#Bug Report: Inability to Access Uploaded Document Contents in ChatGPT Across Multiple Browsers

1 messages · Page 1 of 1 (latest)

thick kernel
#

Platform/Environment: ChatGPT Web Interface; Tested on Chrome and Firefox

Description of the Issue:
When attempting to access uploaded documents in ChatGPT, an error occurs indicating that the document has no contents or cannot be opened. This issue persists across different document formats (.pdf, .docx) and browsers (Chrome, Firefox), indicating a systemic issue with ChatGPT's document handling capabilities.

Steps to Reproduce:

Attempt to upload a document (e.g., .pdf, .docx) in ChatGPT using Chrome.
Use the open_url command to access the document.
Observe the error indicating no content or inability to open the document.
Repeat steps 1-3 using Firefox to rule out browser-specific issues.
Expected Behavior:
ChatGPT should be able to access and read the contents of supported document formats uploaded by users, enabling interactions based on the document's contents.

Actual Behavior:
ChatGPT fails to access or read the contents of uploaded documents, displaying an error message about the lack of contents or inability to open the documents. This issue is consistent across multiple document types, creation methods, and web browsers.

Frequency of Occurrence: Consistently reproducible with every attempt to access uploaded documents.

Severity/Impact:
High - This issue severely impacts user experience by preventing access to a key functionality of the platform, potentially affecting user trust and the utility of ChatGPT for document-based tasks.

User Environment:

Browsers: Chrome, Firefox
Not browser extension or ad-blocker specific, as the issue persists across browsers
Attempted Workarounds:

Switching browsers from Chrome to Firefox
Uploading different document formats and a very basic test document
Multiple attempts with different files to rule out file-specific issues
None of these workarounds resolved the issue, indicating a problem inherent to the ChatGPT platform's document handling functionality.

rose micaBOT
#

Hi @thick kernel. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

Based on the information provided in the extracts, it appears that multiple users have reported similar issues with GPT's inability to read or access uploaded documents, including PDFs and text files. This issue seems to be a recent development, as users have reported that the functionality was working fine until a few days ago.

Here are some relevant extracts that highlight the issue:

  1. Forum Post: GPTs not reading PDFs in messages anymore > Answers Part 2 (https://community.openai.com/t/632599): Users reported that GPTs are no longer able to read PDFs, text files, and other document types that they upload. This issue seems to be widespread and not limited to a specific user or GPT.

  2. Forum Post: My custom GPT cannot read pdf attached in the chat box > Original post (https://community.openai.com/t/643588): A user reported that their custom GPT, which previously could read a calendar document attached in the chat window, is now unable to do so.

  3. Forum Post: GPTs not reading PDFs in messages anymore > Original post (https://community.openai.com/t/632599): A user reported that their GPT, which previously could analyze PDFs uploaded with messages, is now unable to do so.

Given the severity and widespread nature of this issue, it's recommended to reach out to OpenAI support for further assistance. It's also advisable to keep an eye on the OpenAI community forum for any updates or potential fixes for this issue.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: