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 #4013] [BUG]: #2553

New Issue
Closed
opened 2026-02-22 18:30:11 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:30:11 -05:00
Owner
Copy Link
Copy Source

Originally created by @AI-Testing-LLM on GitHub (Jun 17, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4013

How are you running AnythingLLM?

Docker (local)

What happened?

I have successfully run anythingLLM on the docker environment. Everything seems to work. However, I get an error when I connect to my own local LLM which runs on Ollama.

I do not get this error with the Windows desktop version. On Winows all words fine , So my backend Ollama is in principle ok. If I choose http://192.168.134.28:3001/onboarding/llm-preference via the web browser and connect the Ollama server Ollama base url: http://192.168.134.30:11434 then the Ollama Model"s are recognized but I get the following error:

Failed to save LLM Settings
network error when attempting to fetch resource

What could be wrong here?

Are there known steps to reproduce?

No response

Originally created by @AI-Testing-LLM on GitHub (Jun 17, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4013 ### How are you running AnythingLLM? Docker (local) ### What happened? I have successfully run anythingLLM on the docker environment. Everything seems to work. However, I get an error when I connect to my own local LLM which runs on Ollama. I do not get this error with the Windows desktop version. On Winows all words fine , So my backend Ollama is in principle ok. If I choose http://192.168.134.28:3001/onboarding/llm-preference via the web browser and connect the Ollama server Ollama base url: http://192.168.134.30:11434 then the Ollama Model"s are recognized but I get the following error: Failed to save LLM Settings network error when attempting to fetch resource What could be wrong here? ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:30:11 -05:00
yindo closed this issue 2026-02-22 18:30:11 -05:00
yindo commented 2026-02-22 18:30:11 -05:00
Author
Owner
Copy Link
Copy Source

@AI-Testing-LLM commented on GitHub (Jun 17, 2025):

Image

But i got this error when i got to next setup screen ..

@AI-Testing-LLM commented on GitHub (Jun 17, 2025): ![Image](https://github.com/user-attachments/assets/4a7097cf-fe7e-4240-b8e7-9e1e6c56aeea) But i got this error when i got to next setup screen ..
yindo commented 2026-02-22 18:30:11 -05:00
Author
Owner
Copy Link
Copy Source

@shatfield4 commented on GitHub (Jun 18, 2025):

The issue you are running into here can be solved with this: https://docs.anythingllm.com/installation-docker/localhost

When connecting to Ollama via docker you need to use the host.docker.internal instead of your IP address. So for this instance you would use http://host.docker.internal:11434 as you Ollama URL and this should fix your issue.

@shatfield4 commented on GitHub (Jun 18, 2025): The issue you are running into here can be solved with this: https://docs.anythingllm.com/installation-docker/localhost When connecting to Ollama via docker you need to use the `host.docker.internal` instead of your IP address. So for this instance you would use **http://host.docker.internal:11434** as you Ollama URL and this should fix your issue.
yindo commented 2026-02-22 18:30:11 -05:00
Author
Owner
Copy Link
Copy Source

@AI-Testing-LLM commented on GitHub (Jun 19, 2025):

The issue you are running into here can be solved with this: https://docs.anythingllm.com/installation-docker/localhost

When connecting to Ollama via docker you need to use the host.docker.internal instead of your IP address. So for this instance you would use http://host.docker.internal:11434 as you Ollama URL and this should fix your issue.

This seems strange. Why? Because my Ollama LLm is not running in the anythingllm docker but on a second server so external. And the anything windows desktop version can connect to it without any problems. And everything works.

If I would use the host.docker.internal then it seems to me that the anythingllm docker can never find the second external server. Because this one runs externally host.docker.internal is the own anythingllm docker.

Or do you mean this differently? Do you understand what I mean? So I have 2 servers 1. anythingllm docker 2. an Ollama LLm server. If you mean this differently please let me know.

Or do I understand this wrong? Thanks for your quick response

@AI-Testing-LLM commented on GitHub (Jun 19, 2025): > The issue you are running into here can be solved with this: https://docs.anythingllm.com/installation-docker/localhost > > When connecting to Ollama via docker you need to use the `host.docker.internal` instead of your IP address. So for this instance you would use **http://host.docker.internal:11434** as you Ollama URL and this should fix your issue. This seems strange. Why? Because my Ollama LLm is not running in the anythingllm docker but on a second server so external. And the anything windows desktop version can connect to it without any problems. And everything works. If I would use the host.docker.internal then it seems to me that the anythingllm docker can never find the second external server. Because this one runs externally host.docker.internal is the own anythingllm docker. Or do you mean this differently? Do you understand what I mean? So I have 2 servers 1. anythingllm docker 2. an Ollama LLm server. If you mean this differently please let me know. Or do I understand this wrong? Thanks for your quick response
yindo changed title from [BUG]: to [GH-ISSUE #4013] [BUG]: 2026-06-05 14:47:12 -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#2553
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?