#Spike of errors when streaming from the API

5 messages · Page 1 of 1 (latest)

cold lava
#

Hi I'm getting a spike of such errors when streaming from the API:

{"error": {"message": "The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID 4a05cb0f2e10da70ff323b9791deddcc in your email.)", "type": "server_error", "param": null, "code": null, "internal_message": "AssertionError('num_top_logprobs=40 num_tokens=469')"}}
#

The internal_message "AssertionError" is quite suspicious

clear scroll
#

This appears to be an error message from the OpenAI server. It seems that there was an issue processing your request and the server encountered an "AssertionError" with the message "num_top_logprobs=40 num_tokens=469." It is suggesting that you retry the request or contact OpenAI through their help center for further assistance with this error. Additionally, it has provided a request ID (4a05cb0f2e10da70ff323b9791deddcc) that you should include in your email for reference.

terse furnace
#

Yeah, this looks like an API error, not something on your end 🙂

cold lava
#

Indeed. The main question is that these errors started popping up quite a lot in the last few hours.