[GH-ISSUE #3030] [BUG]: can't select any local model from AnythingLLM after removing a model using command "ollama rm " #1937

Closed
opened 2026-02-22 18:27:19 -05:00 by yindo · 1 comment
Owner

Originally created by @daviddalao on GitHub (Jan 26, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3030

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

After I removed a local model using the command "ollama rm nezahatkorkmaz/deepseek-v3: latest", I recieved an message saying something like "Could not respond to message, nezahatkorkmaz/deepseek-v3: latest is not available" no matter which other loaded model I selected.

Are there known steps to reproduce?

No response

Originally created by @daviddalao on GitHub (Jan 26, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3030 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? After I removed a local model using the command "ollama rm nezahatkorkmaz/deepseek-v3: latest", I recieved an message saying something like "Could not respond to message, nezahatkorkmaz/deepseek-v3: latest is not available" no matter which other loaded model I selected. ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:27:19 -05:00
yindo closed this issue 2026-02-22 18:27:19 -05:00
Author
Owner

@timothycarambat commented on GitHub (Jan 27, 2025):

After I removed a local model using the command "ollama rm nezahatkorkmaz/deepseek-v3: latest", I recieved an message saying something like "Could not respond to message, nezahatkorkmaz/deepseek-v3: latest is not available" no matter which other loaded model I selected.

Did you change the model selection in AnythingLLM? Changing or removing models in your external ollama CLI has zero impact on what model we have set in AnythingLLM. The two programs are not linked.

You removed the model in ollama, but had it set in AnythingLLM, so when you use AnythingLLM we expect the same model to be there.

Make sure the system LLM is Ollama+ the model you desire.

Image

Also if you happen to set this as a workspace setting model - you'll want to unset that.

Image
@timothycarambat commented on GitHub (Jan 27, 2025): > After I removed a local model using the command "ollama rm nezahatkorkmaz/deepseek-v3: latest", I recieved an message saying something like "Could not respond to message, nezahatkorkmaz/deepseek-v3: latest is not available" no matter which other loaded model I selected. Did you change the model selection in _AnythingLLM_? Changing or removing models in your external `ollama` CLI has zero impact on what model we have set in AnythingLLM. The two programs are not linked. You removed the model in ollama, but had it set in AnythingLLM, so when you use AnythingLLM we expect the same model to be there. Make sure the system LLM is Ollama+ the model you desire. <img width="1612" alt="Image" src="https://github.com/user-attachments/assets/507a08d7-0a79-4a43-bb1c-00e0235b1658" /> Also if you happen to set this as a workspace setting model - you'll want to unset that. <img width="1612" alt="Image" src="https://github.com/user-attachments/assets/7c2eb094-e306-4e85-9c7e-5d17590564f8" />
yindo changed title from [BUG]: can't select any local model from AnythingLLM after removing a model using command "ollama rm " to [GH-ISSUE #3030] [BUG]: can't select any local model from AnythingLLM after removing a model using command "ollama rm " 2026-06-05 14:43:34 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1937