Find answers from the community

Updated 8 months ago

Agents

@Logan M do you think I could contribute this change, where I add an optional reasoning llm that handles the reasoning portion, and a generation llm that does the final generation

4 comments

LLogan M

Hmm, but how do you know ahead of time whether a tool is called vs. a final response?

mmaybe goats dont exist

Good question, and I'm going to need to look at the code to see but I was thinking maybe something could be done in finalize response

LLogan M

I think since the LLM dynamically writes tool calls and final responses, there isn't really a way to know before it write it 🤔

mmaybe goats dont exist

Oof yeah that makes sense

Add a reply