[GH-ISSUE #8220] Image requests from OpenWebUI not reaching Ollama #53709

New Issue

GiteaMirror · 2026-05-05T15:10:37-05:00

GiteaMirror commented

2026-05-05 15:10:37 -05:00

Originally created by @loglux on GitHub (Dec 31, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8220

I've encountered an issue with OpenWebUI where image requests no longer work, although everything was functioning properly before. This might have started after an OpenWebUI update.

Details of the setup:

Models Used: LLaMA3.2-Vision, LLAVA, LLAVA-LLaMA3.
OpenWebUI Environment: Running in a Docker container on a NAS.
Ollama Environment: Running locally on a Windows 11 machine.

Issue Description:

Text-based chats work perfectly.
When I try to send an image, nothing happens: the spinner shows up, but it gets stuck and no further processing occurs.
Logs:
- No errors in OpenWebUI logs.
- Ollama doesn't receive any requests when images are sent.
Tests and Observations:
- Network connectivity between the Docker container and the Windows machine is fine (tested with curl).
- Models in OpenWebUI are loaded correctly, and text messages are processed as expected.

What I’ve Tried:

Checked OpenWebUI logs—no relevant errors.
Confirmed that Ollama is running and reachable on the correct port.
Restarted both OpenWebUI and Ollama.
Updated OpenWebUI and Ollama to the latest versions.

It seems like OpenWebUI is not forwarding image requests to Ollama for some reason. Has anyone else encountered this issue or know how to resolve it?

Thanks in advance for any advice or suggestions!

PS.
OpenWebUI Version: v0.5.2 (on OpenWebUI Version: v0.5.1 didn't work too)

Originally created by @loglux on GitHub (Dec 31, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/8220 I've encountered an issue with OpenWebUI where image requests no longer work, although everything was functioning properly before. This might have started after an OpenWebUI update. ### Details of the setup: - **Models Used:** LLaMA3.2-Vision, LLAVA, LLAVA-LLaMA3. - **OpenWebUI Environment:** Running in a Docker container on a NAS. - **Ollama Environment:** Running locally on a Windows 11 machine. ### Issue Description: - Text-based chats work perfectly. - When I try to send an image, nothing happens: the spinner shows up, but it gets stuck and no further processing occurs. - **Logs:** - No errors in OpenWebUI logs. - Ollama doesn't receive any requests when images are sent. - **Tests and Observations:** - Network connectivity between the Docker container and the Windows machine is fine (tested with `curl`). - Models in OpenWebUI are loaded correctly, and text messages are processed as expected. ### What I’ve Tried: 1. Checked OpenWebUI logs—no relevant errors. 2. Confirmed that Ollama is running and reachable on the correct port. 3. Restarted both OpenWebUI and Ollama. 4. Updated OpenWebUI and Ollama to the latest versions. It seems like OpenWebUI is not forwarding image requests to Ollama for some reason. Has anyone else encountered this issue or know how to resolve it? Thanks in advance for any advice or suggestions! PS. OpenWebUI Version: v0.5.2 (on OpenWebUI Version: v0.5.1 didn't work too)

GiteaMirror closed this issue

2026-05-05 15:10:38 -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#53709