How does Boomerang handle the trade-off between speed and accuracy? Does it sacrifice the quality of the results for faster response time? (I know answer as I am one of the founders of Vectara, asking this for the benefit of others)
On the other hand, GTR-XXL is an example of a research model that biases in favor of search relevance, at the expense of latency. It's not really practical to deploy in production environments as a result.