FANN: Vector Search in 200 Lines of Rust

Re:FANN: Vector Search in 200 Lines of Rust by tipsytoad on Thursday June 15, 2023 @10:47AM (#36341273)

I couldn't find anywhere in the article, how long does it take to add all 10,000 embeddings to the index? That seems quite important for many applications

[ Parent | on HN ]

Re:FANN: Vector Search in 200 Lines of Rust by zX41ZdbW on Thursday June 15, 2023 @11:24AM (#36341864)

It should take less than one second on CPU.

For example, see my comment above: https://news.ycombinator.com/item?id=36341754

[ Parent | on HN ]

Re:FANN: Vector Search in 200 Lines of Rust by nikhilgarg28 on Thursday June 15, 2023 @02:30PM (#36344663)

We did some benchmarking and found that an index of 1M vectors using 15 trees can be built up in ~115 seconds (8 CPU, 8 GB RAM). https://github.com/fennel-ai/fann/pull/8.

Given this, around a second to build an index of 10K items sounds about right.

[ Parent | on HN ]