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 #4252] [BUG]: Sources not being properly retrieved for exact match in one workspace while it works properly in another workspace #2706

New Issue
Closed
opened 2026-02-22 18:30:52 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:30:52 -05:00
Owner
Copy Link
Copy Source

Originally created by @sha-roze on GitHub (Aug 6, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4252

How are you running AnythingLLM?

Docker (local)

What happened?

I searched for the exact content in a document in two workspaces. It only listed the document in sources in one workspace despite it being available in both workspaces. The embedding model I'm using is openai's ada and Milvus as vector database.

Are there known steps to reproduce?

I think this is reproducible only when there are a large number of documents in each workspace (1307).

Originally created by @sha-roze on GitHub (Aug 6, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4252 ### How are you running AnythingLLM? Docker (local) ### What happened? I searched for the exact content in a document in two workspaces. It only listed the document in sources in one workspace despite it being available in both workspaces. The embedding model I'm using is openai's ada and Milvus as vector database. ### Are there known steps to reproduce? I think this is reproducible only when there are a large number of documents in each workspace (1307).
yindo added the possible bug label 2026-02-22 18:30:52 -05:00
yindo closed this issue 2026-02-22 18:30:52 -05:00
yindo commented 2026-02-22 18:30:53 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Aug 8, 2025):

This is how RAG works, we only grab the top n of snippets. Even with the same documents there is no real promise that embedding vectors and responses will return 100% the same results - although they should be close.

@timothycarambat commented on GitHub (Aug 8, 2025): This is how RAG works, we only grab the top `n` of _snippets_. Even with the same documents there is no real promise that embedding vectors and responses will return 100% the same results - although they should be close.
yindo changed title from [BUG]: Sources not being properly retrieved for exact match in one workspace while it works properly in another workspace to [GH-ISSUE #4252] [BUG]: Sources not being properly retrieved for exact match in one workspace while it works properly in another workspace 2026-06-05 14:48:04 -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 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#2706
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?