ML Recommendation Engines - What Are the Bottlenecks?

The retrieval of vector search basically at scale. That part for us in the last year, I think it's been the part where we've actually working the most in production. It also comes into question what is the best possible architecture for this. Do you have two indexes, one dense and one sparse? Do you have one that kind of does both of this? Like elastic, for example, it's a popular open source choice that sort of does both. But there's an argument to be made that maybe the vector searching elastic is not the most optimized one for much learning. So now what do we do? We have a part of the company that uses elastic and a parts of the company