mirror of
https://github.com/Mintplex-Labs/anything-llm.git
synced 2026-07-19 14:13:35 -04:00
Closed
opened 2026-02-22 18:24:17 -05:00 by yindo
·
5 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
No Label
possible bug
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#1329
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 @dan8798 on GitHub (Aug 3, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2038
How are you running AnythingLLM?
AnythingLLM desktop app
What happened?
I've downloaded and installed anythingllm desktop on win11. Everything went fine, except when i try to download llms such as llama3.1 etc, it won't complete, no matter which llm i try to download. I've uninstalled and reinstalled anythingllm desktop to no avail, frustrating.
Are there known steps to reproduce?
I've uninstalled and reinstalled anythingllm desktop. I"ve tried all the other llms, they all won't complete downloading.
@timothycarambat commented on GitHub (Aug 5, 2024):
This is not a bug with AnythingLLM, but likely from ollama's model registry - which is where the download stream originate from. We have seem download's hang from people who have limited disk space where AnythingLLM is using storage and with VPNs. Do either of these apply to you?
I downloaded llava-llama3 on a fresh windows desktop today actually - no issues
@dan8798 commented on GitHub (Aug 5, 2024):
None applied, not using vpn and plenty of space on my hard drive. I download with ollama, webui and others and never encountered this issue.
@mercs759 commented on GitHub (Oct 21, 2024):
Same situation here : Win10pro on intel 6500T, 16GBram , 40Gb Free SSD space.
Gpt4all goes fine, Lm Studio goes fine, Anything stops downloading models between 40 and 56%
@kckcki commented on GitHub (Jan 30, 2025):
My runtime environment / computer:
─────────────────────────────────────
■ Lenovo ThinkPad P53 Laptop
■ 8TB SSD space = 2 x 4TB built-in SSDs on PCIe Bus
■ 64 Gigabytes of RAM
■ CPU: Should Not matter
■ GPU: Should Not matter
■ OS: Windows 11 Enterprise LTSC
■ Type of Internet Connection: Should Not matter
YES I wasted 45 gigabytes of my internet data due to the AnythingLLM download getting stuck !
I had to redo/repeat the download over 9 times :((
I lost a WEEK, redownloading the model (LLaVA Llama3 8B 5.5GB) :((
At the END of the week, I was at a point where I was willing to completely give up on this rather promising LLM ::(( Having wasted 45 gigabytes of my internet data :((
Initial Symptoms:
─────────────────────────────────────
While AnythingLLM was running
I went into my folder
c:\Users\User1\AppData\Roaming\anythingllm-desktop\storage\models\ollama\blobs
we should call this the “blobs” folder.
and Lo and Behold, I found these files
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-0
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-1
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-2
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-3
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-4
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-5
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-6
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-7
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-8
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-9
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-10
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-11
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-12
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-13
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-14
sha256-b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc-partial-15
a) The first file without a number suffix, is 4.58 gigabytes in size !
b) The REST of the files were super-tiny and almost empty, each of them was less than 200 bytes in length.
c) These files struck me as CLEARLY the files that make up the so-called Model, i.e. the Model BEING DOWNLOADED and AnythingLLM FAILING to COMPLETE the download process.
The first file, when I . . .
right-clicked it and
checked its Size by looking at its reported “Size on Disk”
closed the file size window (Properties dialog box), and waited 4 to 10 seconds
right-clicked it AGAIN/afresh and
checked its Size afresh by looking at its reported “Size on Disk”
. . . I could clearly see and tell whether it was GROWING in size or just STUCK at one size.
When the download is NOT stuck (working fine, truly and busy downloading), the file was GROWING at a rate of 11 megabytes per second, indicating that NOT only was my internet speed fast, but SOMEONE was writing data to this file and causing it to GROW, with it occupying more and more disk space.
on the OTHER hand, when the download was STUCK (while AnythingLLM continued to show a FAKE progress indicator spinning circle!!), the file’s “Size on Disk” was sitting at ONE value, indicating that the file is NOTTT GROWING, and that NO ONE is writing data to this file as it is NOT progressively occupying more and more disk space :(
Typical First Line Intervention:
─────────────────────────────────────
For most of us, we would naturally be tempted to attempt the following (in the order of least disruption)
a) STOP the download, or
b) CLOSE the app and restart it, or
c) just uninstall the app and wipe everything out (clean sweep), and re-install the whole app afresh.
Unearthing the Bug:
─────────────────────────────────────
I have PROOF that AnythingLLM, contrary to its claim on its user interface,
whenever you STOP the download [within the app, top right corner]
it tells you that your Download can be RESUMED later, which is a FALSE claim :((
the claim is FALSE because once you STOP the download [within the app, top right corner], or you CLOSE the App’s window
it actually DELETES ALL the already/partly downloaded files in the blobs folder
c:\Users\User1\AppData\Roaming\anythingllm-desktop\storage\models\ollama\blobs
these partly-downloaded files can be GIGABYTES of WASTED data in the case of you stopping the download at 80% and they get deleted like this !! :(( and that is exactly HOW I ended up wasting 45 gigabytes of my internet data through repeated fresh re-downloads :((
I know FOR SURE that it Deletes the partly-downloaded files, because
a) While watching in the folder, as soon as I STOP the download [within the app, top right corner], or CLOSE the App’s window, I could witness the partly-downloaded files disappearing (ALL of them) :((
b) With my partly-downloaded files GONE, I would then look for the files by their age and size (Not by their name!) and I cud Not find traces of them ANYWHERE on my hard disk :(( I had hoped that it was MOVING the files to another hidden location so that it may return them BACK to the blobs folder for it to RESUME the download when you relaunch it, as it [falsely] claims. The truth however is that AnythingLLM does Not competently know what “RESUMING” a download means :((
c) My FREE DISK SPACE increased by a warping 5 GB as soon as I STOP the download or close the window !! This one was the last nail in the coffin and it was ENOUGH for me to conclude that . . . AnythingLLM definitely DELETES partly-downloaded files (leaving No hope for resumption of the download).
This brings us to the END of the PROBLEM Description.
▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
Now let’s get to the SOLUTION :))
─────────────────────────────────────
When my download reached 98% in the new week, it got STUCK :((
I went into the blobs folder and I COPIED away ALL of my partly-downloaded files
I pasted them into my own backup folder C:\A\Save_My_Partly_Downloaded_Blobs
we could call these “RESCUE COPIES” or “backup copies”.
I then proceeded to STOP the download [within the app, top right corner], I could have also CLOSED the App’s window
The partly-downloaded files disappeared from the blobs folder as expected :)) This time around I was smiling, knowing that I had my own RESCUE COPIES of my 98% partly-downloaded files :))
I COPIED BACK the RESCUE COPIES of my 98% partly-downloaded files from
C:\A\Save_My_Partly_Downloaded_Blobs
to the
blobs folder
I relaunched AnythingLLM
Lo and Behold, the download indicator within AnythingLLM showed that my download was at 98% and it rapidly RESUMED to 99% :)) Within 2 minutes the download was at 100% and AnythingLLM was Un-Packing the download :)))
I was so EXCITED I had the motivation to come here and WRITE this whole Essay :)))
It’s been two weeks, and I am proud to say that I have the “LLaVA Llama3 8B 5.5GB” model running locally inside of my AnythingLLM installation and EVERYTHING else about my ordeal HISTORY :))
Subject / Topic:
Downloading of the Models gets stuck during installation of AnythingLLM.
Google Search Engine Keywords:
AnythingLLM, downloading of model does Not complete, downloading of model is stuck, downloading model does Not resume, downloading model does Not finish, fails to resume model download, model download starting from scratch, model download starting afresh, closing and reopening AnythingLLM does not help /work, resintalling AnythingLLM does not help / work. I’ve tried everything.
kind regards
this is Tebza a.k.a. Kcee, all the way from the City of Johannesburg, South Africa, on the continet of Africa
last updated : Thursday, 30 January 2025, 12:31
██ End ███████████████████████████████████
@timothycarambat commented on GitHub (Jan 30, 2025):
Ollama's registry has been having cloudflare issues all week
This has resulted in hanging downloads, stuck downloads, failures to unpack layers, and it has been intermittent. All we do it pull from their registry so there is little for us to do to make it work. Since it is wholly dependent on their registry working and also the client connection persisting it.
LLM downloads stuck at 50-60% [BUG]:to [GH-ISSUE #2038] LLM downloads stuck at 50-60% [BUG]: