A vector database stores and indexes vector embeddings - the numeric representations that encode the meaning of a piece of text - so they can be searched by similarity at speed, even across millions of passages.
Why it matters
Finding the right passage in a large document (or a large collection of documents) means comparing a query against every stored chunk, thousands or millions of times per second. A general-purpose database isn't built for that; it stores structured rows, not clouds of high-dimensional numbers. A vector database is purpose-built for it: it organizes embeddings spatially, so a nearest-neighbor lookup is fast and cheap rather than an exhaustive scan.
That speed is what makes semantic search practical. When you ask a question, the query is embedded and the vector database finds the chunks whose vectors point in the same direction - those are the passages most likely to answer it. Without an efficient index, even a perfectly accurate embedding model can't return results in a reasonable time.
The passages a vector database returns are the raw material for retrieval-augmented generation: retrieve the right chunks first, then hand them to the model to compose an answer from real source text rather than memory.
Sidenote runs vector search under the hood whenever you ask about a document, surfacing the passages that ground each answer and make it possible to cite the exact sentence behind every claim.
FAQ
Do I need a vector database to search my own documents?
Not directly; you need a tool that uses one. Any product offering semantic search over documents runs embeddings and a vector index under the hood. The database is infrastructure, not something a reader sets up.
How is a vector database different from a regular database?
A regular database matches exact values ("find the row where id = 42"); a vector database finds nearest neighbors in high-dimensional space ("find the passages most similar in meaning to this query"). The data model, the indexes, and the queries are all built around similarity rather than equality.