Find answers from the community

Updated 3 months ago

Translate

Hi , when using llama index and ask for translating a document, or some other tasks to last gpt-4 using your api, I often encounter api timeouts (because too much retries), how to fix that ?
L
R
4 comments
I think you'll need to either increase the timeout or increase the retries

llm = OpenAI(..., timeout=60.0, max_retries=3)

That is the default parameters
Okey, but why there is retries ?
Not sure -- maybe because the request is taking longer than 60s? Network issue?
no, does not have any network issues, as it's a azure vm lol
Add a reply
Sign up and join the conversation on Discord