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 #5633] [BUG]: "Failed to Fetch" on Synology DS225+ during Embedding Setup #5204

New Issue
Closed
opened 2026-06-05 14:52:38 -04:00 by yindo · 2 comments
yindo commented 2026-06-05 14:52:38 -04:00
Owner
Copy Link
Copy Source

Originally created by @pantesou on GitHub (May 15, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5633

Image Image

How are you running AnythingLLM?

Docker (local)

What happened?

Hi, I'm running AnythingLLM on a Synology DS225+ (Docker/Container Manager) with 10GB RAM. My system is healthy, and I've configured Google DNS (8.8.8.8).
While the LLM setup (Gemini 2.5 Flash) works, the Embedding Preference consistently returns 'Failed to fetch' and causes the container to restart, regardless of whether I use Native Embedder or Gemini API.
I have already tried resetting the container and clearing the storage folder. Any specific Docker environment variables or network settings for Synology users to bypass this?

Are there known steps to reproduce?

No response

LLM Provider & Model (if applicable)

No response

Embedder Provider & Model (if applicable)

No response

Originally created by @pantesou on GitHub (May 15, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5633 <img width="1213" height="850" alt="Image" src="https://github.com/user-attachments/assets/b6738769-a49f-48c5-b5f1-ba2dcb68b0e4" /> <img width="1260" height="868" alt="Image" src="https://github.com/user-attachments/assets/3fba3a01-3683-456a-b791-c0352c0de2aa" /> ### How are you running AnythingLLM? Docker (local) ### What happened? Hi, I'm running AnythingLLM on a Synology DS225+ (Docker/Container Manager) with 10GB RAM. My system is healthy, and I've configured Google DNS (8.8.8.8). While the LLM setup (Gemini 2.5 Flash) works, the Embedding Preference consistently returns 'Failed to fetch' and causes the container to restart, regardless of whether I use Native Embedder or Gemini API. I have already tried resetting the container and clearing the storage folder. Any specific Docker environment variables or network settings for Synology users to bypass this? ### Are there known steps to reproduce? _No response_ ### LLM Provider & Model (if applicable) _No response_ ### Embedder Provider & Model (if applicable) _No response_
yindo added the possible bug label 2026-06-05 14:52:38 -04:00
yindo closed this issue 2026-06-05 14:52:38 -04:00
yindo commented 2026-06-05 14:52:38 -04:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (May 16, 2026):

This is a deployment/networking level issue. When using embedding models that do not yet exist on the server we will attempt to pull from HuggingFace and then failover to our CDN for mirror.

These are downloaded once as needed as to not bloat the container image and only to pull models as needed. This was originally a solve for people in China that are VPN blocked by HF so they can still use the app for models that are in the critical path (like embedding).

This error would occur if both the HF and our CDN connection fail.
You should see these error logs in the container when you attempt to embed something.

Since you are seeing this on save of setting this would indicate that you likely also are running the container without the valid STORAGE_DIR set. Can you share your docker command? The most simple startup command is this:
https://docs.anythingllm.com/installation-docker/quickstart

<!-- gh-comment-id:4468192034 --> @timothycarambat commented on GitHub (May 16, 2026): This is a deployment/networking level issue. When using embedding models that do not yet exist on the server we will attempt to pull from HuggingFace and then failover to our CDN for mirror. These are downloaded **once as needed** as to not bloat the container image and only to pull models as needed. This was originally a solve for people in China that are VPN blocked by HF so they can still use the app for models that are in the critical path (like embedding). This error would occur if both the HF and our CDN connection fail. You should see these error logs in the container when you attempt to embed something. Since you are seeing this **on save** of setting this would indicate that you likely also are running the container without the valid `STORAGE_DIR` set. Can you share your docker command? The most simple startup command is this: https://docs.anythingllm.com/installation-docker/quickstart
yindo commented 2026-06-05 14:52:38 -04:00
Author
Owner
Copy Link
Copy Source

@pantesou commented on GitHub (May 18, 2026):

hi
My problem solved. I use these and everything works well.
thank you Timothy!

Image
<!-- gh-comment-id:4475034447 --> @pantesou commented on GitHub (May 18, 2026): hi My problem solved. I use these and everything works well. thank you Timothy! <img width="435" height="237" alt="Image" src="https://github.com/user-attachments/assets/48422e48-247d-4130-bc48-6f7f747d178b" />
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#5204
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?