Bug: MAIN: Changing model mid conversation to a non-vision model results in a HANG if the conversation contains an image. #1056

New Issue

2025-11-11T14:36:24-06:00

GiteaMirror commented

2025-11-11 14:36:24 -06:00

Originally created by @spammenotinoz on GitHub (May 28, 2024).

Bug Report

Description

Bug: MAIN: Changing model mid conversation to a non-vision model results in a HANG if the conversation contains an image.

Bug Summary: / Steps to Reproduce:

Start a conversation with a vision capable model, upload an Image and submit message.
Upon receipt of response, change model to one that does NOT support models (ie: most)

MAIN Branch: Hangs for a long time before returning a response..
DEV Brach: Red Error "Model x is not vision capable"

Expected Behavior:
Upon Model Change, either Clear entire History, or clear images from History.

Actual Behavior:
PROD: Pause for a few minutes before a response.
DEV: Red Error "Model x is not vision capable"

Environment

Open WebUI Version: [e.g., 0.1.120]
Ollama (if applicable): [N/A
Operating System: [Windows 10 and Ubuntu 20.04]
Browser (if applicable): [Edge and Safari]

Reproduction Details

Confirmation:

[ x ] I have read and followed all the instructions provided in the README.md.
[ x ] I am on the latest version of both Open WebUI and Ollama.
[ N/A ] I have included the browser console logs.
[ N/A ] I have included the Docker container logs.

Logs and Screenshots

No Errors in Logs

Browser Console Logs:
[Include relevant browser console logs, if applicable]

Docker Container Logs:
No errors in logs

Screenshots (if applicable):
Hang is not applicable in a screen shot, so not included.

Installation Method

Docker Compose

Additional Information

N/A

Originally created by @spammenotinoz on GitHub (May 28, 2024). # Bug Report ## Description Bug: MAIN: Changing model mid conversation to a non-vision model results in a HANG if the conversation contains an image. **Bug Summary:** / **Steps to Reproduce:** 1. Start a conversation with a vision capable model, upload an Image and submit message. 2. Upon receipt of response, change model to one that does NOT support models (ie: most) 3. MAIN Branch: Hangs for a long time before returning a response.. DEV Brach: Red Error "Model x is not vision capable" **Expected Behavior:** Upon Model Change, either Clear entire History, or clear images from History. **Actual Behavior:** PROD: Pause for a few minutes before a response. DEV: Red Error "Model x is not vision capable" ## Environment - **Open WebUI Version:** [e.g., 0.1.120] - **Ollama (if applicable):** [N/A - **Operating System:** [Windows 10 and Ubuntu 20.04] - **Browser (if applicable):** [Edge and Safari] ## Reproduction Details **Confirmation:** - [ x ] I have read and followed all the instructions provided in the README.md. - [ x ] I am on the latest version of both Open WebUI and Ollama. - [ N/A ] I have included the browser console logs. - [ N/A ] I have included the Docker container logs. ## Logs and Screenshots No Errors in Logs **Browser Console Logs:** [Include relevant browser console logs, if applicable] **Docker Container Logs:** No errors in logs **Screenshots (if applicable):** Hang is not applicable in a screen shot, so not included. ## Installation Method Docker Compose ## Additional Information N/A

GiteaMirror closed this issue

2025-11-11 14:36:25 -06:00

GiteaMirror referenced this issue

2026-04-19 19:13:14 -05:00

[GH-ISSUE #1056] Is there a command tool which like the ollama cli? #12315

GiteaMirror referenced this issue

2026-04-25 02:36:10 -05:00

[GH-ISSUE #1056] Is there a command tool which like the ollama cli? #27843

GiteaMirror referenced this issue

2026-05-05 11:41:07 -05:00

[GH-ISSUE #1056] Is there a command tool which like the ollama cli? #50980

GiteaMirror referenced this issue