Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Lantern – a PostgreSQL vector database for building AI applications

docs.lantern.dev

Post reply on HN
Print view View original

31–40 of 46 posts

Re: Show HN: Lantern – a PostgreSQL vector database for building AI applications

#31

Post by radus »

justanotheratom wrote: post #15

can I use this in Supabase?

Not a Supabase user, but to my knowledge -- no. Except for a set of blessed extentions, Supabase only supports extensions that are written in "trusted languages" (ie. supported by pg_tle), and Lantern is written in C, which is currently not supported.

Re: Show HN: Lantern – a PostgreSQL vector database for building AI applications

#32

Post by diqi »

radus wrote: post #31
justanotheratom wrote: post #15

can I use this in Supabase?

Not a Supabase user, but to my knowledge -- no. Except for a set of blessed extentions, Supabase only supports extensions that are written in "trusted languages" (ie. supported by pg_tle), and Lantern is written in C, which is currently not supported.

pgvector is written in C and is supported by Supabase. There's nothing inherent preventing Supabase from supporting Lantern.

Re: Show HN: Lantern – a PostgreSQL vector database for building AI applications

#33

Post by ezra-varady »

Hey everyone for those interested I built an updated version of the lanterndb semantic search application that should be a bit nicer. An instance is running at

http://170.187.170.169/

And code can be found at

https://github.com/ezra-varady/react-semantic-search

Re: Show HN: Lantern – a PostgreSQL vector database for building AI applications

#34

Post by dalberto »

jeungsp wrote: post #29
dalberto wrote: post #26

Any plans to support sparse vectors?

We’re built on top of Usearch, which will very soon support sparse vectors. We’re working with them to make sure it also works in Lantern. Can you tell me more about your use case?

For hybrid search

Re: Show HN: Lantern – a PostgreSQL vector database for building AI applications

#37

Post by gregwebs »

bryan0 wrote: post #35

> Switch from pgvector, get FREE AirPods Pro. > Book some time here, and we will help switch you over for FREE and get you a pair of FREE AirPods Pro This just comes off as sketchy to me. If the tech is good it will stand on its own.

Although it doesn’t meet the definition of bribery it’s a similar concept. It’s trying to influence someone’s decision by personal gain rather than just what’s best for the company. DataDog used to do this (maybe they still do) where if you signed up for a trial they said you would get a 1 in 8 chance of getting an iPhone.

Re: Show HN: Lantern – a PostgreSQL vector database for building AI applications

#40

Post by ngalstyan4 »

jw903 wrote: post #38

Impressive performance. In your experience, is there a range of vector dimension for faster search results?

We have not run microbenchmarks to see what dimension ranges perform best but those are coming soon! Below is an anecdotal answer:

We run our ci/cd benchmarks on 128dim sift vectors. We have some demos using clip embeddings (512dim) and baai/bge 768 dimensional embeddings.

Generally, smaller vectors allow higher throughput and result in smaller indexes. But the effect on performance is small. Once we merge the PR implementing vector element casts to 1 and 2 byte floats, the effect of this on throughput should be even smaller.

Post reply on HN