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 #3750] [BUG]: Can not Import LLM from ollama, huging faces nor from file #2414

New Issue
Closed
opened 2026-02-22 18:29:34 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:29:34 -05:00
Owner
Copy Link
Copy Source

Originally created by @Calimero33 on GitHub (May 1, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3750

How are you running AnythingLLM?

Docker (local)

What happened?

Since literally 3 days fighting with this issue. Imported around 10 different (Hugging Faces) models all but one hanged at around 90%, and one, got to the installation, however install hanged. Reinstalled it just today to give it one last shoot with a fresh clean install, and nothing again.

Troubleshooting it for 2 WHOLE days now and slowly giving up on this, otherwise brilliant program because there is absolutely nothing I can do anymore. So here my last try (cry) for help, if someone has a similar issue and can maybe help me with this.

Vanilla models in the program its download presets, does partly download and install (the small ones 2-4GB). However, while those are perhaps fine for some small coding and chatting, asking them for news headlines from a specific website, already gets you confronted with their guardrails and limitations. Won't even imagine limiting you in coding without your knowledge because it interpreted something wrong... I need large uncensored LLM versions but somehow, AnythingLLM is refusing to import and install those without exceptions.

Here is the log file:

Microsoft Windows [Version 10.0.19045.2006]
(c) 2019 Microsoft Corporation. All rights reserved.

C:\Windows\system32>cd C:\Users*******\AppData\Local\Programs\AnythingLLM

C:\Users******\AppData\Local\Programs\AnythingLLM>anythingllm.exe

C:\Users*\AppData\Local\Programs\AnythingLLM>
[Preferences] preference config stored at C:\Users*\AppData\Roaming\anythingllm-desktop\config.json
Prisma schema loaded from prisma\schema.prisma
Datasource "db": SQLite database "anythingllm.db" at "file:C:/Users/******/AppData/Roaming/anythingllm-desktop/storage/anythingllm.db"

Already in sync, no schema change or pending migration was found.

Ô£ö Generated Prisma Client (v5.3.1) to .\node_modules@prisma\client in 246ms

Prisma schema loaded from prisma\schema.prisma

Ô£ö Generated Prisma Client (v5.3.1) to .\node_modules@prisma\client in 248ms

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.
[Preferences] Will load window with last know bounds.
[collector] info: [TikTokenTokenizer] Initialized new TikTokenTokenizer instance.
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[backend] info: [TokenManager] Initialized new TokenManager instance for model: gpt-3.5-turbo
[collector] info: Collector hot directory and tmp storage wiped!
[collector] info: [production] AnythingLLM Standalone Document processor listening on port 8888.
[backend] info: [TokenManager] Returning existing instance for model: gpt-3.5-turbo
[backend] info: [TELEMETRY ENABLED] Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM.
[backend] info: prisma:info Starting a sqlite pool with 45 connections.
[backend] info: [TELEMETRY SENT] {"event":"server_boot","distinctId":"db02633f-3969-46ff-b1c2-0c669fd6a329","properties":{"runtime":"desktop","distribution":"windows-x64"}}
[backend] info: Hot loading of AnythingLLMOllama - LLM_PROVIDER is anythingllm_ollama.
[backend] info: [NativeEmbedder] Initialized
[backend] info: [CommunicationKey] RSA key pair generated for signed payloads within AnythingLLM services.
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[backend] info: [production] AnythingLLM Standalone Backend listening on port 3001. Network discovery is disabled.
[OllamaProcessManager] SINGLETON LOCK: Using existing OllamaProcessManager.
[backend] info: [BackgroundWorkerService] Feature is not enabled and will not be started.
[OllamaProcessManager] [windows] Ollama subprocess running. Port 11434. PID 13272.
[backend] info: OllamaAPI offline - retrying. 1/3

Image
Image

Are there known steps to reproduce?

Import from Hugging Faces: ollama run hf.co/username/repository[:tag] FAILS
Import from file, Huging Faces manually downloaded GGUF´s on: C:\Users******\AppData\Roaming\anythingllm-desktop\storage\models FAILS (error?? "400" blinking)

System: Xenon 22c, 5070 Ti, 128GB ram.

Originally created by @Calimero33 on GitHub (May 1, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3750 ### How are you running AnythingLLM? Docker (local) ### What happened? Since literally 3 days fighting with this issue. Imported around 10 different (Hugging Faces) models all but one hanged at around 90%, and one, got to the installation, however install hanged. Reinstalled it just today to give it one last shoot with a fresh clean install, and nothing again. Troubleshooting it for 2 WHOLE days now and slowly giving up on this, otherwise brilliant program because there is absolutely nothing I can do anymore. So here my last try (cry) for help, if someone has a similar issue and can maybe help me with this. Vanilla models in the program its download presets, does partly download and install (the small ones 2-4GB). However, while those are perhaps fine for some small coding and chatting, asking them for news headlines from a specific website, already gets you confronted with their guardrails and limitations. Won't even imagine limiting you in coding without your knowledge because it interpreted something wrong... I need large uncensored LLM versions but somehow, AnythingLLM is refusing to import and install those without exceptions. Here is the log file: -------------------------------------------------------------------------------------- Microsoft Windows [Version 10.0.19045.2006] (c) 2019 Microsoft Corporation. All rights reserved. C:\Windows\system32>cd C:\Users\*******\AppData\Local\Programs\AnythingLLM C:\Users\******\AppData\Local\Programs\AnythingLLM>anythingllm.exe C:\Users\*******\AppData\Local\Programs\AnythingLLM> [Preferences] preference config stored at C:\Users\******\AppData\Roaming\anythingllm-desktop\config.json Prisma schema loaded from prisma\schema.prisma Datasource "db": SQLite database "anythingllm.db" at "file:C:/Users/*******/AppData/Roaming/anythingllm-desktop/storage/anythingllm.db" Already in sync, no schema change or pending migration was found. Ô£ö Generated Prisma Client (v5.3.1) to .\node_modules\@prisma\client in 246ms Prisma schema loaded from prisma\schema.prisma Ô£ö Generated Prisma Client (v5.3.1) to .\node_modules\@prisma\client in 248ms 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. [Preferences] Will load window with last know bounds. [collector] info: [TikTokenTokenizer] Initialized new TikTokenTokenizer instance. [backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data. [backend] info: [TokenManager] Initialized new TokenManager instance for model: gpt-3.5-turbo [collector] info: Collector hot directory and tmp storage wiped! [collector] info: [production] AnythingLLM Standalone Document processor listening on port 8888. [backend] info: [TokenManager] Returning existing instance for model: gpt-3.5-turbo [backend] info: [TELEMETRY ENABLED] Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM. [backend] info: prisma:info Starting a sqlite pool with 45 connections. [backend] info: [TELEMETRY SENT] {"event":"server_boot","distinctId":"db02633f-3969-46ff-b1c2-0c669fd6a329","properties":{"runtime":"desktop","distribution":"windows-x64"}} [backend] info: Hot loading of AnythingLLMOllama - LLM_PROVIDER is anythingllm_ollama. [backend] info: [NativeEmbedder] Initialized [backend] info: [CommunicationKey] RSA key pair generated for signed payloads within AnythingLLM services. [backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data. [backend] info: [production] AnythingLLM Standalone Backend listening on port 3001. Network discovery is disabled. [OllamaProcessManager] SINGLETON LOCK: Using existing OllamaProcessManager. [backend] info: [BackgroundWorkerService] Feature is not enabled and will not be started. [OllamaProcessManager] [windows] Ollama subprocess running. Port 11434. PID 13272. [backend] info: OllamaAPI offline - retrying. 1/3 -------------------------------------------------------------------------------------------- ![Image](https://github.com/user-attachments/assets/43fe72bb-98d8-4a09-934b-90310454af5b) ![Image](https://github.com/user-attachments/assets/658447b9-60f7-4036-a12b-cfd90a75c0dc) ### Are there known steps to reproduce? Import from Hugging Faces: ollama run hf.co/username/repository[:tag] **FAILS** Import from file, Huging Faces manually downloaded GGUF´s on: C:\Users\******\AppData\Roaming\anythingllm-desktop\storage\models **FAILS** (error?? "400" blinking) System: Xenon 22c, 5070 Ti, 128GB ram.
yindo added the possible bugDesktop labels 2026-02-22 18:29:34 -05:00
yindo closed this issue 2026-02-22 18:29:35 -05:00
yindo commented 2026-02-22 18:29:35 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (May 1, 2025):

This has been resolved and will be deployed in v1.8.1 to be released next week. The issue is both related to ollama and Electrons bandwidth limits since 2GB is far below your models size of 50GB.

That being said, it has been patched and will be fixed in v1.8.1 - thanks for bringing it to our attention.

@timothycarambat commented on GitHub (May 1, 2025): This has been resolved and will be deployed in v1.8.1 to be released next week. The issue is both related to ollama and Electrons bandwidth limits since 2GB is far below your models size of 50GB. That being said, it has been patched and will be fixed in v1.8.1 - thanks for bringing it to our attention.
yindo commented 2026-02-22 18:29:35 -05:00
Author
Owner
Copy Link
Copy Source

@Calimero33 commented on GitHub (May 2, 2025):

Epic! Thank you! Furthermore, maybe worth of mentioning, the CPU usage by the APP is extremely poor 2-3% near the installation and 3-4% near Importing the models, did not see it surpassing it (only near running model and also there not more than 40-55%. Best regards!

@Calimero33 commented on GitHub (May 2, 2025): Epic! Thank you! Furthermore, maybe worth of mentioning, the CPU usage by the APP is extremely poor 2-3% near the installation and 3-4% near Importing the models, did not see it surpassing it (only near running model and also there not more than 40-55%. Best regards!
yindo changed title from [BUG]: Can not Import LLM from ollama, huging faces nor from file to [GH-ISSUE #3750] [BUG]: Can not Import LLM from ollama, huging faces nor from file 2026-06-05 14:46:24 -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 Desktop 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#2414
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?