Skip to main content
All CollectionsChatGPT Enterprise
Visual Retrieval with PDFs FAQ
Visual Retrieval with PDFs FAQ
Updated over a month ago

What is this feature?

ChatGPT Enterprise now supports reading and understanding visuals (images, graphs, diagrams, etc.) embedded in PDF files. Users can upload a PDF, and ChatGPT can interpret the text and any visual elements within that file.

Who can use it?

This capability is available only to ChatGPT Enterprise customers. It is not supported for ChatGPT Free, Pro, Team, or Edu accounts, and it is not currently available for GPT-based projects.

What problem does it solve?

Previously, ChatGPT could only process images when uploaded separately (e.g., as PNGs/JPEGs). Embedded visuals within a PDF were overlooked. Now, ChatGPT can provide a more holistic analysis—combining the text and visuals in one go—leading to more accurate and context-rich responses.

How does it work?

  1. Click the paperclip (attachment) icon in the chat to upload your PDF.

  2. ChatGPT will read both the text and any embedded images or diagrams within the PDF.

  3. You can then ask questions or request summaries—anything from extracting the main points of a report to explaining complex charts.

Will this feature eventually extend to other plans?

It’s currently exclusive to Enterprise and may be expanded in the future. We’re monitoring customer feedback to determine when and how to broaden support.

Did this answer your question?