vectordb VS supabase

We needed a low latency, on premise solution that we can run on edge nodes (so lightweight) with sane defaults that anyone in the team can whim in a sec.

Result is this and we constantly benchmark performance of different embeddings to ensure best defaults.

[1] https://github.com/kagisearch/vectordb#embeddings-performanc...

If you are looking for lightweight, low- latency, fully local, end-to-end solution (chunking, embedding, storage and vector search), try vectordb [1]

Just spent a day updating it with latest benchmarks for text embedding models.

[1] https://github.com/kagisearch/vectordb

It was a great experience using Supabase’s rock-solid PostgreSQL database for this app. The DX around that product is phenomenal: viewing and managing the DB data was a lifesaver when you don’t want to craft your own admin panel from scratch.

I didn't really give much thought as to which backend I would use. I already had 2 projects in Supabase (BOXCUT & MineWork), but also a few projects in Firebase too. I was more concerned at the time at actually building the product.

Sign up for SupaBase: Head over to SupaBase and sign up. Create a new workspace and project with your preferred names.

Setting up Supabase Create a new Supabase project, and get the connection string for the database from settings > database.

Supabase (start for free)

Built with Supabase, Astro, Unreal Speech, Stable Diffusion, Replicate, Metropolitan Museum of Art

Supabase will be used for storing article data in the database and the cover image of the article in storage. Chakra UI will be used to provide style to the elements. By using both, we can build the blog with ease.

For AutoRepurpose, I opted for Supabase as the backbone of the backend. It has reliably supported Penelope AI, which garnered over 15k users in 2022 without any issues.

Semantic search demo

1. Create a new Supabase project: Visit Supabase and create a new project.