github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-30 17:11:20 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #24052] issue: I have two ollama servers as connections, models only shows models from the first connection; not the second #123479

New Issue
Closed
opened 2026-05-21 02:46:50 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-21 02:46:50 -05:00
Owner
Copy Link
Copy Source

Originally created by @misterjice on GitHub (Apr 23, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/24052

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.9.1

Ollama Version (if applicable)

ollama version is 0.21.1

Operating System

Windows 11 / WSL

Browser (if applicable)

Vivaldi 7.9.3970.55 (Official Build) (64-bit)

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 provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

I have two connections under Admin Panel --> Settings --> Connections: these are both local ollama instances. They both work. When I do inference I see both servers via SSH and I see that models are pulled.

When I go to Admin Panel --> Settings --> Models I expect to see models from BOTH local ollama servers.

Actual Behavior

However, when I go to Admin Panel --> Settings --> Models, it only shows models for the first server connection in Admin Panel --> Settings --> Connections and not the second.

Steps to Reproduce

  1. Set up two local ollama connections in Admin Panel --> Settings --> Connections
  2. Test that they work on each server using watch -n 1 ollama ps and see the model called and working.
  3. Confirm inference and rag in OpenWebUI itself (YAY! both connections work!)
  4. Go to Admin Panel --> Settings --> Models to fine tune advanced parameters.
  5. BOOO, only models from the first server show and not the second!

Logs & Screenshots

N/A

Additional Information

N/A

Originally created by @misterjice on GitHub (Apr 23, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/24052 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!). - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.9.1 ### Ollama Version (if applicable) ollama version is 0.21.1 ### Operating System Windows 11 / WSL ### Browser (if applicable) Vivaldi 7.9.3970.55 (Official Build) (64-bit) ### 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 **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior I have two connections under Admin Panel --> Settings --> Connections: these are both local ollama instances. They both work. When I do inference I see both servers via SSH and I see that models are pulled. When I go to Admin Panel --> Settings --> Models I expect to see models from BOTH local ollama servers. ### Actual Behavior However, when I go to Admin Panel --> Settings --> Models, it only shows models for the first server connection in Admin Panel --> Settings --> Connections and not the second. ### Steps to Reproduce 1. Set up two local ollama connections in Admin Panel --> Settings --> Connections 2. Test that they work on each server using watch -n 1 ollama ps and see the model called and working. 3. Confirm inference and rag in OpenWebUI itself (YAY! both connections work!) 4. Go to Admin Panel --> Settings --> Models to fine tune advanced parameters. 5. BOOO, only models from the first server show and not the second! ### Logs & Screenshots N/A ### Additional Information N/A
GiteaMirror added the bug label 2026-05-21 02:46:50 -05:00
GiteaMirror commented 2026-05-21 02:46:54 -05:00
Author
Owner
Copy Link
Copy Source

@mmb78 commented on GitHub (Apr 24, 2026):

I had a similar problem. But I realized that I had the same models served by both Ollama servers and the lists were only merging into one list and I could not see the models "twice". When I later changed my servers to serve different models, everything worked as expected and I saw models from both servers.

<!-- gh-comment-id:4311095354 --> @mmb78 commented on GitHub (Apr 24, 2026): I had a similar problem. But I realized that I had the same models served by both Ollama servers and the lists were only merging into one list and I could not see the models "twice". When I later changed my servers to serve different models, everything worked as expected and I saw models from both servers.
GiteaMirror commented 2026-05-21 02:46:54 -05:00
Author
Owner
Copy Link
Copy Source

@tjbck commented on GitHub (Apr 24, 2026):

Intended behaviour, please set prefix id.

<!-- gh-comment-id:4311404423 --> @tjbck commented on GitHub (Apr 24, 2026): Intended behaviour, please set prefix id.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No labels bug
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#123479