this is a long time for such a key feature to be down. I’m surprised.
It behaves like it knows how to look into the documents, but it does not generate any knowledge from doing so
Yes, certain formats are only able to be read by Code Interpreter, but it doesn’t say that for PDFs, for example.
has anyone escalated this issue? any response from OpenAI? Any timeline when this would be resolved? Its really frustrating now wasting my money on their subscription
Nope. Interestingly it is only some of my CustomGPT’s that are effected. Its got something to do with a feature where its searches twice and the proper search takes to long so it gives up and uses the 1st 5sec search.
The issue is also being discussed in this thread, no response from OpenAI yet: https://community.openai.com/t/gpt-suddenly-cant-read-files-in-its-knowledge-base
Hey folks, I flagged this to the team, will follow up with details soon!
Thanks. Been like this for 3+ days.
Update: The functionality of reading data from knowledge source is back!
Hey folks! This should now be resolved. I am going to close this thread so it is easier to track if things like this happen in the future. Thanks for being patient and building with us : )