@track

Decorator which creates a Pay-i instrumentation scope. Every inference request in this scope will be instrumented by Pay-i with the properties defined

To use @track effectively, you must also understand how python decorators are evaluted. @track is called once when the decoratored function is defined and NOT each time the decorated function is called. For instance the following example, @track() is called when do_work() declared on line 4, generating one random use_case_id value that will be shared across all calls to do_work(). In other words, @track()is not called when do_work() is called on lines 8 and 9.

from random import random

@track(use_case_name="example", use_case_id=str(random()))
def do_work():
  # inference calls
  ...
  
do_work()
do_work()

All parameters are optional and default to None

Parameter	Type	Notes
`limit_ids`	`list[str]`
`use_case_name`	`str`
`use_case_id`	`str`	If `None`and the passed `use_case_name` 1. creates a new payi instrumentation scope 2. or is different value comapred to the current payi instrumentation scope Then in a new `use_case_id` will be automatically generated for the new payi instrumenation scope. This evaluation occurs every time the decorated function (`do_work()` in the example) is called.
`use_case_version`	`int`
`user_id`	`str`
`account_name`	`str`
`request_properties`	`dict[str, str]`
`use_case_properties`	`dict[str, str]`
`log_prompt_and_response`	`bool`	Overrides the global `log_prompt_and_response` setting created by payi_instrument()