https://prefect.io logo
Title
n

Ned Cartmell

05/17/2023, 8:29 PM
Hey team, just learned about Marvin and can't stop using it! That said, I'm now encountering a timeout error when I try to use an `@ai_model`to extract structured data from freetext, as below. Seems like it's set to 60 seconds somewhere:
13:23:45.510 | WARNING | langchain.chat_models.openai - Retrying langchain.chat_models.openai.acompletion_with_retry.<locals>._completion_with_retry in 1.0 seconds as it raised Timeout: Request timed out.
πŸ˜›anda-dancing: 1
Any idea how I can set the timeout to be longer? I don't see anything promising in
marvin.settings
n

Nate

05/17/2023, 9:36 PM
hi there @Ned Cartmell - great to hear you're using Marvin πŸ™‚ we use langchain for the actual API call, and Im not actually sure if they expose timeout configuration I can check!
worth mentioning that there was an outage with OpenAI today that might explain those timeouts
πŸ‘€ 1
and just so you know, we have a discord where we talk all things Marvin
πŸ™Œ 1