workaround to OpenAi's rate limits
Important
This update introduces new config values, after running the server with this plugin you will notice a new field
Changes
- changed the function of the
use-gpt-4
value to switch between 4o when true and 4o-mini when false, if you are getting rate limited use 4o-mini - added the rate parameter, this allows you to change the amount of time between calls to GPT. The number is in seconds. increase this number if you are experiencing rate limits, it is 40 by default.