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 #4854] [BUG]: #3059

New Issue
Closed
opened 2026-02-22 18:32:27 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:32:27 -05:00
Owner
Copy Link
Copy Source

Originally created by @franztaussig-rgb on GitHub (Jan 11, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4854

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

Description

AnythingLLM Desktop consistently terminates all Ollama API requests after exactly 5 minutes with an HTTP 500 error, regardless of configuration attempts.

Environment

  • OS: Antix Linux (init-based, no systemd)
  • AnythingLLM Version: 1.9.1 (Desktop AppImage)
  • Ollama Version: 0.13.5
  • Ollama Host: 127.0.0.1:11434 (local)

Steps to Reproduce

  1. Start a chat request that requires >5 minutes to process
  2. Observe the request failing at exactly the 5-minute mark

Log Output

[GIN] 2026/01/11 - 08:21:56 | 500 | 5m0s | 127.0.0.1 | POST "/api/chat"

What I've Tried

All attempts to increase the timeout have failed:

Ollama Configuration (confirmed working)

  • ✅ OLLAMA_KEEP_ALIVE=24h - verified in Ollama server config
  • ✅ OLLAMA_LOAD_TIMEOUT=15m - verified in Ollama server config
  • ✅ Direct curl requests to Ollama work beyond 5 minutes

AnythingLLM Configuration Attempts

  • ❌ Environment variables at AppImage launch: LLM_TIMEOUT=900000, REQUEST_TIMEOUT=900000, OLLAMA_TIMEOUT=900000
  • ❌ Modified Ollama base URL to use a socat proxy with extended timeout (-T600)
  • ❌ Searched AppImage contents (app.asar, backend/server.js, dist-electron/) - no configurable timeout found

Expected Behavior

Timeout should be configurable or at least respect longer timeouts (15+ minutes) for complex requests.

Actual Behavior

All requests terminate at exactly 300 seconds (5 minutes) regardless of configuration.

Additional Context

The 5-minute timeout appears to be hard-coded somewhere in the Electron app or backend, likely in:

  • The Ollama provider implementation
  • An HTTP client configuration (axios/fetch)
  • IPC communication between frontend and backend

This makes AnythingLLM unusable for longer-running tasks with local models.

Possible Solution

Add a user-configurable timeout setting in the UI or .env file, or increase the default to at least 15-30 minutes for LLM providers.

Are there known steps to reproduce?

No response

Originally created by @franztaussig-rgb on GitHub (Jan 11, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4854 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? ## Description AnythingLLM Desktop consistently terminates all Ollama API requests after exactly 5 minutes with an HTTP 500 error, regardless of configuration attempts. ## Environment - **OS:** Antix Linux (init-based, no systemd) - **AnythingLLM Version:** 1.9.1 (Desktop AppImage) - **Ollama Version:** 0.13.5 - **Ollama Host:** 127.0.0.1:11434 (local) ## Steps to Reproduce 1. Start a chat request that requires >5 minutes to process 2. Observe the request failing at exactly the 5-minute mark ## Log Output ``` [GIN] 2026/01/11 - 08:21:56 | 500 | 5m0s | 127.0.0.1 | POST "/api/chat" ``` ## What I've Tried All attempts to increase the timeout have failed: ### Ollama Configuration (confirmed working) - ✅ `OLLAMA_KEEP_ALIVE=24h` - verified in Ollama server config - ✅ `OLLAMA_LOAD_TIMEOUT=15m` - verified in Ollama server config - ✅ Direct `curl` requests to Ollama work beyond 5 minutes ### AnythingLLM Configuration Attempts - ❌ Environment variables at AppImage launch: `LLM_TIMEOUT=900000`, `REQUEST_TIMEOUT=900000`, `OLLAMA_TIMEOUT=900000` - ❌ Modified Ollama base URL to use a `socat` proxy with extended timeout (`-T600`) - ❌ Searched AppImage contents (`app.asar`, `backend/server.js`, `dist-electron/`) - no configurable timeout found ## Expected Behavior Timeout should be configurable or at least respect longer timeouts (15+ minutes) for complex requests. ## Actual Behavior All requests terminate at exactly 300 seconds (5 minutes) regardless of configuration. ## Additional Context The 5-minute timeout appears to be hard-coded somewhere in the Electron app or backend, likely in: - The Ollama provider implementation - An HTTP client configuration (axios/fetch) - IPC communication between frontend and backend This makes AnythingLLM unusable for longer-running tasks with local models. ## Possible Solution Add a user-configurable timeout setting in the UI or `.env` file, or increase the default to at least 15-30 minutes for LLM providers. ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:32:27 -05:00
yindo closed this issue 2026-02-22 18:32:27 -05:00
yindo commented 2026-02-22 18:32:27 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jan 12, 2026):

The 5-minute timeout appears to be hard-coded somewhere in the Electron app or backend, likely in:

The default NodeJS timeout is exactly 300 seconds. We added an ENV control for this
https://github.com/Mintplex-Labs/anything-llm/blob/7c3b7906e798314a4aeb5be38b42a1a29599e381/server/utils/AiProviders/ollama/index.js#L137

This ENV (you can set by editing the desktop storage .env manually) will persist this value so you dont get timeouts or at least get them within your personal expectations. Being able to set this from the UI is an improvement we should consider though.

@timothycarambat commented on GitHub (Jan 12, 2026): > The 5-minute timeout appears to be hard-coded somewhere in the Electron app or backend, likely in: The default NodeJS timeout is exactly 300 seconds. We added an ENV control for this https://github.com/Mintplex-Labs/anything-llm/blob/7c3b7906e798314a4aeb5be38b42a1a29599e381/server/utils/AiProviders/ollama/index.js#L137 This ENV (you can set by editing the desktop storage .env manually) will persist this value so you dont get timeouts or at least get them within your personal expectations. Being able to set this from the UI is an improvement we should consider though.
yindo changed title from [BUG]: to [GH-ISSUE #4854] [BUG]: 2026-06-05 14:50:04 -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#3059
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?