A vector database is a database specialized in storing vectors, called embeddings, and in quickly finding the vectors closest to a query, which makes it possible to retrieve content by closeness of meaning rather than by keywords.
Each document, paragraph or image is converted into a vector by an embedding model. For a given question, the database returns the items whose vectors are closest. Over millions of vectors, an exhaustive comparison would be too slow: it uses approximate search indexes (HNSW, IVF, DiskANN) that trade a little precision for a lot of speed.
It is the typical storage layer of RAG architectures, recommendation engines and semantic search. There are dedicated databases (Pinecone as a managed service, Qdrant, Weaviate, Milvus or Chroma as open source) and extensions of existing databases, such as pgvector for PostgreSQL or the vector search in Elasticsearch and OpenSearch.
Why it matters when hiring
Plugging a vector database into a RAG tutorial takes an hour. Making it work in production is another matter: document chunking, choice of embedding model, filtering, index updates, measuring result quality. Ask the AI Engineer how they evaluated the relevance of their search. Without metrics or a test set, the project never got past the demo stage.