[m00dy]

does duckdb scale well over large datasets for vector search ?

[lgrebe]

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

[m00dy]

like over 1tb.

[cess11]

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]

its clear many DuckDB sql queries can handle terabytes of data, but the question here was about vector search..