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 #2863] [BUG]: No vector column found to match with the query vector dimension: 1536 #1824

New Issue
Closed
opened 2026-02-22 18:26:41 -05:00 by yindo · 4 comments
yindo commented 2026-02-22 18:26:41 -05:00
Owner
Copy Link
Copy Source

Originally created by @jwr on GitHub (Dec 17, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2863

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

I configured OpenAI API keys, created a new workspace, uploaded several documents and moved them to the workspace.

Asking any query results in:

Failed to execute query stream: Invalid input, No vector column found to match with the query vector dimension: 1536

If I change the embedder to a different one and reset the vector database for the workspace, the number is different, but I can never get anything to work.

Are there known steps to reproduce?

No response

Originally created by @jwr on GitHub (Dec 17, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2863 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? I configured OpenAI API keys, created a new workspace, uploaded several documents and moved them to the workspace. Asking any query results in: `Failed to execute query stream: Invalid input, No vector column found to match with the query vector dimension: 1536` If I change the embedder to a different one and reset the vector database for the workspace, the number is different, but I can never get anything to work. ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:26:41 -05:00
yindo closed this issue 2026-02-22 18:26:41 -05:00
yindo commented 2026-02-22 18:26:41 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 17, 2024):

Reset the vector database on the workspace. You changed your vector db or embedding model/prefernce and now you have a dimensionality mismatch.

We fixed this in https://github.com/Mintplex-Labs/anything-llm/pull/2819 to prevent it from happening in the future, it is not in desktop app until next patch

@timothycarambat commented on GitHub (Dec 17, 2024): Reset the vector database on the workspace. You changed your vector db or embedding model/prefernce and now you have a dimensionality mismatch. We fixed this in https://github.com/Mintplex-Labs/anything-llm/pull/2819 to prevent it from happening in the future, it is not in desktop app until next patch
yindo commented 2026-02-22 18:26:41 -05:00
Author
Owner
Copy Link
Copy Source

@jwr commented on GitHub (Dec 17, 2024):

I did reset the vector database in the workspace. Multiple times. I even created a new workspace, but no matter what I do I can't seem to get past this.

@jwr commented on GitHub (Dec 17, 2024): I did reset the vector database in the workspace. Multiple times. I even created a new workspace, but no matter what I do I can't seem to get past this.
yindo commented 2026-02-22 18:26:41 -05:00
Author
Owner
Copy Link
Copy Source

@jwr commented on GitHub (Dec 18, 2024):

After banging my head against this wall some more, I now think the problem is that resetting the vector database does not help. What does help is completely deleting all uploaded documents (not just ones moved to the workspace, all uploaded ones).

@jwr commented on GitHub (Dec 18, 2024): After banging my head against this wall some more, I now think the problem is that resetting the vector database does not help. What does help is completely deleting all uploaded documents (not just ones moved to the workspace, all uploaded ones).
yindo commented 2026-02-22 18:26:41 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 18, 2024):

Your old docments were cached and so they also had the old embedding dimensions, so when you re-added them it just set the table back to the old dimensions over and over. You had to remove the documents and re-embed them as well.

Again, we fixed this in the PR linked. It will basically wipe all namespace and unembed and wipe the cache of documents away too so you dont encounter this again

@timothycarambat commented on GitHub (Dec 18, 2024): Your old docments were _cached_ and so they _also_ had the old embedding dimensions, so when you re-added them it just set the table back to the old dimensions over and over. You had to remove the documents and re-embed them as well. Again, we fixed this in the PR linked. It will basically wipe all namespace and unembed and wipe the cache of documents away too so you dont encounter this again
yindo changed title from [BUG]: No vector column found to match with the query vector dimension: 1536 to [GH-ISSUE #2863] [BUG]: No vector column found to match with the query vector dimension: 1536 2026-06-05 14:42:53 -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#1824
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?