why do we need the worker phase?

Open hyusetiawan opened this issue 2 years ago • 1 comments

using gpt-4 i am able to generate plans that are interdependent as a json that i can immediately execute by looping through them, at this point, we don't need the worker phase right? I can just pass the result of the execution straight to the solver?

Sep 30 '23 19:09 hyusetiawan

Sure, the worker is just a stage for executing those plans. And since the plans are interdependent, you can parallelize the execution in most cases. See below for a 8-plan example https://youtu.be/diJ4IDaT4Z4?t=116

Oct 04 '23 02:10 billxbf

Closing this thread as solved.

Oct 04 '24 00:10 billxbf