[GH-ISSUE #3196] [BUG]: [OllamaProcessManager] Cannot boot Ollama - linux is not supported. #2056

Closed
opened 2026-02-22 18:27:58 -05:00 by yindo · 4 comments
Owner

Originally created by @FY21TH on GitHub (Feb 13, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3196

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

when I startup AnythingLLM desktop app in docker on Centos7

I encounter the issues like this

Image

but I can use Ollama server.

Are there known steps to reproduce?

No response

Originally created by @FY21TH on GitHub (Feb 13, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3196 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? when I startup AnythingLLM desktop app in docker on Centos7 I encounter the issues like this ![Image](https://github.com/user-attachments/assets/e75b9e4e-37af-436e-b9d9-962f8325760a) but I can use Ollama server. ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:27:58 -05:00
yindo closed this issue 2026-02-22 18:27:58 -05:00
Author
Owner

@timothycarambat commented on GitHub (Feb 13, 2025):

Correct, we dont boot ollama on linux for desktop because we dont pre-bundle it in the linux build. You can install ollama locally and connect to it in AnythingLLM and it will work functionally the same.

@timothycarambat commented on GitHub (Feb 13, 2025): Correct, we dont boot ollama on linux for desktop because we dont pre-bundle it in the linux build. You can install ollama locally and connect to it in AnythingLLM and it will work functionally the same.
Author
Owner

@m17306 commented on GitHub (May 12, 2025):

Hi, I'm a noobie and excited about AnythingLLM but only half way there. I have installed ollama in Fedora 40. It runs by itself in the terminal ok. I have installed AnythingLLM and I can have basic chats with it. I don't know if it has partial use of ollama or is running stand alone. Because adding local docs do not seem to be seen for RAG. I get the dreaded "Error downloading model" and "Internal server error" And Ollama is running and Ollama server is running from what I can tell in terminal. But in the linux terminal I also get this when starting up: "Cannot boot Ollama - no executable found in /home/m/AnythingLLMDesktop/anythingllm-desktop/resources/ollama/llm"
I tried to create the missing ollama directory and copy and paste the executable into it but no go. I don't know what's missing here. I have spent a lot of time searching the net on this but can't fix it yet.

@m17306 commented on GitHub (May 12, 2025): Hi, I'm a noobie and excited about AnythingLLM but only half way there. I have installed ollama in Fedora 40. It runs by itself in the terminal ok. I have installed AnythingLLM and I can have basic chats with it. I don't know if it has partial use of ollama or is running stand alone. Because adding local docs do not seem to be seen for RAG. I get the dreaded "Error downloading model" and "Internal server error" And Ollama is running and Ollama server is running from what I can tell in terminal. But in the linux terminal I also get this when starting up: "Cannot boot Ollama - no executable found in /home/m/AnythingLLMDesktop/anythingllm-desktop/resources/ollama/llm" I tried to create the missing ollama directory and copy and paste the executable into it but no go. I don't know what's missing here. I have spent a lot of time searching the net on this but can't fix it yet.
Author
Owner

@halcyonsys commented on GitHub (May 18, 2025):

It's not that obvious from the UI but you don't use the 'Anything LLM' AI provider.

Search for Ollama on the 'Search all LLM providers' popup. You can then select 'Ollama (Run LLMs locally on your own machine)', which will then use the Ollama standalone server you are running.

@halcyonsys commented on GitHub (May 18, 2025): It's not that obvious from the UI but you don't use the 'Anything LLM' AI provider. Search for Ollama on the 'Search all LLM providers' popup. You can then select 'Ollama (Run LLMs locally on your own machine)', which will then use the Ollama standalone server you are running.
Author
Owner

@ml-w commented on GitHub (Jul 17, 2025):

I am not using Ollama provider but Local AI provider but somehow it consistently tries to boot ollama and the error popup are quite annoying despite I can use chat and embedding normally, am I missing something?

@ml-w commented on GitHub (Jul 17, 2025): I am not using Ollama provider but Local AI provider but somehow it consistently tries to boot ollama and the error popup are quite annoying despite I can use chat and embedding normally, am I missing something?
yindo changed title from [BUG]: [OllamaProcessManager] Cannot boot Ollama - linux is not supported. to [GH-ISSUE #3196] [BUG]: [OllamaProcessManager] Cannot boot Ollama - linux is not supported. 2026-06-05 14:44:16 -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#2056