosystem.samcarlton.com/hybrid-search): Combining keyword search and similarity search, so results match both exact terms, such as product codes, and overall meaning.
- [Latent space](https://ecosystem.samcarlton.com/latent-space): The internal map of numbers where a model places the things it reads.
- [Lexical search](https://ecosystem.samcarlton.com/lexical-search): Search that matches the exact words in a query.
- [Chunking](https://ecosystem.samcarlton.com/chunking): Splitting long documents into smaller passages before creating embeddings, so a search can return just the relevant part instead of a…
- [Dimension](https://ecosystem.samcarlton.com/dimension): One number position in a vector, like one axis on a map.
- [Elasticsearch](https://ecosystem.samcarlton.com/elasticsearch): Software for fast searching across large amounts of text and data, from Elastic.

Map view: https://ecosystem.samcarlton.com/vector-database