RAG Pipelines with Pinecone and Supabase pgvectorRAG Pipelines with Pinecone and Supabase pgvector
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
LAKSHAY's avatar
LAKSHAY NAGDA
• 1d
I build the "AI that knows your data" part of apps: RAG pipelines with a vector database.
I've set this up with both Pinecone and Supabase (pgvector), so I pick what fits your app, not what I'm used to.
What I do:
Turn your content (notes, documents, chats, courses) into embeddings with OpenAI
Set up search so the AI answers from your data, not from guesses
Keep each user's data private, so one user can never search another's
Connect it to a React Native, React or Next.js app with a Node.js backend
How I choose:
Private, per-user data (journals, health, notes): Supabase pgvector. It lives in the same database as your users, and Row Level Security keeps data separate.
Huge document sets where search is the whole product: Pinecone.
Small team, small budget: Supabase. Fewer things to run.
Example: Daisy, an AI journaling app I built and shipped on the Play Store and the App Store, uses a RAG pipeline with OpenAI embeddings and Pinecone.
Building an AI feature on your own data? Message me what your app does, and I'll tell you which setup fits.
ragAI Automationpinecone
Back to feed
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started