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 #971] [BUG]: Could not respond to message. LanceDBError: LanceError(IO): Query vector must have non-zero length #592

New Issue
Closed
opened 2026-02-22 18:20:22 -05:00 by yindo · 15 comments
yindo commented 2026-02-22 18:20:22 -05:00
Owner
Copy Link
Copy Source

Originally created by @lbls888 on GitHub (Mar 25, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/971

How are you running AnythingLLM?

Desktop

What happened?

The knowledge base has an error. Is it a problem with the settings or something else? Does anyone know?

Are there known steps to reproduce?

No response

Originally created by @lbls888 on GitHub (Mar 25, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/971 ### How are you running AnythingLLM? Desktop ### What happened? The knowledge base has an error. Is it a problem with the settings or something else? Does anyone know? ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:20:22 -05:00
yindo closed this issue 2026-02-22 18:20:22 -05:00
yindo commented 2026-02-22 18:20:22 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Mar 25, 2024):

This happens when sending a chat?

@timothycarambat commented on GitHub (Mar 25, 2024): This happens when sending a chat?
yindo commented 2026-02-22 18:20:22 -05:00
Author
Owner
Copy Link
Copy Source

@lbls888 commented on GitHub (Mar 26, 2024):

This happens when sending a chat?

Yes, after uploading the knowledge base file, selecting it, and returning to the chat page, this situation occurs. The introductory video works very smoothly, so why is this problem occurring? I'm deeply doubting myself.

@lbls888 commented on GitHub (Mar 26, 2024): > This happens when sending a chat? Yes, after uploading the knowledge base file, selecting it, and returning to the chat page, this situation occurs. The introductory video works very smoothly, so why is this problem occurring? I'm deeply doubting myself.
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Mar 26, 2024):

You reported this issue as using docker. Can you open the docker container logs and send a chat to see the full crash error and report.

@timothycarambat commented on GitHub (Mar 26, 2024): You reported this issue as using docker. Can you open the docker container logs and send a chat to see the full crash error and report.
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@mulderyu commented on GitHub (Mar 27, 2024):

i have the same issue, when setting "Embedding Preference" to opanai or others, ther error will occure, i can only use anythingllm embedder

@mulderyu commented on GitHub (Mar 27, 2024): i have the same issue, when setting "Embedding Preference" to opanai or others, ther error will occure, i can only use anythingllm embedder
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@lbls888 commented on GitHub (Mar 27, 2024):

You reported this issue as using docker. Can you open the docker container logs and send a chat to see the full crash error and report.

I only used the desktop version of AnythingLLM for desktop. I don't understand Docker and I can't use it. The log in the software is: workspace_documents_added，"workspaceName": "lbls88", "numberOfDocumentsAdded": 1
QQ截图20240327163405

@lbls888 commented on GitHub (Mar 27, 2024): > You reported this issue as using docker. Can you open the docker container logs and send a chat to see the full crash error and report. I only used the desktop version of AnythingLLM for desktop. I don't understand Docker and I can't use it. The log in the software is: workspace_documents_added，"workspaceName": "lbls88", "numberOfDocumentsAdded": 1 ![QQ截图20240327163405](https://github.com/Mintplex-Labs/anything-llm/assets/131499083/8d9353e2-fbe3-4d64-b1a9-135771f8a08e)
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Mar 27, 2024):

Then why did you report the issue as Docker (local)?? @mulderyu are you on docker or desktop?

@timothycarambat commented on GitHub (Mar 27, 2024): Then why did you report the issue as Docker (local)?? @mulderyu are you on docker or desktop?
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@mulderyu commented on GitHub (Mar 28, 2024):

Then why did you report the issue as Docker (local)?? @mulderyu are you on docker or desktop?

sorry forgot to mention that i'm using docker verison

@mulderyu commented on GitHub (Mar 28, 2024): > Then why did you report the issue as Docker (local)?? @mulderyu are you on docker or desktop? sorry forgot to mention that i'm using docker verison
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@mulderyu commented on GitHub (Mar 28, 2024):

i just find out the solution(maybe) on docker version
just delete /app/server/storage/lancedb/{workspace name}.lance directory, re-add document to workspace, then it works!
maybe it can use on desktop version too

@mulderyu commented on GitHub (Mar 28, 2024): i just find out the solution(maybe) on docker version just delete /app/server/storage/lancedb/{workspace name}.lance directory, re-add document to workspace, then it works! maybe it can use on desktop version too
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@mulderyu commented on GitHub (Mar 28, 2024):

i just find out the solution(maybe) on docker version just delete /app/server/storage/lancedb/{workspace name}.lance directory, re-add document to workspace, then it works! maybe it can use on desktop version too

remember to remove and delete files on workspace, then delete /app/server/storage/lancedb/{workspace name}.lance directory

@mulderyu commented on GitHub (Mar 28, 2024): > i just find out the solution(maybe) on docker version just delete /app/server/storage/lancedb/{workspace name}.lance directory, re-add document to workspace, then it works! maybe it can use on desktop version too remember to remove and delete files on workspace, then delete /app/server/storage/lancedb/{workspace name}.lance directory
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Mar 28, 2024):

Creating a new workspace would solve this and is going to be the recommended go-forward solutions for this. Root cause is the dimensionality response from using the non-default embedder and getting a 0 length response.

If you delete a workspace it will delete the attached files (not the source files!) and the lance folder for that workspace if you wanted to clean that up!

@timothycarambat commented on GitHub (Mar 28, 2024): Creating a new workspace would solve this and is going to be the recommended go-forward solutions for this. Root cause is the dimensionality response from using the non-default embedder and getting a 0 length response. If you delete a workspace it will delete the attached files (not the source files!) and the lance folder for that workspace if you wanted to clean that up!
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@snoworld888 commented on GitHub (Apr 27, 2024):

i just find out the solution(maybe) on docker version just delete /app/server/storage/lancedb/{workspace name}.lance directory, re-add document to workspace, then it works! maybe it can use on desktop version too

remember to remove and delete files on workspace, then delete /app/server/storage/lancedb/{workspace name}.lance directory

it doesn't work
Could not respond to message.
LanceDBError: LanceError(IO): Query vector must have non-zero length, C:\Users\runneradmin.cargo\registry\src\index.crates.io-6f17d22bba15001f\lance-0.9.18\src\dataset\scanner.rs:378:27

@snoworld888 commented on GitHub (Apr 27, 2024): > > i just find out the solution(maybe) on docker version just delete /app/server/storage/lancedb/{workspace name}.lance directory, re-add document to workspace, then it works! maybe it can use on desktop version too > > remember to remove and delete files on workspace, then delete /app/server/storage/lancedb/{workspace name}.lance directory it doesn't work Could not respond to message. LanceDBError: LanceError(IO): Query vector must have non-zero length, C:\Users\runneradmin\.cargo\registry\src\index.crates.io-6f17d22bba15001f\lance-0.9.18\src\dataset\scanner.rs:378:27
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@snoworld888 commented on GitHub (Apr 27, 2024):

Creating a new workspace would solve this and is going to be the recommended go-forward solutions for this. Root cause is the dimensionality response from using the non-default embedder and getting a 0 length response.

If you delete a workspace it will delete the attached files (not the source files!) and the lance folder for that workspace if you wanted to clean that up!

it doesn't work too

@snoworld888 commented on GitHub (Apr 27, 2024): > Creating a new workspace would solve this and is going to be the recommended go-forward solutions for this. Root cause is the dimensionality response from using the non-default embedder and getting a 0 length response. > > If you delete a workspace it will delete the attached files (not the source files!) and the lance folder for that workspace if you wanted to clean that up! it doesn't work too
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

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

What are you using for embedding? This error occurs to those who use Ollama and forgot to run ollama serve or are using an LLM for embedding like llama2 instead of an actual embedding model since ollama does not differentiate and people just pick a random one

@timothycarambat commented on GitHub (Apr 28, 2024): What are you using for embedding? This error occurs to those who use Ollama and forgot to run `ollama serve` or are using an LLM for embedding like `llama2` instead of an actual embedding model since ollama does not differentiate and people just pick a random one
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@snoworld888 commented on GitHub (May 8, 2024):

What are you using for embedding? This error occurs to those who use Ollama and forgot to run ollama serve or are using an LLM for embedding like llama2 instead of an actual embedding model since ollama does not differentiate and people just pick a random one

Yes, I used Ollama, but it has already started and AnythingLLM has been updated to 1.5.3, and this issue still exists
1715220827250

@snoworld888 commented on GitHub (May 8, 2024): > What are you using for embedding? This error occurs to those who use Ollama and forgot to run `ollama serve` or are using an LLM for embedding like `llama2` instead of an actual embedding model since ollama does not differentiate and people just pick a random one Yes, I used Ollama, but it has already started and AnythingLLM has been updated to 1.5.3, and this issue still exists <img width="798" alt="1715220827250" src="https://github.com/Mintplex-Labs/anything-llm/assets/9781204/4d2b89d1-25ef-47b3-95af-e674682254e8">
yindo commented 2026-02-22 18:20:23 -05:00
Author
Owner
Copy Link
Copy Source

@laowalter commented on GitHub (Jul 2, 2024):

I got the same problem with the latest docker every time upload local documents.
here is the outputs of the docker log:

[Event Logged] - sent_chat
Adding new vectorized document into namespace asdf
Cached vectorized results of custom-documents/AttentionLSTM.pdf-3c95c5d7-e805-4bd6-8c96-aebdc3809ff7.json found! Using cached data to save on embed costs.
Adding new vectorized document into namespace asdf
Cached vectorized results of custom-documents/CNN_for_stock_price_prediction.pdf-232e22cf-27e7-4d4a-b6c2-9bc499e13c45.json found! Using cached data to save on embed costs.
[TELEMETRY SENT] {
event: 'documents_embedded_in_workspace',
distinctId: 'cb46b0f4-fe3a-4e49-8d97-35ce385574d9',
properties: {
LLMSelection: 'ollama',
Embedder: 'ollama',
VectorDbSelection: 'lancedb',
runtime: 'docker'
}
}
[Event Logged] - workspace_documents_added
[OllamaEmbedder] Embedding 1 chunks of text with nomic-embed-text:latest.
[Error: Failed to execute query stream: lance error: LanceError(IO): Query vector must have non-zero length, /home/build_user/.cargo/registry/src/index.crates.io-6f17d22bba15001f/lance-0.12.1/src/dataset/scanner.rs:434:17] {
code: 'GenericFailure'
}

@laowalter commented on GitHub (Jul 2, 2024): I got the same problem with the latest docker every time upload local documents. here is the outputs of the docker log: [Event Logged] - sent_chat Adding new vectorized document into namespace asdf Cached vectorized results of custom-documents/AttentionLSTM.pdf-3c95c5d7-e805-4bd6-8c96-aebdc3809ff7.json found! Using cached data to save on embed costs. Adding new vectorized document into namespace asdf Cached vectorized results of custom-documents/CNN_for_stock_price_prediction.pdf-232e22cf-27e7-4d4a-b6c2-9bc499e13c45.json found! Using cached data to save on embed costs. [TELEMETRY SENT] { event: 'documents_embedded_in_workspace', distinctId: 'cb46b0f4-fe3a-4e49-8d97-35ce385574d9', properties: { LLMSelection: 'ollama', Embedder: 'ollama', VectorDbSelection: 'lancedb', runtime: 'docker' } } [Event Logged] - workspace_documents_added [OllamaEmbedder] Embedding 1 chunks of text with nomic-embed-text:latest. [Error: Failed to execute query stream: lance error: LanceError(IO): Query vector must have non-zero length, /home/build_user/.cargo/registry/src/index.crates.io-6f17d22bba15001f/lance-0.12.1/src/dataset/scanner.rs:434:17] { code: 'GenericFailure' }
yindo changed title from [BUG]: Could not respond to message. LanceDBError: LanceError(IO): Query vector must have non-zero length to [GH-ISSUE #971] [BUG]: Could not respond to message. LanceDBError: LanceError(IO): Query vector must have non-zero length 2026-06-05 14:36:11 -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#592
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?