20 companies
Loading the map…
Storage and search for embeddings, used to give a model access to information it was never trained on. Purpose-built vector databases sit here beside established general-purpose databases and search engines that have added vector indexes. Choosing between those two is the central decision in the space.
Weigh a dedicated vector store against a vector index in a database you already run in production. Compare index types and their recall-versus-latency trade-offs, hybrid keyword-plus-vector search, metadata filtering, and whether you can self-host. At small scale the general-purpose option is very often enough.