Closed hyusetiawan closed 14 hours ago
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
Closing this thread as solved.
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?