I have searched the existing issues and discussions.
Installation Method
Docker
Open WebUI Version
git-9f27d77
Ollama Version (if applicable)
No response
Operating System
Bookworm
Browser (if applicable)
Firefox 128.7.0
Confirmation
I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have checked the browser console logs.
I have checked the Docker container logs.
I have listed steps to reproduce the bug in detail.
Expected Behavior
GIven a Direct Connections config item for an OpenAI compatible API, open webui should response normally.
Actual Behavior
Open webui frontend stucks at waiting. There is a request to fetch models. No request is sent to the specified endpoint /v1/chat/completions. After a while, the request is timed out and the backend returns 400 error.
Steps to Reproduce
Open Firefox
Add a custom OpenAI compatible endpoint
Chat
Logs & Screenshots
Additional Information
No response
Originally created by @Darejkal on GitHub (Mar 5, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11217
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
### Installation Method
Docker
### Open WebUI Version
git-9f27d77
### Ollama Version (if applicable)
_No response_
### Operating System
Bookworm
### Browser (if applicable)
Firefox 128.7.0
### Confirmation
- [x] I have read and followed all instructions in `README.md`.
- [x] I am using the latest version of **both** Open WebUI and Ollama.
- [x] I have checked the browser console logs.
- [x] I have checked the Docker container logs.
- [x] I have listed steps to reproduce the bug in detail.
### Expected Behavior
GIven a Direct Connections config item for an OpenAI compatible API, open webui should response normally.
### Actual Behavior
Open webui frontend stucks at waiting. There is a request to fetch models. No request is sent to the specified endpoint `/v1/chat/completions`. After a while, the request is timed out and the backend returns 400 error.
### Steps to Reproduce
1. Open Firefox
2. Add a custom OpenAI compatible endpoint
3. Chat
### Logs & Screenshots
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-04-19 22:09:36 -05:00
Can you share a screenshot of the network activity in Dev Tools?
Currently I am unable to reproduce this bug using any Adblock extensions and running with SSL and without SSL, but knowing more about the state of your specific setup could help.
<!-- gh-comment-id:2702167546 -->
@atgehrhardt commented on GitHub (Mar 5, 2025):
@Darejkal can you share a few more details:
1. Are you using SSL?
2. Are you using any Adblock extensions?
3. Can you share a screenshot of the network activity in Dev Tools?
Currently I am unable to reproduce this bug using any Adblock extensions and running with SSL and without SSL, but knowing more about the state of your specific setup could help.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @Darejkal on GitHub (Mar 5, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11217
Check Existing Issues
Installation Method
Docker
Open WebUI Version
git-9f27d77
Ollama Version (if applicable)
No response
Operating System
Bookworm
Browser (if applicable)
Firefox 128.7.0
Confirmation
README.md.Expected Behavior
GIven a Direct Connections config item for an OpenAI compatible API, open webui should response normally.
Actual Behavior
Open webui frontend stucks at waiting. There is a request to fetch models. No request is sent to the specified endpoint
/v1/chat/completions. After a while, the request is timed out and the backend returns 400 error.Steps to Reproduce
Logs & Screenshots
Additional Information
No response
@atgehrhardt commented on GitHub (Mar 5, 2025):
@Darejkal can you share a few more details:
Currently I am unable to reproduce this bug using any Adblock extensions and running with SSL and without SSL, but knowing more about the state of your specific setup could help.