Find answers from the community

Updated 3 months ago

Hi all, what is the difference between

Hi all, what is the difference between using llm.predict_and_call([function1, function2]...) and using an agent with FunctionCallingAgentWorker([function1 function2], llm=llm,...)?
L
n
R
6 comments
Not much, but a function calling worker can be hooked into an overall agent with memory
the agent will drive the worker, and make many function calls

predict_and_call is a single iteration, a lower level api
Got it! Thanks for the quick response.
a followup question is:
Is it possible to assign different llms to FunctionCallingAgentWorker and AgentRunner instances?
The AgentRunner class actually doesn't use an LLM
Add a reply
Sign up and join the conversation on Discord