Glossary
Vector database
Storage built for meaning: finds content by similarity, not just keywords.
A vector database stores embeddings (numeric representations of meaning) and finds similar content fast. It is the retrieval engine inside RAG systems and semantic search: your documents become vectors, questions become vectors, and the database returns the passages whose meaning is closest. pgvector (inside PostgreSQL) covers most business scale; specialized engines matter at larger scale.
Example from practice
Searching your contracts for 'termination during probation' finds the clause using different wording entirely, because the match is on meaning.
Related terms
Evaluating what these mean for your business? See the services built on them or ask us directly.