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 #5208] [BUG]: [NativeEmbedder] Failed to download model from primary URL. #4965

New Issue
Closed
opened 2026-06-05 14:51:11 -04:00 by yindo · 2 comments
yindo commented 2026-06-05 14:51:11 -04:00
Owner
Copy Link
Copy Source

Originally created by @wilsoja1 on GitHub (Mar 14, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5208

How are you running AnythingLLM?

Docker (local)

What happened?

Clicked "Save and Embed" using the default config and the Fetch fails. Docker logs indicate the URL is trying to be fetched below but a manual browser session yields a 404

[backend] info: [Event Logged] - workspace_documents_added

[backend] info: [VectorDB::LanceDb] Adding new vectorized document into namespace sap-hana-schema

[backend] info: [NativeEmbedder] Initialized Xenova/all-MiniLM-L6-v2

[backend] info: [RecursiveSplitter] Will split with {"chunkSize":1000,"chunkOverlap":20,"chunkHeader":"<document_metadata>\nsourceDocument: output.csv\npub..."}

[backend] info: [VectorDB::LanceDb] Snippets created from document: 317

[backend] info: [NativeEmbedder] The native embedding model has never been run and will be downloaded right now. Subsequent runs will be faster. (~23MB)

[backend] info: [NativeEmbedder] Downloading Xenova/all-MiniLM-L6-v2 from https://cdn.anythingllm.com/support/models/

[backend] info: [NativeEmbedder] Failed to download model from primary URL. Using fallback https://cdn.anythingllm.com/support/models/

[backend] info: [NativeEmbedder] Downloading Xenova/all-MiniLM-L6-v2 from https://cdn.anythingllm.com/support/models/

[backend] info: [VectorDB::LanceDb] addDocumentToNamespace fetch failed

[backend] error: Failed to vectorize output.csv

Are there known steps to reproduce?

No response

Originally created by @wilsoja1 on GitHub (Mar 14, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5208 ### How are you running AnythingLLM? Docker (local) ### What happened? Clicked "Save and Embed" using the default config and the Fetch fails. Docker logs indicate the URL is trying to be fetched below but a manual browser session yields a 404 [backend] info: [Event Logged] - workspace_documents_added [backend] info: [VectorDB::LanceDb] Adding new vectorized document into namespace sap-hana-schema [backend] info: [NativeEmbedder] Initialized Xenova/all-MiniLM-L6-v2 [backend] info: [RecursiveSplitter] Will split with {"chunkSize":1000,"chunkOverlap":20,"chunkHeader":"<document_metadata>\nsourceDocument: output.csv\npub..."} [backend] info: [VectorDB::LanceDb] Snippets created from document: 317 [backend] info: [NativeEmbedder] The native embedding model has never been run and will be downloaded right now. Subsequent runs will be faster. (~23MB) [backend] info: [NativeEmbedder] Downloading Xenova/all-MiniLM-L6-v2 from https://cdn.anythingllm.com/support/models/ [backend] info: [NativeEmbedder] Failed to download model from primary URL. Using fallback https://cdn.anythingllm.com/support/models/ [backend] info: [NativeEmbedder] Downloading Xenova/all-MiniLM-L6-v2 from https://cdn.anythingllm.com/support/models/ [backend] info: [VectorDB::LanceDb] addDocumentToNamespace fetch failed [backend] error: Failed to vectorize output.csv ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-06-05 14:51:11 -04:00
yindo closed this issue 2026-06-05 14:51:11 -04:00
yindo commented 2026-06-05 14:51:11 -04:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Mar 14, 2026):

Are you offline or on a restrict network? You should see progress logs of the model pulling. This indicates that you are either fully offline or the instance cannot pull the required model to do the task.

We mirror some assets on our CDN for users in geo-restricted countries where they cannot pull from HF natively as a convenience to them. These models only need to download once so that we dont have to pre-pack them into the image making the image massive.

<!-- gh-comment-id:4061018920 --> @timothycarambat commented on GitHub (Mar 14, 2026): Are you offline or on a restrict network? You should see [progress logs of the model pulling](https://github.com/Mintplex-Labs/anything-llm/blob/master/server/utils/EmbeddingEngines/native/index.js#L135-L145). This indicates that you are either fully offline or the instance cannot pull the required model to do the task. We mirror some assets on our CDN for users in geo-restricted countries where they cannot pull from HF natively as a convenience to them. These models only need to download once so that we dont have to pre-pack them into the image making the image massive.
yindo commented 2026-06-05 14:51:11 -04:00
Author
Owner
Copy Link
Copy Source

@wilsoja1 commented on GitHub (Mar 17, 2026):

Thanks for reaching out. The machine I was using does have a lot of security on it.

Jimmy Wilson | Software Development Analyst, ERP Systems Special Programs
Northrop Grumman Corporation | Enterprise Services
O: 310-297-5884 | C: 334-707-1676 | @.@.>

From: Timothy Carambat @.>
Sent: Saturday, March 14, 2026 1:15 PM
To: Mintplex-Labs/anything-llm @.>
Cc: Wilson, Jimmy [US] (CO) @.>; Author @.>
Subject: EXT :Re: [Mintplex-Labs/anything-llm] [BUG]: [NativeEmbedder] Failed to download model from primary URL. (Issue #5208)

This email originated from outside of Northrop Grumman.

[https://avatars.githubusercontent.com/u/16845892?s=20&v=4]timothycarambat left a comment (Mintplex-Labs/anything-llm#5208)https://github.com/Mintplex-Labs/anything-llm/issues/5208#issuecomment-4061018920

Are you offline or on a restrict network? You should see progress logs of the model pullinghttps://github.com/Mintplex-Labs/anything-llm/blob/master/server/utils/EmbeddingEngines/native/index.js#L135-L145. This indicates that you are either fully offline or the instance cannot pull the required model to do the task.

We mirror some assets on our CDN for users in geo-restricted countries where they cannot pull from HF natively as a convenience to them. These models only need to download once so that we dont have to pre-pack them into the image making the image massive.

—
Reply to this email directly, view it on GitHubhttps://github.com/Mintplex-Labs/anything-llm/issues/5208#issuecomment-4061018920, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AQXKQJXBG6VR3OBFGGSIR2D4QWOTFAVCNFSM6AAAAACWR22UQGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHM2DANRRGAYTQOJSGA.
You are receiving this because you authored the thread.Message ID: @.@.>>

<!-- gh-comment-id:4076190291 --> @wilsoja1 commented on GitHub (Mar 17, 2026): Thanks for reaching out. The machine I was using does have a lot of security on it. Jimmy Wilson | Software Development Analyst, ERP Systems Special Programs Northrop Grumman Corporation | Enterprise Services O: 310-297-5884 | C: 334-707-1676 | ***@***.******@***.***> From: Timothy Carambat ***@***.***> Sent: Saturday, March 14, 2026 1:15 PM To: Mintplex-Labs/anything-llm ***@***.***> Cc: Wilson, Jimmy [US] (CO) ***@***.***>; Author ***@***.***> Subject: EXT :Re: [Mintplex-Labs/anything-llm] [BUG]: [NativeEmbedder] Failed to download model from primary URL. (Issue #5208) This email originated from outside of Northrop Grumman. [https://avatars.githubusercontent.com/u/16845892?s=20&v=4]timothycarambat left a comment (Mintplex-Labs/anything-llm#5208)<https://github.com/Mintplex-Labs/anything-llm/issues/5208#issuecomment-4061018920> Are you offline or on a restrict network? You should see progress logs of the model pulling<https://github.com/Mintplex-Labs/anything-llm/blob/master/server/utils/EmbeddingEngines/native/index.js#L135-L145>. This indicates that you are either fully offline or the instance cannot pull the required model to do the task. We mirror some assets on our CDN for users in geo-restricted countries where they cannot pull from HF natively as a convenience to them. These models only need to download once so that we dont have to pre-pack them into the image making the image massive. — Reply to this email directly, view it on GitHub<https://github.com/Mintplex-Labs/anything-llm/issues/5208#issuecomment-4061018920>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AQXKQJXBG6VR3OBFGGSIR2D4QWOTFAVCNFSM6AAAAACWR22UQGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHM2DANRRGAYTQOJSGA>. You are receiving this because you authored the thread.Message ID: ***@***.******@***.***>>
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#4965
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?