← back
Supabase Vector: The Postgres Vector database: Paul Copplestone
Takeaway
You probably don't need a dedicated vector DB — PG Vector inside the Postgres you already run gets you 90% of the way with RLS and joins.
Summary
- Supabase CEO makes the case for PG Vector over dedicated vector DBs — same Postgres you already use for auth, storage, realtime; row-level security and joins for free.
- Recounts merging PG Vector via a single cold email from Greg, then shipping Clippy (early doc-search assistant) two weeks later as the first AI-on-docs template.
- PG Vector adoption visibly accelerated new database creation on Supabase — a major tailwind on platform growth.
- Stack pitch: Postgres + Auth + Edge Functions (Deno) + Storage + Realtime + Vector all in one MIT/Apache-licensed open-source platform.
vector-dbpostgressupabase
Original description
Every month, thousands of new AI applications are launched on Supabase, powered by pgvector. We'll take a brief look into the role of pgvector in the Vector database space, some of the use cases it enables, and some of the future of embeddings in the database space. Recorded live in San Francisco at the AI Engineer Summit 2023. See the full schedule of talks at https://ai.engineer/summit/schedule & join us at the AI Engineer World's Fair in 2024! Get your tickets today at https://ai.engineer/worlds-fair About Paul Copplestone Paul is the CEO and cofounder of Supabase, a database platform for developers. He is a 3-time founder and a developer with 20 years experience. Supabase is one of the fastest-growing communities of builders. with thousands of AI applications launched every week, and powering apps with millions of users.