Supabase can be used as a vector database! This means that you can perform a semantic search against Supabase! This allows you to create RAG apps or content recommendation engines on top of Supabase! Learn what embeddings are, and how you can use them 👇

Building a local tennis app with supabase , open ai embeddings, and the vector columns work very nicely

Wow, this is impressive!

Can reinforcement learning handle stock market swings? In my latest free Substack, find out how SARSA reinforcement learning algorithm can help create adaptive strategies and improve performance.

More content recommendation tutorial would be appriciated

Will try to push out more! Content recommendations with embeddings are awesome!

Makes dedicated vector DBs obsolete IMO. The only thing that's annoying is switching to a different embedding model (if a new one is released e.g. by OpenAI) is hard because of the different vector sizes. Not really a supabase issue, but in general a challenge with vector dbs I guess.

Love Supabase but we need BM25 support. I know about the options and saw previous comments on it. BM25 is still standard in dedicated vector databases and I wish Supabase would support it!

Yes! I’ve done this before and it works beautifully!!

If Supabase is connected with Real time data, Real time data gets updated in vector database as well ?

Not entirely sure of the question. Would you be able to elaborate more, maybe with examples?

I think they wrote pgvector which you're free to use for extending postgresql.