mirror of
https://github.com/Mintplex-Labs/anything-llm.git
synced 2026-07-19 14:13:35 -04:00
Closed
opened 2026-02-22 18:19:51 -05:00 by yindo
·
29 comments
No Branch/Tag Specified
master
5846-bug-when-scrolling-up-scrolling-jumps
refactor-remove-workspace-pfp
5969-bug-stopgenerationbutton-disappears-on-the-first-prompt-that-initiates-an-agent-session
2235-bug-how-to-upload-a-folder-with-subfolders-with-files-to-anythingllm
5990-workspace-update-fails-with-unknown-argument-router_id-v1130v1150-intel-mac
opencomputer-examples
pg
feat/image-generation-translations
feat/image-generation
5924-bug-meeting-summary-fails-with-sincludes-is-not-a-function-when-default-llm-is-anthropic-claude
render
feat/uniform-modal-component
5883-bug-unescaped-content-in-json-strings-being-passed-to-document-generator-tools
5901-bug-api-update-embeddings-fails-prisma-argument-filename-is-missing-on-workspace_documentscreate-desktop-windows-v1141
hybrid-search
1981-translations
5752-bug-prompts-to-local-jan-endpoint-unresponsive
feat-disable-native-tool-calling-env-var
5676-bug-non-ollama-agent-providers-do-not-parse-and-present-reasoning-content
feat/markdown-web-scraping
5717-bug-apiv1documentupload-silently-drops-metadata-field-in-desktop-1130-arg-count-mismatch-nested-payload-key
fix/aibitat-context-overflow
5711-bug-erratic-deepseek-v4-flash-the-agent-model-failed-to-respond-400-the-reasoning_content
5631-feat-custom-api-request-timeouts-for-ai-providers
feat-reasoning-control
feat-agent-clarifying-questions-translations
5583-bug-lm-studio-provider-does-not-present-reasoning-output
5313-normalize-translations
feat/memory-translations
5305-lemonade-embedding-engine-swallows-errors-falsely-reports-documents-as-embedded
5060-bug-agent-interactions-agent-are-not-persisted-to-thread-history-via-api
pptx-subagent
feat-render-images-from-mcp-tool-results
stt-provider-expansion-openai-api-compatible
feat-file-search-agent-tool
feat-native-embedder-job-queue
5189-normalize-translations
feat-file-search-agent-tool-translations
i18n-eslint
5140-auto-migration
5112-bug-openrouter-failed-message-bug
3506-feat-parameters-for-openrouter-models
4992-feat-preserve-scroll-position
4973-bug-markdown-numbered-list-display-in-reasoning-pane
desktop
4938-bug-pending-chat-rerendering-ui-bug
quickstart-env
node-llama-cpp-in-container-cuda
node-llama-cpp-in-container
ollama-in-container
4817-feat-set-cooldown-per-mcp-server
4845-keyboard-shortcuts-to-navigate-in-chat
4844-feat-reorder-threads-by-latest-interaction
standardize-username-constraints-normalize-translations
4792-feat-refactor-workspacepfp-image
1382-embed-ip-improvements
1382-bug-embed-api-improvements
refactor-eslint-frontend
4687-feat-refactor-vector-db-providers
4615-feat-disable-apidocs-with-environment-variable
4559-feat-agent-web-search-enable-ordering-of-results
4599-bug-ollama-race-condition-bug
4572-bug-lmstudio-provided-llm-stopped-working-with-anything-llm-after-upgrading-to-190
4508-agent-youtube-transcript-analysis
4497-feat-workspace-names
frontend-eslint
ollama-lmstudio-auto-context-window
4431-validate-vector-database-connectioN
2019-slash-command-keyboard-selection
microsoft-foundry-provider
4431-validate-vector-database-connection
4325-sys-prompt-var-improvements
3209-feat-apiv1workspacestream-chat-sources-citations
4210-bug-voice-to-text-overwrite
4136-feat-jan-as-a-backend-server-option
4172-feat-openai-o3-support
1.8.3-rerelease
web-push-notifications-service
tasks
3955-feat-jinaai-embedder-provider-support
3921-feat-agent-skills-uiux-improvements
3901-bug-validfunccall-checks-optional-arguments
keyboard-dev
1787-custom-roles-and-permissions
add-jira-slack-data-connector
office-extension-wip
lightmode-dropdown-color-update
3586-bug-agent-flow-function-description-provided-by-user-is-not-seen-in-the-llm-query
3463-bug-agent-continues-to-run-if-request-failed-even-after-exit
3439-feat-call-variables-within-the-flow-api-block-url-field
3282-manager-view-models-workspace
3280-token-counting-server-side-truncation-improvements
3147-bug-embedded-chat-widget---not-considering-query-mode-option-always-working-in-chat-mode
2995-feat-disable-temperature-setting-for-deepseek-r1-deepseek-reasoner-model
2827-feat-perplexity-citations
2866-feat-finally-a-gemini-models-endpoint
2647-feat-hpp-header-for-a-c++-code-file-mime-addition
lancedb-revert
1656-feat-implement-tooltip-ui-designs
2011-feat-bump-perplexity-models
1873-feat-auto-add-and-watch-folder-for-document-uploads
1297-feat-gemini-agent-support
1759-bug-ui-bug-fixes
1686-feat-implement-winston-for-logging
1536-bug-toggling-on-users-can-delete-workspaces-does-not-take-effect
agent-ui-mobile-styles
1522-feat-chromadb-support
1595-bug-unable-to-get-live-web-search-and-browsing-agent-working-using-google-custom-search-engine-error-getaddrinfo-enotfound-http-errno-3008
1582-bug-lm-studio-does-not-allow-for-different-model-selection
1312-bug-usernames-should-not-be-case-sensitive-when-logging-in
1029-feat-hf-serverless-inference-api
1086-feat-implement-normalized-input-fields
knowledge-graph-support
644-bug-uploaded-file-name-does-not-match-the-displayed-file-name-after-the-upload
v1.15.0
v1.14.2
v1.14.1
v1.14.0
v1.13.0
v1.12.1
v1.12.0
v1.11.2
v1.11.1
v1.11.0
v1.10.0
v1.9.1
v1.9.0
v1.8.5
v1.8.4
v1.8.3
v1.8.2
v1.8.1
v1.8.0
v1.7.8
v1.7.6
v1.7.5
v1.7.4
v1.4.0
v1.3.0
v1.2.4
v1.2.3
v1.2.2
v1.2.1
v1.2.0
v1.1.1
v1.1.0
v1.0.0
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
question
stage: specifications
wontfix
Mirrored from GitHub Pull Request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: Mintplex-Labs/anything-llm#511
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
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?
Originally created by @ub1979 on GitHub (Mar 5, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/866
How are you running AnythingLLM?
AnythingLLM desktop app
What happened?
Are there known steps to reproduce?
No response
@luoluoter commented on GitHub (Mar 6, 2024):
got the same problem like you;
i reinstalled the latest dmg from official website and still not working.
@StephenHnilica commented on GitHub (Mar 6, 2024):
If you uploaded an audio / video file, what's happening is that it's transcribing the file & that takes a while. On my PC it takes ~1m for every 1m of audio.
For some reason it pauses the queuing function while it's working. When the transcription is finished, the document processor will come back online.
You can read my documentation of the issue here: https://github.com/Mintplex-Labs/anything-llm/issues/849
@ub1979 commented on GitHub (Mar 6, 2024):
no its not letting to upload any file from start, like I made the workspace and when I press upload file I got this msg.
I uninstall it and tried , restarted the computer too.
but today when I open it again it was allowing me to upload the file. :) strange I hope it keeps working now
@timothycarambat commented on GitHub (Mar 6, 2024):
@ub1979
What OS are you on for mac?
What chip are you running (intel/M-series)
Can you open the
Terminalapplication and run this - make sure the currently running app is fully quit:/Applications/AnythingLLM.app/Contents/MacOS/AnythingLLM(then press enter)It will start the app like usual but all logs will be dumped to terminal. Can you paste that output into here? We have seen this issue on Windows but never on Mac and it will be easier to debug this way.
If you can do this we can fully squash this issue as others have not been able to provide us these logs and we cannot replicate it on any machine we get our hands on.
@PieroPicc commented on GitHub (Mar 6, 2024):
Hi @timothycarambat I'm having the same issue on M1 Mac, here are the logs:
Seems like a permission issue and a missing Prisma module. Are there any additional steps after installation I might've missed?
@PieroPicc commented on GitHub (Mar 6, 2024):
Solved it, the problem is due to System Integrity Protection (SIP) on macOS. To solve you just need to install it inside the Applications folder of the current user and not in the root application folder.
Hope it helps!
@timothycarambat commented on GitHub (Mar 6, 2024):
@PieroPicc THANK YOU. This is almost certainly the case as well for multi-user Windows systems that are encountering this issue. The app should only be installed as the current user as the global
/Applicationswill fail due to perms.Ping me in Discord if you want a contributor badge, this headache is worthy of one. In the meantime I will see if there is a way to prevent that kind of install error from occuring.
@luoluoter commented on GitHub (Mar 6, 2024):
Terminalrun/Applications/AnythingLLM.app/Contents/MacOS/AnythingLLMis working, for me;don't know how to 'install it inside the Applications folder of the current user and not in the root application folder.',
i only can see ONE application folder, and open in folder or Dock is not working.
@timothycarambat commented on GitHub (Mar 7, 2024):
@luoluoter In Finder click in Go -> "Go to Folder" ->
~/Applicationsand drag the app from the root application folder and into that one. The dock shows both I believe.@timothycarambat commented on GitHub (Mar 8, 2024):
Also related #875 if this does not solve your issue
@dmatora commented on GitHub (Mar 28, 2024):
Same issue on MacOS.
Working fine on Intel MacBook, but getting Document Processor Unavailable on M1
Here is M1 log
Applications/AnythingLLM.app/Contents/MacOS/AnythingLLM
Prisma schema loaded from prisma/schema.prisma
Datasource "db": SQLite database "anythingllm.db" at "file:/Users/Melanj/Library/Application Support/anythingllm-desktop/storage/anythingllm.db"
Already in sync, no schema change or pending migration was found.
✔️ Generated Prisma Client (v5.3.1) to ./node_modules/@prisma/client in 86ms
Prisma schema loaded from prisma/schema.prisma
✔️ Generated Prisma Client (v5.3.1) to ./node_modules/@prisma/client in 89ms
Start using Prisma Client in Node.js (See: https://pris.ly/d/client)
import { PrismaClient } from '@prisma/client'
const prisma = new PrismaClient()
or start using Prisma Client at the edge (See: https://pris.ly/d/accelerate)
import { PrismaClient } from '@prisma/client/edge'
const prisma = new PrismaClient()
See other ways of importing Prisma Client: http://pris.ly/d/importing-client
[OllamaProcessManager] Ollama will bind on port 11434 when booted.
[TELEMETRY ENABLED] Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM.
Collector hot directory and tmp storage wiped!
[production] AnythingLLM Standalone Document processor listening on port 8888
prisma:info Starting a sqlite pool with 17 connections.
[TELEMETRY SENT] {
event: 'server_boot',
distinctId: '...',
properties: { runtime: 'desktop' }
}
Skipping preloading of AnythingLLMOllama - LLM_PROVIDER is lmstudio.
[production] AnythingLLM Standalone Backend listening on port 3001
@timothycarambat commented on GitHub (Mar 28, 2024):
Its been pointed out before that moving the App from /Applications to /User/Applications will solve this. This may be the issue
@dmatora commented on GitHub (Mar 29, 2024):
@timothycarambat just tried that, but it did not not help
@moltar commented on GitHub (Apr 2, 2024):
same prob on the hosted trial
@timothycarambat commented on GitHub (Apr 2, 2024):
Then you should email team@mintplexlabs.com with your domain or reboot the instance. That should never be the case on hosted. Likely crashed from uploading something
@monokrome commented on GitHub (Mar 19, 2025):
If it ever did, it seems like copying to $HOME/Applications doesn't solve this any more. Same error reports as previously provided here.
@dirtstudio commented on GitHub (Dec 11, 2025):
I'm having the same issue and have found that turning my VPN off fixes the issue. Turning it back on causes the issue again with immediate effect
@timothycarambat commented on GitHub (Dec 11, 2025):
@dirtstudio That is bizzare. The collector is fully local, why would the VPN stop that processing from booting? Are you able to view the collector logs? https://docs.anythingllm.com/installation-desktop/storage
@dirtstudio commented on GitHub (Dec 11, 2025):
Hey @timothycarambat
Here's what's there. It's a fairly fresh install as I've been trying to fix this issue by wiping the deck clean.
Thanks in advance for taking a look
OS: MacOS 26.1
Processor: M1 Max
Mem: 64GB RAM
AnythingLLM Desktop: Version 1.9.1 (1.9.1)
@timothycarambat commented on GitHub (Dec 11, 2025):
@dirtstudio
We run the collector on port 8888, which can sometimes be used for web-proxies and especially VPN activities. With the VPN running and AnythingLLM closed can you see what the result of
sudo lsof -i :8888We do port-hunt to ensure we dont try to use an occupied port but that may not be being detected or something
@dirtstudio commented on GitHub (Dec 11, 2025):
@timothycarambat
With VPN on and AnythingLLM closed, looks like nada
@timothycarambat commented on GitHub (Dec 11, 2025):
Hm, then I am really out of ideas on why this would be the case TBH. I guess just going to file that under "things that might come up randomly" haha
@dirtstudio commented on GitHub (Dec 11, 2025):
@timothycarambat I'm just glad I got it working! Thanks for your help and for the app, I love it
@ColoursofOSINT commented on GitHub (Dec 27, 2025):
Can confirm that on MacOS VPN breaks it, turning it off it starts working again. Firewall (Little Snitch) seems to have no impact.
I was wondering why it was working then failed but I was turning on VPN and didn't think this could be the issue, until I saw the solution. Seems like it is a fetch failed error. I will see if I can get more details.
Could you guys add timestamps to your logs? Would make troubleshooting much easier.
@ColoursofOSINT commented on GitHub (Dec 27, 2025):
[backend] info: [LMStudio] No context windows cached - Context window may be inaccurately reported.
[backend] info: [LMStudio] No context windows cached - Context window may be inaccurately reported.
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[collector] info: Found 21 files from Obsidian Vault obsidian to process
[backend] info: [TELEMETRY SENT] {"event":"extension_invoked","distinctId":"016460fd-0ab5-412f-aa8b-5e1fe5c836bf","properties":{"type":"obsidian_vault"}}
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[backend] info: [CollectorApi] fetch failed
[backend] info: [TELEMETRY SENT] {"event":"extension_invoked","distinctId":"016460fd-0ab5-412f-aa8b-5e1fe5c836bf","properties":{"type":"obsidian_vault"}}
prisma:info Starting a sqlite pool with 17 connections.
[backend] warn: Child process exited with code 0 and signal null
[backend] info: Worker for job "cleanup-orphan-documents" exited with code 0
You can see the first works without VPN, then I turned it on and instant failure.
@ColoursofOSINT commented on GitHub (Dec 27, 2025):
I used wireshark but couldnt see any network failures, and I don't know why this might be happening. Going to debug with node.
@ColoursofOSINT commented on GitHub (Dec 27, 2025):
Found the issue, looks like 0.0.0.0 gets killed by the VPN, whereas 127.0.0.1 loopback is fine which explains why the lmstudio still works.
Heres some other information relating to ProtonVPN blocking 0.0.0.0
NO VPN
and with VPN
@MVFX-Zbiggy commented on GitHub (Jan 29, 2026):
Encountered this recently and, as mentioned above, you need to specifically allow access to 0.0.0.0
If you're using Lulu, then you need to add a rule for that.
Without it, the document uploader was offline. After adding, it was enabled/available.
[BUG]: Desktop "Document Processor Unavailable" on launchto [GH-ISSUE #866] [BUG]: Desktop "Document Processor Unavailable" on launch@ghost commented on GitHub (Jan 29, 2026):
Encountered this recently and, as mentioned above, you need to specifically allow access to 0.0.0.0
If you're using Lulu, then you need to add a rule for that.
Without it, the document uploader was offline. After adding, it was enabled/available.