Lantern
Data
vector database
SHOW HN2023
196points
43comments
#284of 3,109 in 2023
Top 10%of 2023 by points
How HN took it
CuriousMostly questions and neutral comments
3 positive, 22 neutral or asking, 1 mixed, 2 critical, out of 28 comments about the project. Thread score +0.04.
Performance: 1 for, 0 againstDesign: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Performance results and benchmarking CI praised
From 2 comments
Epic result, and thank you for mentioning USearch! Would be happy to further optimize it for your needs! I also love your specialized CI! Pgvector probably doesn’t report…
ashvardanian on HNThat's really useful, thanks.
simonw on HN
Objections
Free AirPods Pro offer to switch from pgvector seen as sketchy
From 3 comments
> 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…
bryan0 on HNAlthough 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…
gregwebs on HNThis is fine, its a standard enterprise marketing technique. Watch a webinar, get a gift card.
rawrawrawrr on HN
Lacks VACUUM cleanup and IVFFlat support
From 2 comments
I'm using pgvector in production, mainly in a table with 500k-1M rows. My main use case is to return search results with pagination: page 1 from 1-50, page 2 from 51-100, page 3…
carlossouza on HNHow do you do cleanup of the index during VACUUM? And, do you have recall-vs-qps graphs like those on https://ann-benchmarks.com/ ? Those are generally more apples-to-apples, as…
mattashii on HN
Embedding functions in the extension raise design concerns
From 1 comment
When you say "produced locally", do you mean on the client? If so, does this mean you require me to use some alternate PostgreSQL driver locally, parsing the SQL to add your one…
saurik on HN
Requests
Support for IVFFlat-style pagination queries
From 1 comment
I'm using pgvector in production, mainly in a table with 500k-1M rows. My main use case is to return search results with pagination: page 1 from 1-50, page 2 from 51-100, page 3…
carlossouza on HN
Sparse vector support for hybrid search
From 2 comments
Any plans to support sparse vectors?
dalberto on HNFor hybrid search
dalberto on HN
Recall-vs-QPS benchmarks on larger datasets
From 2 comments
How do you do cleanup of the index during VACUUM? And, do you have recall-vs-qps graphs like those on https://ann-benchmarks.com/ ? Those are generally more apples-to-apples, as…
mattashii on HNCurious about how it scales. Plenty of solutions look good with small amounts of data, but completely fall apart past a point. Would be interesting to see the latency numbers for…
loxias on HN
Questions
How does it differ from pgvector and hosted Postgres with pgvector
From 1 comment
This might be a noob question but what does Lantern have that a normal Postgres dB with pgvector does not? I think Supabase already has a Postgres as a service product with the…
fakedang on HN
Can it run on Supabase
From 2 comments
can I use this in Supabase?
justanotheratom on HNNot 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…
radus on HN
How index updates and inserts perform
From 2 comments
"There's three key metrics we track. CREATE INDEX time, SELECT throughput, and SELECT latency." There's a fourth metric that I'm really interested in: assuming it's possible, how…
simonw on HN> There's a fourth metric that I'm really interested in: assuming it's possible, how long does it take to update the index with just one or two updated or inserted vectors?…
diqi on HN
Alternatives named
pgvector
From 2 comments
> 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…
bryan0 on HNHow do you handle conflict with pgvector's hnsw if you want to install both extensions ? CREATE INDEX semantic_image ON image_table USING hnsw (v dist_cos_ops) WITH (M=5, ef=30,…
raoufchebri on HN
Qdrant
From 1 comment
I like how easy postgresql vector is to use, but scaling up seems to get pretty expensive when comapred to something like qdrant.
swalsh on HN
pg_embedding (Neon)
From 1 comment