The community member who posted the original post is having an issue with their bot not routing to the correct query engine. They are wondering if there is a way to make the routing choices more robust by providing extra details, similar to how semantic routers work by creating a route and adding utterances to route to the correct direction.
The comments suggest that adding a proper and good description for each routing option is crucial, as it helps the language model (LLM) choose the best one based on the query. Additionally, the comments note that if the LLM is open-source, it may be more difficult for it to choose the correct routing option, as open-source LLMs are not as capable.
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.
