Feature to prevent openai rate limit when resuming conversations #1662
Description
Is your feature request related to a problem? Please describe.
I have noticed a few times that when I have longer conversations i seem to hit an openai rate limit immediately after loading it. Not sure what causes is, could it be that it parses the convo json and feeds it all to openai api rapid hundreds of times, rapid fire?
Describe the solution you'd like
Not sure, but a way to read through a previous conversations json locally with hitting the rate limit would be great.
Describe alternatives you've considered
No response
Additional context
No response