Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
tebeka
25 days ago
|
parent
|
context
|
favorite
| on:
Ask HN: How are you doing RAG locally?
https://duckdb.org/2024/05/03/vector-similarity-search-vss
jlarks32
25 days ago
|
next
[–]
+1 on this one, I've been pleasantly surprised by this for a small (<3GB) local project
m00dy
25 days ago
|
prev
[–]
does duckdb scale well over large datasets for vector search ?
lgrebe
25 days ago
|
parent
[–]
What order of magnitude would you define as „large“ in this case?
m00dy
25 days ago
|
root
|
parent
[–]
like over 1tb.
cess11
25 days ago
|
root
|
parent
[–]
Some people are using DuckDB for large datasets,
https://duckdb.org/docs/stable/guides/performance/working_wi...
, but you'd probably do some testing under the specific conditions of your rig to figure out if it is a good match or not.
riku_iki
25 days ago
|
root
|
parent
[–]
its clear many DuckDB sql queries can handle terabytes of data, but the question here was about vector search..
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: