> I imagine using their embeddings and training a classifier on top of that is probably a lot more effective?
I’d be interested in seeing this in action - I think the vector embeddings are underused generally - but my understanding is that’d be for something closer to sentiment analysis? In this case I’m talking about a setup closer to where you’ve got an LLM agent with a set of tools that’s interpreting a user’s request to identify which of those tools are the right ones to use. The requests can be complex, and involve multiple tool runs or chaining. If that’s doable by more deterministic mechanisms, I’d (genuinely) love to hear about it.
I’d be interested in seeing this in action - I think the vector embeddings are underused generally - but my understanding is that’d be for something closer to sentiment analysis? In this case I’m talking about a setup closer to where you’ve got an LLM agent with a set of tools that’s interpreting a user’s request to identify which of those tools are the right ones to use. The requests can be complex, and involve multiple tool runs or chaining. If that’s doable by more deterministic mechanisms, I’d (genuinely) love to hear about it.