[GH-ISSUE #5177] [BUG]: AnythingLLM happily allows multiple copies of the same URL in a RAG/"query" workspace. #4953

Closed
opened 2026-06-05 14:51:06 -04:00 by yindo · 1 comment
Owner

Originally created by @bulrush15 on GitHub (Mar 9, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5177

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

I have AnythingLLM v1.10 on Windows 11.

I created a RAG AI workspace, which ALLM calls "query".

Proposed solution

  1. Before clicking "Move to workspace" make sure all URLs and documents are not in the current workspace.
  2. For documents do a checksum on the doc in the workspace and the doc ready to be added again. If the checksums are the same, there is a good chance the documents are the same.

Are there known steps to reproduce?

Here's how to duplicate this bug.

  1. Click Upload icon next to the RAG workspace name.
  2. Add this URL as an example: https://www.nber.org/papers/w34836 then click Fetch button.
  3. After the site is fetched check the square box the left of the site in the upper half of the popup window.
  4. Click the "Move to workspace" button.
  5. Close the upload window.
  6. Repeat these steps.

This URL will be in workspace twice. I have to wonder if this URL will then have more "weight" than other URLs.

Originally created by @bulrush15 on GitHub (Mar 9, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5177 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? I have AnythingLLM v1.10 on Windows 11. I created a RAG AI workspace, which ALLM calls "query". **Proposed solution** 1. Before clicking "Move to workspace" make sure all URLs and documents are not in the current workspace. 2. For documents do a checksum on the doc in the workspace and the doc ready to be added again. If the checksums are the same, there is a good chance the documents are the same. ### Are there known steps to reproduce? Here's how to duplicate this bug. 1. Click Upload icon next to the RAG workspace name. 2. Add this URL as an example: https://www.nber.org/papers/w34836 then click Fetch button. 3. After the site is fetched check the square box the left of the site in the upper half of the popup window. 4. Click the "Move to workspace" button. 5. Close the upload window. 6. Repeat these steps. This URL will be in workspace twice. I have to wonder if this URL will then have more "weight" than other URLs.
yindo added the possible bug label 2026-06-05 14:51:06 -04:00
yindo closed this issue 2026-06-05 14:51:06 -04:00
Author
Owner

@timothycarambat commented on GitHub (Mar 9, 2026):

Yes, because the URL content may have changed between fetches since it is only capturing the static content of that URL at the time of fetch. If you want continuous sync enable Live file sync feature and watch the file.

<!-- gh-comment-id:4025569857 --> @timothycarambat commented on GitHub (Mar 9, 2026): Yes, because the URL content may have changed between fetches since it is only capturing the static content of that URL at the time of fetch. If you want continuous sync enable [`Live file sync`](https://docs.anythingllm.com/beta-preview/active-features/live-document-sync) feature and watch the file.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#4953