The server had an error while processing your request. Sorry about that!
pipecat version
latest
Python version
3.12
Operating System
Ubuntu 24
Issue description
I am getting this issue in Openai Realtimebeta WebRTC api.
link: https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/19-openai-realtime-beta.py
A fatal error occurred: ErrorFrame#0(error: The server had an error while processing your request. Sorry about that! Please contact us through our help center at help.openai.com if the error persists. (include session ID in your message: sess_BP5fRzdWUvJgqrLQY5bv1). We recommend you retry your request., fatal: True)
Reproduction steps
running time issue. sometime occurs
Expected behavior
I am expecting when this error occurs if we can retry.
Actual behavior
running time issue. sometime occurs
Logs
I'm not sure there's much to do. This appears to be an OpenAI Realtime issue that's out of our control. Did your bot continue after the error?
got it @markbackman . Also i am getting this issue.
{"timestamp": "2025-04-2414:40:05.378974Z", "level": "ERROR", "fields": {"message": "stopTranscription (request 8) encountered an error: Transcription (CallState(NotInACall)) "}, " target": "daily core::native::ffi::call client"}
what does it means?
Two questions:
- Are you using Daily as a transport?
- Do you get this upon leaving?
If yes to both, then it's a log from the underlying library that can be ignored.
@vitxpert are you still impacted?
FYI: the Daily error you received looks like you attempt to stop transcription after the client already left the call.
I'm going to close this issue unless you need further help.
Faced with the same issue.
Deps: pipecat-ai[google,daily,silero,deepgram.stt,deepgram]==0.0.76
@mbarinov, sorry, which issue? There are two mentioned here. Any further info you can share?
If it's this error:
The server had an error while processing your request. Sorry about that! Please contact us through our help center at help.openai.com if the error persists.
then it's an OpenAI error, so there's not much Pipecat can do about it. The action is to contact OpenAI.
I am also having this issue sometimes in pipecat version 0.0.89.
I understand its an issue from openai. But my bot stops entirely when this error occurs. Is there any way to gracefully handle this scenario?
@markbackman
We're improving error handling here, making it more consistent: https://github.com/pipecat-ai/pipecat/pull/3084
I'm closing out this issue since it's out of scope for Pipecat, AFAIK. If there is a repro case in Pipecat that helps us find a root cause in Pipecat, we can reopen and investigate.