vector database

A vector database is a specialized data system for storing, indexing, and querying high-dimensional embedding vectors (numerical arrays). It enables items with similar meaning or structure to be close together in vector space.

It supports fast nearest-neighbor or similarity searches using different techniques, such as graph-based indices, inverted-file clustering, product quantization or hybrid indexes—often in conjunction with metadata filters and keyword plus vector hybrid ranking.

Core capabilities of a vector database include inserting, updating, deleting (CRUD/upsert) vectors and associated metadata, batch ingestion, support for similarity metrics like cosine similarity or inner product, and trade-offs between recall and latency.