Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-21 01:25:28 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #1131] [BUG]: Could not respond to message. LanceDBError: No vector column found to create index #698

New Issue
Closed
opened 2026-02-22 18:20:53 -05:00 by yindo · 5 comments
yindo commented 2026-02-22 18:20:53 -05:00
Owner
Copy Link
Copy Source

Originally created by @Ikaros-521 on GitHub (Apr 19, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1131

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

workspace ask question，return error：

Could not respond to message.
LanceDBError: No vector column found to create index

Are there known steps to reproduce?

embedding model used local ollama，qwen1.5b

Originally created by @Ikaros-521 on GitHub (Apr 19, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1131 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? workspace ask question，return error： ``` Could not respond to message. LanceDBError: No vector column found to create index ``` ### Are there known steps to reproduce? embedding model used local ollama，qwen1.5b
yindo added the possible bug label 2026-02-22 18:20:53 -05:00
yindo closed this issue 2026-02-22 18:20:53 -05:00
yindo commented 2026-02-22 18:20:53 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 19, 2024):

This happens when you embed your files with some previous embedder model, and then at a later date swap the embedder model but still continue to use the previously cached files. Your query dimensions will not be congruent and this error is the result.

Un embed all documents from the workspace and even delete the existing cached documents. Then reupload and embed the documents.

We will be adding an error message to prevent this from accidentally occurring in the future.

@timothycarambat commented on GitHub (Apr 19, 2024): This happens when you embed your files with some previous embedder model, and then at a later date swap the embedder model but still continue to use the previously cached files. Your query dimensions will not be congruent and this error is the result. Un embed all documents from the workspace and even delete the existing cached documents. Then reupload and embed the documents. We will be adding an error message to prevent this from accidentally occurring in the future.
yindo commented 2026-02-22 18:20:53 -05:00
Author
Owner
Copy Link
Copy Source

@Ikaros-521 commented on GitHub (Apr 19, 2024):

This happens when you embed your files with some previous embedder model, and then at a later date swap the embedder model but still continue to use the previously cached files. Your query dimensions will not be congruent and this error is the result.

Un embed all documents from the workspace and even delete the existing cached documents. Then reupload and embed the documents.

We will be adding an error message to prevent this from accidentally occurring in the future.

Thank you for the answer. It was very helpful. THX.
Looking forward to optimization~

@Ikaros-521 commented on GitHub (Apr 19, 2024): > This happens when you embed your files with some previous embedder model, and then at a later date swap the embedder model but still continue to use the previously cached files. Your query dimensions will not be congruent and this error is the result. > > Un embed all documents from the workspace and even delete the existing cached documents. Then reupload and embed the documents. > > We will be adding an error message to prevent this from accidentally occurring in the future. Thank you for the answer. It was very helpful. THX. Looking forward to optimization~
yindo commented 2026-02-22 18:20:53 -05:00
Author
Owner
Copy Link
Copy Source

@rickywu commented on GitHub (Apr 28, 2024):

I have the same, and tried remove and upload again,but not work
I use one embedding model and changed to another runs in ollama

@rickywu commented on GitHub (Apr 28, 2024): I have the same, and tried remove and upload again,but not work I use one embedding model and changed to another runs in ollama
yindo commented 2026-02-22 18:20:53 -05:00
Author
Owner
Copy Link
Copy Source

@llwwei168 commented on GitHub (Jun 10, 2024):

"I'm experiencing the same issue, I've uploaded relevant documents to my workspace, and when doing RAG, this prompt appeared:"
My configuration:
LLM Provider：Ollama
Models: qiwen2
Embedding Model Selection: qiwen2
Vector Database Provider: LnaceDB

@llwwei168 commented on GitHub (Jun 10, 2024): "I'm experiencing the same issue, I've uploaded relevant documents to my workspace, and when doing RAG, this prompt appeared:" My configuration: LLM Provider：Ollama Models: qiwen2 Embedding Model Selection: qiwen2 Vector Database Provider: LnaceDB
yindo commented 2026-02-22 18:20:53 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jun 10, 2024):

@llwwei168 this occurs when you changed your embedder after either inserting a single document into a workspace or have documents in a workspace and have a cached document that was embedded by a previous embedder.

Depending on which one you are effect by:

  • Workspace -> Reset vector database -> then embed
  • Documents -> Unembed + delete all docs and reupload and embed so you can be sure all are on the same embedder
@timothycarambat commented on GitHub (Jun 10, 2024): @llwwei168 this occurs when you changed your embedder after either inserting a single document into a workspace or have documents in a workspace and have a cached document that was embedded by a previous embedder. Depending on which one you are effect by: - Workspace -> Reset vector database -> then embed - Documents -> Unembed + delete all docs and reupload and embed so you can be sure all are on the same embedder
yindo changed title from [BUG]: Could not respond to message. LanceDBError: No vector column found to create index to [GH-ISSUE #1131] [BUG]: Could not respond to message. LanceDBError: No vector column found to create index 2026-06-05 14:36:43 -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#698
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?