A vector database stores data in the form of embeddings — high-dimensional numerical vectors that represent meaning. When a query comes in, it is converted to a vector and the database returns the stored vectors most similar to it.
Traditional databases match exact values. Vector databases match meaning. For enterprise knowledge retrieval where users ask questions in varied language about content using different terminology, this distinction is significant. It is what makes semantic search and RAG retrieval possible at the scale and speed that enterprise applications require.
