It seems that the current mode (eg fashion) is a hybrid approach, with vector results on one side, BM25 on the other, and then a re-reank algo to smooth things out.
I'm out of my depth here but genuinely interested and curious to see over the horizon.
Out of interest how come you use the word "mode" here?
Best is to use one statistical model and encode the underlying aspects of the context that relate to goal outcomes.