Comments (7)
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 namedstorage\models\Xenova\
and there should be a subfolder forall-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.
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.
Related Issues (20)
- [FEAT]: Add support for TSX files as text files. HOT 1
- [BUG]: OpenAI::CreateModeration failed with: Request failed with status code 403 HOT 1
- [BUG]: UI bug fixes
- [FEAT]: Add speech-to-text prompting possibility activated with a key combination
- [BUG]: Failed to vectorize file HOT 1
- Is there a limit to the content length of the application's ability to crawl the site? Is the crawling content accurate and comprehensive? Because I need to extract the information from the text accurately and that's very important HOT 1
- [FEAT]: Rename "New thread" when thread is created
- [BUG]: Could not respond to message. fetch failed HOT 8
- Can AI agents' RAG Search find all the contents of the workspace document HOT 1
- [FEAT]: Add searXNG to the list of live web searching and browsing HOT 2
- Add the ability to upload an image to the AI. [FEAT]: HOT 1
- [BUG]: Could not respond to message. fetch failed HOT 2
- [BUG]: Unable to Move Window on M1 MacBook Pro (v12.5.1) HOT 2
- [BUG]: agent and llama3 HOT 3
- [BUG]: can't delete database connection of SQL agent
- [BUG]: File upload dialog has 32k chars string length limit, preventing users from bulk-importing thousands of files
- [BUG]: unable to login after deploy HOT 1
- [FEAT]: Progress report for embeddings
- [BUG]: 10 - 20% gpu being used when embedding files into anything llm in win desktop manager HOT 3
- Can AnythingLLM support langchain API calls? HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from anything-llm.