# Vector database

> A vector database stores embeddings, the numeric fingerprints of text or images, and quickly finds the stored items whose meaning is closest to a query.

- Page: https://methodcrew.com/glossary/vector-database
- Last updated: 2026-10-28
- Publisher: [The Method Crew](https://methodcrew.com/)
- Also known as: vector store

## How it works

Each document passage is turned into an [embedding](https://methodcrew.com/glossary/embeddings): a list of hundreds or thousands of numbers that places it in a space where similar meanings sit close together. The vector database stores those lists alongside the original text and metadata such as source, date and access rights. A query is embedded the same way, and the database returns its nearest neighbors.

Comparing a query against millions of vectors one by one is slow, so these systems build approximate nearest neighbor indexes such as [HNSW](https://arxiv.org/abs/1603.09320) (Malkov and Yashunin, 2016). They give up a sliver of accuracy to answer in milliseconds.

Options range from dedicated services (Pinecone, Qdrant, Weaviate, Milvus) to the [pgvector](https://github.com/pgvector/pgvector) extension for Postgres, which many teams already run. It runs exact search by default and approximate search once you add an HNSW or IVFFlat index.

## How businesses use it

A vector database is the retrieval layer under most [RAG systems](https://methodcrew.com/glossary/retrieval-augmented-generation). It also powers [semantic search](https://methodcrew.com/glossary/semantic-search) on help centers, product recommendations and duplicate detection, for example spotting the same supplier entered 3 different ways.

For most companies with fewer than a few million passages, Postgres with pgvector is enough, and it keeps your data in a database you already back up and secure. A dedicated service is worth the cost at larger scale or with heavy filtering. On our [RAG builds](https://methodcrew.com/services/rag-knowledge-systems), the infrastructure sits on your account and is passed through at cost.

## Where it goes wrong

Teams often pick the database first and the use case second. Which database you choose matters far less than how your documents are chunked and searched.

Watch for these problems instead:

- Stale data: a withdrawn policy stays searchable because nobody wired deletions into the index
- Missing filters: without metadata for department or permissions, results leak across teams
- Model changes: switching embedding models means re-embedding every document, because vectors from different models cannot be compared
- Exact terms: vector similarity is weak on SKUs and error codes, so pair it with [hybrid search](https://methodcrew.com/glossary/hybrid-search)

A vector database is a search component. It does not decide what is true, and it returns its closest match even when nothing relevant exists.

## Example (hypothetical)

Hypothetical: a 200-person insurer wants claims handlers to search 400,000 past claim notes by meaning. Postgres with pgvector, filtered by line of business and region, returns similar past claims from the database the IT team already runs, with no new vendor to approve.

## Related terms

- [Embeddings](https://methodcrew.com/glossary/embeddings): Embeddings are lists of numbers that capture the meaning of text or images, so software can measure how closely related one item is to another.
- [Semantic search](https://methodcrew.com/glossary/semantic-search): Semantic search finds results by meaning instead of exact words, so a query can match relevant content even when they share no vocabulary.
- [Hybrid search](https://methodcrew.com/glossary/hybrid-search): Hybrid search runs keyword search and semantic search on the same query and merges the results, so it catches exact terms and paraphrased meaning together.
- [Retrieval-augmented generation (RAG)](https://methodcrew.com/glossary/retrieval-augmented-generation): Retrieval-augmented generation is a method where a system first searches your own documents for relevant passages, then gives them to a language model to answer from.
- [Chunking](https://methodcrew.com/glossary/chunking): Chunking is splitting documents into smaller passages before they are embedded and indexed, so a retrieval system can find and return the exact part that answers a question.

## Services where this matters

- [RAG and knowledge systems](https://methodcrew.com/services/rag-knowledge-systems): Your documents turned into an assistant that cites its sources. $15,000 to $75,000 per project.
- [Custom AI agents and copilots](https://methodcrew.com/services/custom-ai-agents): Agents that look things up in your CRM or helpdesk and take the next step, with approvals. $15,000 to $90,000 per project.

## Articles that use this term

- [How to build a company knowledge assistant that cites its sources](https://methodcrew.com/insights/build-rag-knowledge-assistant)

Full glossary: https://methodcrew.com/glossary