Issue with Advanced Data Analysis Functionality in Reading PDFs

I am writing to report an issue I have encountered with the Advanced Data Analysis (ADA) functionality in ChatGPT, specifically regarding reading PDF files. A couple of days ago, I was able to utilize ADA to read and analyze PDF files without any problems. However, recently, the functionality seems to have been compromised as ADA is no longer able to read PDF files.

The error message I receive states: “It seems like the extracted text is encoded or encrypted, as it consists largely of non-readable characters, which might be due to the use of certain fonts or encoding mechanisms that are not directly interpretable by the text extraction tool.”

I have searched for any recent updates or changes that might have affected this functionality but have not found any clear information.

I would appreciate any insights or solutions to resolve this issue. Thank you for your time and assistance.

I’m experiencing a similar problem where the assistant I created no longer is able to read pdf’s where it was able to do that just days ago.

"I’m unable to directly read or analyze PDFs or any other documents that aren’t already part of our training data or accessible through the tools I have, such as browsing current web content. "

1 Like

when prompted it just says “The change in capabilities, such as the inability to directly read PDFs, is often due to updates or modifications in the tools and features available to me. These changes are made to optimize performance, ensure user privacy, and comply with data handling standards.”

Have you found any solutions to the problem?