privateGPT instance is only using 30-40% of my processor

[amsheldon]

I have an instance of privateGPT running in a Proxmox VM with 24 Zen3 threads assigned. The instance is only using 30 to 40% of the processor and about 24 GB of RAM when processing a request. I saw a few solutions for defining the number of threads but none of them seem to work in the newer releases. Can anyone provide a solution that will work on the current release?