On: Are we at peak vector database?

[nikita]

What is taking the most time at scale? Is this ingest, index build or lookups ?

[visarga → nikita]

ingest and index build can take time

[nikita → visarga]

What volumes are we talking about.

There are ways to speed things up dramatically. Index build just became multithreaded (see above).

We have ideas on what to do with ingest.

Also do you interest from S3 ?

[visarga → nikita]

np.dot is also multi-threaded, based on BLAS