I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Git Clone
Open WebUI Version
0.6.10
Ollama Version (if applicable)
No response
Operating System
macOS Sonoma (15.5) - Running on Docker
Browser (if applicable)
Arc (Chromium based) as well as Chrome Version 136.0.7103.114
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 included the browser console logs.
I have included the Docker container logs.
I have listed steps to reproduce the bug in detail.
Expected Behavior
When adding a Langdock API (officially supporting OpenAI API) as a tool server in Open WebUI, it should connect and respond correctly when the model is selected and queried. If the connection is disabled in settings, it should be either hidden or disabled.
Actual Behavior
When clicking the load button (circular arrows) for Langdock API, I get the error:
404: Open WebUI: Server Connection Error
Similarly, when specifying a model and asking questions, the same 404 error appears. The browser shows:
Unexpected error: HTTP Error: 404
This happens despite:
Using the same API key as a friend who successfully runs Langdock on their Open WebUI setup.
Generating a new API key with no improvement.
Adding the API via both the admin console and user console.
Curling the Langdock API URL with the API key inside the Docker container works fine.
Accessing the Langdock API via Python script works perfectly with the same key and URL.
Steps to Reproduce
Install Open WebUI 0.6.10 on Docker (macOS 15.5).
Set up Ollama and Gemini API integrations — they work fine.
Add Langdock API integration using the OpenAI-compatible API key and endpoint.
Click the load button (circular arrows) for Langdock API in the UI.
Observe the 404 Server Connection Error both on load and on querying the model.
Originally created by @hajiabadi-finbridge on GitHub (May 21, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14118
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Git Clone
### Open WebUI Version
0.6.10
### Ollama Version (if applicable)
_No response_
### Operating System
macOS Sonoma (15.5) - Running on Docker
### Browser (if applicable)
Arc (Chromium based) as well as Chrome Version 136.0.7103.114
### 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 included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have listed steps to reproduce the bug in detail.
### Expected Behavior
When adding a Langdock API (officially supporting OpenAI API) as a tool server in Open WebUI, it should connect and respond correctly when the model is selected and queried. If the connection is disabled in settings, it should be either hidden or disabled.
### Actual Behavior
When clicking the load button (circular arrows) for Langdock API, I get the error:
```
404: Open WebUI: Server Connection Error
```
Similarly, when specifying a model and asking questions, the same 404 error appears. The browser shows:
```
Unexpected error: HTTP Error: 404
```
This happens despite:
* Using the same API key as a friend who successfully runs Langdock on their Open WebUI setup.
* Generating a new API key with no improvement.
* Adding the API via both the admin console and user console.
* Curling the Langdock API URL with the API key inside the Docker container works fine.
* Accessing the Langdock API via Python script works perfectly with the same key and URL.
### Steps to Reproduce
1. Install Open WebUI 0.6.10 on Docker (macOS 15.5).
2. Set up Ollama and Gemini API integrations — they work fine.
3. Add Langdock API integration using the OpenAI-compatible API key and endpoint.
4. Click the load button (circular arrows) for Langdock API in the UI.
5. Observe the 404 Server Connection Error both on load and on querying the model.
### Logs & Screenshots
Browser Logs:
Docker Logs:
[docker_logs.txt](https://github.com/user-attachments/files/20361741/docker_logs.txt)
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-05-05 18:06:43 -05:00
@hajiabadi-finbridge commented on GitHub (May 21, 2025):
fixed it by myself. apparently the link reference was wrong. instead of https://api.langdock.com/openai/eu/v1/chat/completionsone only needs https://api.langdock.com/openai/eu/v1
<!-- gh-comment-id:2896853797 -->
@hajiabadi-finbridge commented on GitHub (May 21, 2025):
fixed it by myself. apparently the link reference was wrong. instead of `https://api.langdock.com/openai/eu/v1/chat/completions`one only needs `https://api.langdock.com/openai/eu/v1`
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 @hajiabadi-finbridge on GitHub (May 21, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14118
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
0.6.10
Ollama Version (if applicable)
No response
Operating System
macOS Sonoma (15.5) - Running on Docker
Browser (if applicable)
Arc (Chromium based) as well as Chrome Version 136.0.7103.114
Confirmation
README.md.Expected Behavior
When adding a Langdock API (officially supporting OpenAI API) as a tool server in Open WebUI, it should connect and respond correctly when the model is selected and queried. If the connection is disabled in settings, it should be either hidden or disabled.
Actual Behavior
When clicking the load button (circular arrows) for Langdock API, I get the error:
Similarly, when specifying a model and asking questions, the same 404 error appears. The browser shows:
This happens despite:
Steps to Reproduce
Logs & Screenshots
Browser Logs:
Docker Logs:
docker_logs.txt
Additional Information
No response
@hajiabadi-finbridge commented on GitHub (May 21, 2025):
fixed it by myself. apparently the link reference was wrong. instead of
https://api.langdock.com/openai/eu/v1/chat/completionsone only needshttps://api.langdock.com/openai/eu/v1