[BUG]: Error after embedding document ""Could not respond to message" about anything-llm HOT 7 CLOSED

If this is happening with every LLM model you are using to try and chat, it sounds like this is probably an issue with Windows Server firewall blocking the connection to whatever model you are using. You will need to investigate and see if your firewall settings are blocking you.

from anything-llm.

Thanx @shatfield4 but firewall is disabled. Without embedding documents all models work fine. So IMHO it seems that is has to do with the embedding model.

If I choose another embedder (e.g. Ollama instead of AnyghingLLM) in the preferences it a) takes much longer to embed a document and b) I get a different error: "Could not respond to message. LanceDBError: No vector column found to create index".

from anything-llm.

That response would typically indicate that the embedder failed to embed the content. With the default embedder can you send a chat on a brand new workspace with no documents? That should have no embedder call required.

Next, I would open C:\Users\user\AppData\Roaming\anythingllm-desktop\storage and see if there is a folder with files in it named storage\models\Xenova\ and there should be a subfolder for all-miniLM-l6 or something to the effect.

from anything-llm.

Thanks @timothycarambat!

With the default embedder can you send a chat on a brand new workspace with no documents? That should have no embedder call required.

If I set the default embedder and make a brand new chat with no documents, there is no error message.

Next, I would open C:\Users\user\AppData\Roaming\anythingllm-desktop\storage and see if there is a folder with files in it named storage\models\Xenova\ and there should be a subfolder for all-miniLM-l6 or something to the effect.

This folder exists. But I don´t understand what it indicates or what do do with it. Should I delete it? It has not created along with the brand new workspace though.

Thanks again for your support and your efforts on AnythingLLM!

from anything-llm.

lets try deleting the Xenova folder and then try to re-embed a file on a fresh and empty workspace. Be sure to close and re-open app after deleting that folder. Please test a smaller text file just to limit variables in debugging. The embedder downloads on the first use so it does not bloat the app if unused. Its only 25MB so it should not take long, however if it still fails then there is a possibility the MSFT C++ Distributable might not be installed on your system - which is possible, but really unlikely but it has happened before.

https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170#latest-microsoft-visual-c-redistributable-version

from anything-llm.

lets try deleting the Xenova folder and then try to re-embed a file on a fresh and empty workspace. Be sure to close and re-open app after deleting that folder. Please test a smaller text file just to limit variables in debugging.

Did that. Same error.

however if it still fails then there is a possibility the MSFT C++ Distributable might not be installed on your system - which is possible, but really unlikely but it has happened before.

I had MS Visual C++ installed, reinstalled vc_redist.x64.exe though but error still occurs after deleting the "Xenova" and re-embedding in a fresh and empty workspace.

from anything-llm.

Hey, i got the exact same error as LLMuser.

I don't get why the ticket have been closed since the error is still there

from anything-llm.