On: Are we at peak vector database?

[vishnumohandas]

There are none that run on the edge, yet. Few more miles to go before we "peak".

[0x6c6f6c → vishnumohandas]

Hmmm. Does pgvector count? That's supported by NeonDB, serverless compute on PostgreSQL.

https://neon.tech/docs/extensions/pgvector

[nikita → 0x6c6f6c]

(Neon CEO) It’s about to get a lot better too. Pgvector now supports multi-threaded build

https://github.com/pgvector/pgvector/issues/409#issuecomment...

[boomskats → nikita]

Another very significant contribution to the pg ecosystem. You guys are awesome, thank you for everything you're doing.

[nikita → boomskats]

Lol rare collaboration between neon, AWS, and supabase.

But if Postgres wins we all win!

[vishnumohandas → 0x6c6f6c]

By "edge", I was talking about mobile / IOT devices.

The closest I can see is the VSS extension[1] for Sqlite.

[1]: https://github.com/asg017/sqlite-vss

[ipsum2 → vishnumohandas]

Incorrect, most of the libraries can run on edge, they're just C++.

[janalsncm → vishnumohandas]

What is the use case for this?

[vishnumohandas → janalsncm]

Running machine learning on device.

Context: I'm working on an e2ee alternative to Google Photos[1] where we have to cluster embeddings (for face recognition) and run similarity searches (for semantic search[2]) on device.

[1]: https://ente.io

[2]: https://openai.com/research/clip

[marginalia_nu → vishnumohandas]

hnswlib?

[vishnumohandas → marginalia_nu]

From a cursory glance, usearch[1] seems more portable.

[1]: https://github.com/unum-cloud/usearch

[marginalia_nu → vishnumohandas]

Neat!