Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
kacperlukawski
on Feb 7, 2023
|
parent
|
context
|
favorite
| on:
Storing OpenAI embeddings in Postgres with pgvecto...
What is a memory usage with 40M vectors?
leobg
on Feb 7, 2023
[–]
Good point! I believe it was on the order of 20 GB. Used a Hetzner 512 GB bare metal server. $50/m.
P.S. Many people seem to think that for vector search you need a GPU. You don't.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
