Vector database

A vector database is a store built to hold embeddings (numeric representations of meaning) and to quickly find the entries most similar to a given query vector — the engine behind meaning-based search.

How it works

Ordinary databases are great at exact matches — find the row where the email equals this value. But “find the content that means roughly this” is a different problem, and that’s what a vector database is designed for.

It indexes embeddings so that, given a new query vector, it can return the closest matches in milliseconds even across large amounts of content.

How SiteMind uses it

SiteMind stores your content’s embeddings in a vector store (Postgres with the pgvector extension) so that every visitor question is matched to the most relevant passages from your knowledge base almost instantly.

Put this to work on your site

Free 3-day trial, no card required.

Start free trial