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 #4506] [BUG]: AnythingLLM stuck on infinite loading (Windows, Ollama installed, no workspace data) #2867

New Issue
Closed
opened 2026-02-22 18:31:35 -05:00 by yindo · 4 comments
yindo commented 2026-02-22 18:31:35 -05:00
Owner
Copy Link
Copy Source

Originally created by @ElyasKing on GitHub (Oct 7, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4506

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

Describe the bug
After a fresh install of AnythingLLM on Windows (x64), the app takes an extremely long time to finish loading. It stays on the Loading screen for several minutes before finally showing the interface. Ollama is installed and working correctly (ollama ps and ollama --version both work fine), but the startup time makes the app basically unusable.

System information

  • OS: Windows 11 Pro x64 (Ryzen 9 5950X, 32 GB RAM, RTX 3090)
  • AnythingLLM version: 1.8.5-r2 (Windows x64 build)
  • Ollama version: 0.3.12
  • Ollama models installed: llama3, llama3.2:11b
  • GPU Acceleration: Enabled (CUDA)
  • No workspace or files added yet
Image

Are there known steps to reproduce?

To Reproduce
Steps to reproduce the behavior:

  1. Install AnythingLLM for Windows (x64)
  2. Launch the app (GUI, not via CLI)
  3. Wait for the main interface to load
  4. Observe that the UI keeps spinning forever
Originally created by @ElyasKing on GitHub (Oct 7, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4506 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? **Describe the bug** After a fresh install of AnythingLLM on Windows (x64), the app takes an extremely long time to finish loading. It stays on the Loading screen for several minutes before finally showing the interface. Ollama is installed and working correctly (ollama ps and ollama --version both work fine), but the startup time makes the app basically unusable. **System information** * OS: Windows 11 Pro x64 (Ryzen 9 5950X, 32 GB RAM, RTX 3090) * AnythingLLM version: 1.8.5-r2 (Windows x64 build) * Ollama version: 0.3.12 * Ollama models installed: `llama3`, `llama3.2:11b` * GPU Acceleration: Enabled (CUDA) * No workspace or files added yet <img width="1155" height="653" alt="Image" src="https://github.com/user-attachments/assets/70396538-bcee-419e-9a70-d0adcf680022" /> ### Are there known steps to reproduce? **To Reproduce** Steps to reproduce the behavior: 1. Install AnythingLLM for Windows (x64) 2. Launch the app (GUI, not via CLI) 3. Wait for the main interface to load 4. Observe that the UI keeps spinning forever
yindo added the possible bug label 2026-02-22 18:31:35 -05:00
yindo closed this issue 2026-02-22 18:31:35 -05:00
yindo commented 2026-02-22 18:31:35 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Oct 7, 2025):

Close the app and re-open. Also does this machine have an internet connection? Sometimes the prisma binary needs to be pulled, resulting in this indefinite state.

Lastly you can launch the app with more debugging via terminal. Just open terminal and drag and drop the exe into that window and press enter. You will see more output you can post here.

@timothycarambat commented on GitHub (Oct 7, 2025): Close the app and re-open. Also does this machine have an internet connection? Sometimes the prisma binary needs to be pulled, resulting in this indefinite state. Lastly you can launch the app with more debugging via terminal. Just open terminal and drag and drop the exe into that window and press enter. You will see more output you can post here.
yindo commented 2026-02-22 18:31:35 -05:00
Author
Owner
Copy Link
Copy Source

@ElyasKing commented on GitHub (Oct 8, 2025):

Hi, thanks for your reply. I tried your suggestions, but the issue still persists.

Here’s what I observed:

  • AnythingLLM takes several minutes to load or stays indefinitely on the "Loading..." screen.

  • I confirmed the PC is online and has no firewall restriction.

  • Ollama is correctly installed and working:

    • ollama serve runs fine on 127.0.0.1:11434
    • ollama ps and ollama --version both return valid output

  • However, in the AnythingLLM debug logs, I see this repeating message:

    [OllamaProcessManager] [windows] Ollama subprocess running. Port 53xxx. PID xxxxx.
[backend] info: OllamaAPI offline - retrying. 1/3

It looks like the app is not connecting to my existing Ollama service, or maybe it’s starting its own instance internally — I’m not sure.
I couldn’t find any clear .env or config setting that explicitly controls that behavior.

I tried the following:

  1. Clean reinstall (removed all folders under %appdata%\anythingllm-* and reinstalled AnythingLLM x64).
  2. Manually started Ollama before launching AnythingLLM.
  3. Verified Prisma client logs — no migration issues detected.

The app backend initializes fine and Prisma syncs correctly, but the UI remains stuck until it times out after several minutes.

System info:

  • Windows 11 Pro x64 (Ryzen 9 5950X / RTX 3090 / 32 GB RAM)
  • AnythingLLM 1.8.5-r2
  • Ollama 0.12.3
  • Models: llama3, llama3.2:11b
  • GPU Acceleration (CUDA): Enabled

It looks like a bug where the app ignores an external Ollama instance and loops trying to reach its internal process.
Do you know if there’s a flag or environment variable to force AnythingLLM to skip the internal Ollama startup entirely?

@ElyasKing commented on GitHub (Oct 8, 2025): Hi, thanks for your reply. I tried your suggestions, but the issue still persists. Here’s what I observed: * AnythingLLM takes several minutes to load or stays indefinitely on the "Loading..." screen. * I confirmed the PC is online and has no firewall restriction. * Ollama is correctly installed and working: * `ollama serve` runs fine on `127.0.0.1:11434` * `ollama ps` and `ollama --version` both return valid output * However, in the AnythingLLM debug logs, I see this repeating message: ``` [OllamaProcessManager] [windows] Ollama subprocess running. Port 53xxx. PID xxxxx. [backend] info: OllamaAPI offline - retrying. 1/3 ``` It looks like the app is not connecting to my existing Ollama service, or maybe it’s starting its own instance internally — I’m not sure. I couldn’t find any clear .env or config setting that explicitly controls that behavior. I tried the following: 1. Clean reinstall (removed all folders under `%appdata%\anythingllm-*` and reinstalled AnythingLLM x64). 2. Manually started Ollama before launching AnythingLLM. 3. Verified Prisma client logs — no migration issues detected. The app backend initializes fine and Prisma syncs correctly, but the UI remains stuck until it times out after several minutes. System info: * Windows 11 Pro x64 (Ryzen 9 5950X / RTX 3090 / 32 GB RAM) * AnythingLLM 1.8.5-r2 * Ollama 0.12.3 * Models: `llama3`, `llama3.2:11b` * GPU Acceleration (CUDA): Enabled It looks like a bug where the app ignores an external Ollama instance and loops trying to reach its internal process. Do you know if there’s a flag or environment variable to force AnythingLLM to skip the internal Ollama startup entirely?
yindo commented 2026-02-22 18:31:36 -05:00
Author
Owner
Copy Link
Copy Source

@ElyasKing commented on GitHub (Oct 21, 2025):

ok @timothycarambat Have I to open new issue ?

@ElyasKing commented on GitHub (Oct 21, 2025): ok @timothycarambat Have I to open new issue ?
yindo commented 2026-02-22 18:31:36 -05:00
Author
Owner
Copy Link
Copy Source

@ElyasKing commented on GitHub (Oct 28, 2025):

hi @timothycarambat ?

@ElyasKing commented on GitHub (Oct 28, 2025): hi @timothycarambat ?
yindo changed title from [BUG]: AnythingLLM stuck on infinite loading (Windows, Ollama installed, no workspace data) to [GH-ISSUE #4506] [BUG]: AnythingLLM stuck on infinite loading (Windows, Ollama installed, no workspace data) 2026-06-05 14:48:58 -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#2867
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?