I use the Open AI Assistant via the Open AI Playground. I gave it an image and told it to add the image to a Word document and export it. It exported the file. But when I go to open the Word doc, a pop up appears saying:
“Word found unreadable content in test_document_with_banner.docx. Do you want to recover the contents of this document? If you trust the source of this document, click Yes.”
I press yes, but then the image isn’t there but instead, an empty box with ‘image cannot be displayed’.
I have tried repeating this with both .png and .jpg. I’ve also lowered the file size down to 37kb. All without success.
The strange thing is, I can see the image when I preview the Word doc. I can even open the Word doc in Apple Pages and the image will be there. It’s just the Word doc that has this problem.
To make things even more confusing, the issue doesn’t occur when you create a Word doc with an image via the ChatGPT website. It only occurs via the Assistants API.