Ok so apparently this documentation guides how to make choices for routing. But I'm having a problem here and that is when I query the bot it doesn't route to the right query engine. I was wondering if there's any way we can make choices more robust by providing extra details as we do in semantic routers by creating a route and then adding utterances to route to the correct direction.
Adding a proper and good description for each one is a must. That helps llm in choosing the best one as per query.
In addition to this, if you are using open-source llm, it may be difficult for the llm to choose the correct one as open-source llm are not that much capable.
