[GH-ISSUE #21684] feat: Conforms to the standard behavior of the OpenAI API for PDF files and other supported file formats in multimodal models #35082

New Issue

GiteaMirror · 2026-04-25T09:17:03-05:00

GiteaMirror commented

2026-04-25 09:17:03 -05:00

Originally created by @Transwarpcom on GitHub (Feb 21, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/21684

Check Existing Issues

I have searched for all existing open AND closed issues and discussions for similar requests. I have found none that is comparable to my request.

Verify Feature Scope

I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.

Problem Description

The version you are currently maintaining does not correctly handle PDF files and other supported file formats as described in the OpenAI API documentation. However, according to the documentation, the development cost to fix this issue is extremely low. Thank you for your time.

Desired Solution you'd like

Correctly implement OpenAI API behavior, the official documentation is as follows:

https://developers.openai.com/api/docs/guides/pdf-files/

Alternatives Considered

No response

Additional Context

I think we could add a switch for each model to toggle between traditional PDF processing (text extraction + OCR) and API upload.

Then, we could add a system-wide switch to toggle the global default state.

If feasible, we could also test model support for this API by maintaining a list of models that support it or by curling this endpoint (though I think this might be overly complex).

Originally created by @Transwarpcom on GitHub (Feb 21, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/21684 ### Check Existing Issues - [x] I have searched for all existing **open AND closed** issues and discussions for similar requests. I have found none that is comparable to my request. ### Verify Feature Scope - [x] I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions. ### Problem Description The version you are currently maintaining does not correctly handle PDF files and other supported file formats as described in the OpenAI API documentation. However, according to the documentation, the development cost to fix this issue is extremely low. Thank you for your time. ### Desired Solution you'd like Correctly implement OpenAI API behavior, the official documentation is as follows: https://developers.openai.com/api/docs/guides/pdf-files/ ### Alternatives Considered _No response_ ### Additional Context I think we could add a switch for each model to toggle between traditional PDF processing (text extraction + OCR) and API upload. Then, we could add a system-wide switch to toggle the global default state. If feasible, we could also test model support for this API by maintaining a list of models that support it or by curling this endpoint (though I think this might be overly complex).

GiteaMirror closed this issue

2026-04-25 09:17:04 -05:00

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#35082