Bug: Evo hits ratelimit for GPT4
rihp opened this issue · comments
Describe the bug
Sometimes evo hits the rate limit like so
Error: { "message": "429 Rate limit reached for gpt-4 in organization org-XXXXX on tokens_usage_based per min: Limit 10000, Used 4853, Requested 5954. Please try again in 4.842s. Visit https://platform.openai.com/account/rate-limits to learn more." }
evo is not configured to watch for timouts and reprompt at the api request level after waiting
To Reproduce
Steps to reproduce the behavior:
1 large initial prompt of about 1,4k tokens
Expected behavior
system should retry once you reach the limits
Desktop (please complete the following information):
on the evo.ninja website
Additional context
Reported by AncientSage10x on Discord