Hello everyone!
I built a scenario that is supposed to extract information from supplier invoices (jpeg files).
4o-mini seemed perfect for that. I upload the file to OpenAI and then provide the assistant the file id:
But I can’t get it to work. I always get an output along the lines of ‘Please provide a file / Can’t access the file’.
With regular GPT4o it works though.
Aren’t they both supposed to support image files? Where’s the error on my part?
Thanks a lot in advance!
You could just use the Vision module instead. It’s simpler to set up.
Otherwise you need to pass in an ARRAY of file IDs, not a single file ID.
You can use an Array Aggregator, or you can add it to an empty array:
Hope this helps! Let me know if there are any further questions or issues.
— @samliew
That works wonderfully, thanks a lot Sam. You’re always very helpful, I appreciate you.
The other solution with the array ALSO works. I’m still curious why though. How did you know this to be the solution?
Best,
Tom
No problem, glad I could help!
The hint is that the field name is plural “Files” – means it takes in more than one item. When this is the case, it usually accepts an array of items, and not a single item’s value.
An array can also contain a single value, as shown above.
1. If anyone has a new question in the future, please start a new thread. This makes it easier for others with the same problem to search for the answers to specific questions, and you are more likely to receive help since newer questions are monitored closely.
2. The Make Community guidelines encourages users to try to mark helpful replies as solutions to help keep the Community organized.
This marks the topic as solved, so that:
To do this, simply click the checkbox at the bottom of the post that answers your question:
3. Don’t forget to like and bookmark this topic so you can get back to it easily in future!
No problem, glad I could help!
— @samliew
P.S.: Did you know, the concepts of about 70% of questions asked on this forum are already covered in the Make Academy. Investing some effort into it will save you lots of time and frustration using Make later!
Okay will remember for the future! ty
Hi Sam, I have a follow up question if that’s okay for you.
The scenario currently looks like this:
Now I think that if I have a PDF with multiple pages, it will only take the first page.
How can I make it so it iterates the PDF conversion for all pages and passes them as an array to GPT Vision at once?
Thanks a lot Sam!
Please create a new thread, I may not be free for the next few days and it’s unfair to others if you direct your question to me only.
