Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #1681] [BUG]: Unable to Connect to LMStudio From AnythingLLM on openSUSE Tumbleweed using either AppImage or Docker #1097

New Issue
Closed
opened 2026-02-22 18:23:06 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:23:06 -05:00
Owner
Copy Link
Copy Source

Originally created by @richardstevenhack on GitHub (Jun 13, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1681

How are you running AnythingLLM?

Docker (local)

What happened?

First encountered the problem using the AppImage. Since the AppImage also had the SSL issue, I switched to the Docker version.
Installed the Docker version using the commands specified in the AnythingLLM docs. That worked fine, can run AnythingLLM, it comes up in Firefox, no problem.
I selected LMStudio as the LM Preference.
I set the LMStudio Base URL to: http://172.17.0.1:1234/v1/chat/completions. I used 172.17.0.1 because the AnythingLLM docs says that docker.internal.host does not work on Linux and that 172.17.0.1 was the correct setting. I also tried with: http://172.17.0.1:1234/v1 which saves successfully but does not work either.
The LM Preference says "loading available models" but there is no model shown even though I am running Phi-3-min-4k-instruct-q4-qquf on LMStudio.
If I save the preference anyway, then switch to a workspace and try a chat, I get "connection error." Obviously because no model is loaded in the first place.

Are there known steps to reproduce?

Run LMStudio with a model loaded.
Install the Docker version of AnythingLLM using the commands specified in the AnythingLLM docs.
Select LMStudio as the LM Preference.
Set the LMStudio Base URL to: http://172.17.0.1:1234/v1/chat/completions.
LM Preference says "loading available models" but there is no model shown.
Save the preference.
Switch to a workspace and try a chat,
Get "connection error." (Obviously because no model is loaded in the first place.)

Originally created by @richardstevenhack on GitHub (Jun 13, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1681 ### How are you running AnythingLLM? Docker (local) ### What happened? First encountered the problem using the AppImage. Since the AppImage also had the SSL issue, I switched to the Docker version. Installed the Docker version using the commands specified in the AnythingLLM docs. That worked fine, can run AnythingLLM, it comes up in Firefox, no problem. I selected LMStudio as the LM Preference. I set the LMStudio Base URL to: http://172.17.0.1:1234/v1/chat/completions. I used 172.17.0.1 because the AnythingLLM docs says that docker.internal.host does not work on Linux and that 172.17.0.1 was the correct setting. I also tried with: http://172.17.0.1:1234/v1 which saves successfully but does not work either. The LM Preference says "loading available models" but there is no model shown even though I am running Phi-3-min-4k-instruct-q4-qquf on LMStudio. If I save the preference anyway, then switch to a workspace and try a chat, I get "connection error." Obviously because no model is loaded in the first place. ### Are there known steps to reproduce? Run LMStudio with a model loaded. Install the Docker version of AnythingLLM using the commands specified in the AnythingLLM docs. Select LMStudio as the LM Preference. Set the LMStudio Base URL to: http://172.17.0.1:1234/v1/chat/completions. LM Preference says "loading available models" but there is no model shown. Save the preference. Switch to a workspace and try a chat, Get "connection error." (Obviously because no model is loaded in the first place.)
yindo added the possible bug label 2026-02-22 18:23:06 -05:00
yindo closed this issue 2026-02-22 18:23:06 -05:00
yindo commented 2026-02-22 18:23:07 -05:00
Author
Owner
Copy Link
Copy Source

@richardstevenhack commented on GitHub (Jun 13, 2024):

OK, I got it working! First, I forgot to turn on the server in LMStudio (not surprising since I hadn't tried connecting to LMStudio from outside it before.) Then I changed the LMStudio Base URL in both the Docker versions of AnythingLLM to http://172.17.0.1:1234/v1 and the AppImage version to http://localhost:1234/v1. Now it can see and load my Phi 3 model. So the problem is resolved.

@richardstevenhack commented on GitHub (Jun 13, 2024): OK, I got it working! First, I forgot to turn on the server in LMStudio (not surprising since I hadn't tried connecting to LMStudio from outside it before.) Then I changed the LMStudio Base URL in both the Docker versions of AnythingLLM to http://172.17.0.1:1234/v1 and the AppImage version to http://localhost:1234/v1. Now it can see and load my Phi 3 model. So the problem is resolved.
yindo changed title from [BUG]: Unable to Connect to LMStudio From AnythingLLM on openSUSE Tumbleweed using either AppImage or Docker to [GH-ISSUE #1681] [BUG]: Unable to Connect to LMStudio From AnythingLLM on openSUSE Tumbleweed using either AppImage or Docker 2026-06-05 14:38:58 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label possible bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1097
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?