Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #1003] [BUG]: AnythingLLM desktop app fails to connect to running binary LocalAI instance #616

New Issue
Closed
opened 2026-02-22 18:20:29 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:20:29 -05:00
Owner
Copy Link
Copy Source

Originally created by @lebedov on GitHub (Apr 1, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1003

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

I'm running LocalAI 2.10.1 locally built as a binary (i.e., not in a Docker image) on an Intel MacBook running MacOS 14.4.1. I can query the running instance via curl (e.g., curl http://localhost:8080/v1/models lists the luna-ai-llama2 model I have stored in the instance's model storage folder), but AnythingLLM doesn't seem to be able to access that instance to let me choose an available model when I select LocalAI on the LLM Preference screen (and if I run the LocalAI instance with the --debug flag, I don't see the app ever make a GET call to the instance when I navigate the the LLM Preference screen and select LocalAI).

Are there known steps to reproduce?

  • Install AnythingLLM 1.4.1 on an Intel MacBook running MacOS 14.4.1.
  • Clone LocalAI 2.10.1 and build on the same system.
  • While in the LocalAI source repo folder, download and install luna-ai-llama2 using wget https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGUF/resolve/main/luna-ai-llama2-uncensored.Q4_0.gguf -O models/luna-ai-llama2
  • Start LocalAI by running the local-ai binary in the above folder.
  • Verify that one can see the saved model by running curl http://localhost:8080/v1/models (which should return something like {"object":"list","data":[{"id":"luna-ai-llama2","object":"model"}]}).
  • Start the AnythingLLM desktop app, navigate to the LLM Preference screen, select LocalAI from the LLM Providers menu, and try to select a model from the Chat Model Selection dropdown menu; the menu will not open.
Originally created by @lebedov on GitHub (Apr 1, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1003 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? I'm running LocalAI 2.10.1 locally built as a binary (i.e., not in a Docker image) on an Intel MacBook running MacOS 14.4.1. I can query the running instance via curl (e.g., `curl http://localhost:8080/v1/models` lists the luna-ai-llama2 model I have stored in the instance's model storage folder), but AnythingLLM doesn't seem to be able to access that instance to let me choose an available model when I select LocalAI on the LLM Preference screen (and if I run the LocalAI instance with the --debug flag, I don't see the app ever make a GET call to the instance when I navigate the the LLM Preference screen and select LocalAI). ### Are there known steps to reproduce? - Install AnythingLLM 1.4.1 on an Intel MacBook running MacOS 14.4.1. - Clone LocalAI 2.10.1 and build on the same system. - While in the LocalAI source repo folder, download and install luna-ai-llama2 using `wget https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGUF/resolve/main/luna-ai-llama2-uncensored.Q4_0.gguf -O models/luna-ai-llama2` - Start LocalAI by running the local-ai binary in the above folder. - Verify that one can see the saved model by running `curl http://localhost:8080/v1/models` (which should return something like `{"object":"list","data":[{"id":"luna-ai-llama2","object":"model"}]}`). - Start the AnythingLLM desktop app, navigate to the LLM Preference screen, select LocalAI from the LLM Providers menu, and try to select a model from the Chat Model Selection dropdown menu; the menu will not open.
yindo added the wontfixIntegration RequestOS: Linux labels 2026-02-22 18:20:29 -05:00
yindo closed this issue 2026-02-22 18:20:29 -05:00
yindo commented 2026-02-22 18:20:29 -05:00
Author
Owner
Copy Link
Copy Source

@lebedov commented on GitHub (Apr 1, 2024):

When I tried changing the endpoint from the default http://localhost:8080/v1 to http://127.0.0.1/v1, the app was able to make a GET call to the LocalAI instance and list the saved luna-ai-llama2 model. The fact that the default didn't work seems like a bug.

@lebedov commented on GitHub (Apr 1, 2024): When I tried changing the endpoint from the default http://localhost:8080/v1 to http://127.0.0.1/v1, the app was able to make a GET call to the LocalAI instance and list the saved luna-ai-llama2 model. The fact that the default didn't work seems like a bug.
yindo commented 2026-02-22 18:20:29 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 1, 2024):

This is certainly some kind of networking layer resolution on your OS, likely related to it being linux based so somehow localhost does not seem to connect or map to 127.0.0.1. Informative but will mark as wonfix for the time being,

@timothycarambat commented on GitHub (Apr 1, 2024): This is certainly some kind of networking layer resolution on your OS, likely related to it being linux based so somehow localhost does not seem to connect or map to 127.0.0.1. Informative but will mark as wonfix for the time being,
yindo commented 2026-02-22 18:20:29 -05:00
Author
Owner
Copy Link
Copy Source

@lebedov commented on GitHub (Apr 1, 2024):

Just to be clear, other apps on my laptop such as curl, wget, Firefox, etc. can resolve localhost to 127.0.0.1 with no problems, so I'm not sure this is due to name resolution issues.

@lebedov commented on GitHub (Apr 1, 2024): Just to be clear, other apps on my laptop such as curl, wget, Firefox, etc. can resolve localhost to 127.0.0.1 with no problems, so I'm not sure this is due to name resolution issues.
yindo changed title from [BUG]: AnythingLLM desktop app fails to connect to running binary LocalAI instance to [GH-ISSUE #1003] [BUG]: AnythingLLM desktop app fails to connect to running binary LocalAI instance 2026-06-05 14:36:18 -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 Integration Request OS: Linux wontfix
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#616
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?