We recently had another user describing a similar issue and we discussed possible causes.
You can try disabling the Code Interpreter, updating, enabling the Cost interpreter and updating again. But this bugfix is hit or miss.
Then we had the assumption that it may be caused by instructions somewhere in the GPT that breach the usage policies. But we can’t confirm this either.
So, sorry nothing concrete to solve your issue.
But maybe some entry points to look for solutions.
Unfortunately Code Interpreter has always been deactivated, but thanks for the tips, i will have a look around instruction looking forward news about the real cause.
I did some limited testing and after I uploaded a file, gave it context I left the builder, went and used the chatbot and it could read and access the file appropriately. I went back into the builder and despite the file still being listed in the configuration area, the builder chat wouldn’t recognize the file.
I think opened up another chatbot conversation, and while the builder can’t read the file, the regular chatbot conversation still could.
Not sure if that interaction helps or not, but I thought it weird.
In my case, i’m still waiting for a confirmation, it looks like something goes wrong if there’s a part of text in knowledge could violate policies. By the way i found so hard to find them, think if you have an academic paper on art mentioning a living artist. It requires a lot of effort if you have 10/12 long documents…
I’m trying to solve with instructions like:
“Filter your search avoiding export of content might violate content policy” but it doesn’work.
My case is a bit more borderline. If i take a book, make my own summary with my opinion and i put everything into a .txt file, inspired obviously by book content but filtered by me, is it a violation? I’m in this field.
Another thing not clear to me is the following: similar content output sometimes is retrievd by the model base knowledge (no uploaded file) during conversation, why in that case is there no violation?
I suggest you try the following based on a somewhat similar issue we were able to solve:
Create a new GPT and see if the same issue happens again.
Then take some files that you know will not be copyrighted in any way and create a GPT just to make sure that it’s not a bug with the retrieval.
If you then determine that the problem is actually in your files you have the time intensive task of finding out where the issue is inside your files.
Maybe go one file at a time and see which one breaks your app.
Then when you have a potential candidate do a quicksearch algorithmic approach where you split the file in the middle and see which part causes the issue and then dig deeper until you found the culprit.
This is cumbersome and I think it makes sense for us to relegate this info directly to OpenAI. At least we should get a better error message. That would be helpful for all of us.
Over the past 2-3 weeks, I’ve encountered a significant issue with my custom GPT assistants on both GPT Plus and GPT Team accounts.
The problem is that my assistants suddenly seem to be ignoring all the materials uploaded to the KNOWLEDGE section. In some cases, they completely disregard the information, while in others, they only partially reference it. Even when I explicitly instruct them to “always review the uploaded KNOWLEDGE” in the instructions, the issue persists. Typically, the problem is only resolved after I prompt them following an incorrect response, which is far from ideal.
This behavior is entirely new—up until recently, the assistants were functioning perfectly for about four months. I’m concerned that this issue could potentially impact the functionality of many other custom assistants as well.
I wanted to ask if anyone else has experienced similar behavior with their GPT assistants? Do you think this could be a widespread bug or an isolated incident?
I have been experiencing this for about 3 weeks straight now. Any CustomGPT with more than 1 file attached is now completely dead. Sorry I don’t have a fix for you; but yes…you are not the only one experiencing this. I have reached out to openai multiple times and have had no luck getting any help.
Incidentally I got on a video call with a friend in the Philippines and got him to create a new GPT while I watched. As soon as he hit 2-3 files (no matter the content) the GPT started failing to update and ignoring the knowledge in the files.
Existing GPTs do not seem to be affected unless you hit the update button for any reason, then they are broken as well.
I hope openai can add some insight to this because as of right now, custom gpts do not exist for me unfortunately.
Having exactly the same problem with Knowledge files. When I created the GPT it worked for the first 24 hours then it now can’t access the files. I’ve tried reuploading in both XLSX and CSV format and no luck at all. It makes it impossible for me to launch this GPT for our team to use.
anynone is facing same behavior?