Runpod return {'error': 'request does not exist'}
I'm using stable-diffusion-forge template. I have sent requests to runpod using /run endpoint and /status endpoint for retrieving the status. Everything work normally until today when im checking the error log, it shows {'error': 'request does not exist'} when sending the /status. I think the error above is from runpod webserver. Can anyone explain about this?
Solution:Jump to solution
If you use
/runsync your request status expires in 60 seconds, and if you use /run, it expires in 30 minutes, so you need to retrieve the status before it expires. I also think you're confusing pods with serverless, because you don't use a stable-diffusion-forge template in severless, you are probably using some custom one.10 Replies
Solution
If you use
/runsync your request status expires in 60 seconds, and if you use /run, it expires in 30 minutes, so you need to retrieve the status before it expires. I also think you're confusing pods with serverless, because you don't use a stable-diffusion-forge template in severless, you are probably using some custom one.Yes, i'm using a custom one from ashleykleynhans but i dont think the problem is from forge. So when the request is expired, it will return above error? But i'm using the /run and try to retrieve the result immediately, weird
yep you will get that error if the request doesnt exist
if you try to do /run it'll return the job's id and status "in_progress", all you need to do is retrieve the job id, and hit the /status and put the id in
you'll get the result there
/run only makes the job, and /runsync runs the job and waits for around a minute before sending request in progress
Yes, that what im doing now, everything working right but only one request return that error
but /run's request Results expire in 30 minutes
while /runsync request Results expire in 1 minutes no matter what
well if request expires, all will be not found and will return that error
so everything good now?
Yes, everything is good now but i want to understand why it happened to handle that in the future
Hmm so there can be two ways to handle i think
either you retry it using /run and collect it using /status or webhooks ( read docs for webhooks )
or well return error that the job has failed.
because the request no longer exists ( expired ) or wrong id
Store your output somewhere if you dont wanna lose it
How are you sending and checking the request? If you're using postman, ensure the request id is correct.
Thanks,
I'm using runpod sdk
i dont thing the request id is wrong because every others request work normally
alright