Remix.run Logo
m00dy 10 hours ago

does duckdb scale well over large datasets for vector search ?

lgrebe 10 hours ago | parent [-]

What order of magnitude would you define as „large“ in this case?

m00dy 9 hours ago | parent [-]

like over 1tb.

cess11 8 hours ago | 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.