Definition

What is a vector database?

Last updated

Definition

A vector database is a data store optimized for similarity search over high-dimensional vectors — used as the retrieval layer for RAG, recommendation, and semantic search applications.

Vector databases index embedding vectors and answer "find the K most similar to this query vector" in milliseconds even at scale. Common options: pgvector (Postgres extension, simplest path), Pinecone (managed), Qdrant (open-source, performant), Weaviate (graph + vector hybrid), and Chroma (developer-friendly). For small corpora, a flat in-memory index works; for production scale, you want HNSW or IVF indexes.

Picking a vector database

  • Already on Postgres? pgvector. Same backups, same connection pool, no new ops.
  • Need scale beyond a single Postgres node? Pinecone (managed) or Qdrant (self-hosted).
  • Hybrid search (vector + keyword)? Weaviate or Postgres with tsvector + pgvector.

Glitch Grow’s Sales Agent uses Postgres + pgvector + tsvector — vector for semantic similarity, FTS for exact matches, in one database with one ops surface.

Related terms

Related agents

Sources

Free Vibe Coder Kit

Get the kit. Ship like a vibe coder.

Installs into Claude Code, Codex, or OpenClaws in under a minute. Required to deploy our paid agents.

Protected by Cloudflare Turnstile. We never share your details. Unsubscribe any time.