I'm trying to evaluate the performance of Oryx 1.x by comparing the recommendations to products subsequently browsed/purchased. Is there an endpoint to query recommendations for multiple users at once? There is /recommendToMany but as far as I understand it, it is getting the recommendations to a group of users whose tastes are assumed similar (clustering first?), which is not quite what I want.
Any pointers would be appreciated!
No sorry, there is not a 'bulk recommend' endpoint at the moment. You can just make a bunch of requests, even in parallel. This works fine but has network overhead; if you're running on the same host as the server though I find it pretty negligible.