At Supabase, we believe that a combination of Postgres and pgvector serves as a better alternative to single-purpose databases like Pinecone for AI...
For further actions, you may consider blocking this person and/or reporting abuse
For anyone interested there's a good guide here on how to generate vector embeddings easily with pgvector on Supabase: supabase.com/docs/guides/ai/quicks...
and another guide here on how to build Q&A into something like a documentation site: supabase.com/docs/guides/ai/exampl...
Which can look something like this:
Lastly we have an awesome python library for interacting with vectors called
vecs
which you can find here: supabase.com/docs/guides/ai/python...And works a bit like this:
pumped for the pgvector 0.5.1 rollout! It'll make HNSW index builds even faster
btw
vecs
library is the one we use in all our postgres+pgvector bencmarks 😉supabase.com/docs/guides/ai/python... 👀
is there any advantage to using Python vs Javascript when working with pgvector?
not really, but python is just more widely used. also
vecs
for example, exposes nice apis to make your life easier when working with vectorsIt's getting so easy these days 😌
The AI chat bot example app is really nice. Everyone looked l liked it when I demoed it at Deno Fest Tokyo!
👀 👀 👀
So happy we can generate embeddings directly in edge functions now 🔥
This is so awesome, @huggingface for the win 🙌
Amazing
Awesome! 🚀
The vecs library is great. Had me up and running building image search in no time 🚀
I created a simple wrapper to pgvector that is inspired by Pinecone's simplicity: github.com/UpMortem/simple-pgvecto...
This is a game changer.