narrow raptor
Our team has a rate limit request outstanding that’s blocking our summarization app.
We need a higher rate limit for gpt-3.5-turbo to facilitate summarizing large texts, but have not heard anything from support for two weeks.
Is this something the channel here can help with? We’ve previously been approved for a rate limit increase for text-davinci-003 in the past.
dire zephyr
Our team has a rate limit request outstanding that’s blocking our summarization ...
Did you use batch method?
narrow raptor
We are using LangChain to manage caching and requests. The issue we are facing is the documents are 100+ pages and hit the 90,000 cap easily with things like Map Reduce