Serverles endpoint status and runsync not returning data anymore in request body (request not found)
Hey Team, I have a custom serverless endpoint worker. It always works. The logs always show that everything went as planned and the requests are always marked as completed after the time I expect. However, on my API the requests error out and on the UI they show completed but have no output. When I inspect the status on Thunderclient, runpod says that the request does not exist. I would like to understand what is going on and how I can make my api more resilient to these issues.
Attached are screenshots of the behavior:
4 Replies
Request does not exists means it expires
Use /run for longer response expiry
If you use /runsync it expires in one minute
Thank you very much
If its scaling down to 0, and no workers are active. then it doesn't make much sense to use
runsync, right? as just downloading the container image will take longer than a minute and response will switch to async?runsync can now run for upto 5mins, use /runsync?wait=300000
this will be announced in weekly updates