Closed kjeldahl closed 4 weeks ago
Thanks for the issue! Adding a new environment variable to split Generation and Embedding Model for Ollama is definitely on the list. We'll look into that 🚀
I think this is a classic XY problem, because I see the error 'NoneType' object is not iterable
that seems to be plaguing many people. I don't think the immediate solution is to add more configuration, although that would be cool to have!
@chaos I have added a pull request which solves the problem, for me any way.
Part of the problem besides trying to chat with an embedding model was that I had not installed llama3
in ollama but llama3:instruct
which caused an error that was not reported in the ui.
@cha0s If I use llama3
it works for both chat and embedding without having separate models.
We seperated both in the newest release!
Description
When running Verba using docker compose with OLLAMA_MODEL set to
llama3
it is not possible add documents. It gives 404 on/api/embeddings
in the ollama server. And it is not possible to get a chat response as it gets a similar response from the ollama server. If I change the OLLAMA_MODEL tomxbai-embed-large
I can import documents and get chunks back as responses, but still no chat answer as 404 is returned on/api/chat
in the ollama server.Is this a bug or a feature?
Steps to Reproduce
Clone the project Add
to
.env
Rundocker compose up
Start ollama serverollama serve
Open http://localhost:8000 Enter something in chat and see it fail with'NoneType' object is not iterable
Also see error in ollama server log| 404 | 577.333µs | 127.0.0.1 | POST "/api/embeddings"
Try to import a document See a list of 404 on /api/embeddings in ollama server
Stop Verba Change OLLAMA_MODEL to
mxbai-embed-large
Startdocker compose up
Import a document and see a lot of 200 responses in ollama server Type something in chat See an ever loopingGenerating response
widget and a 404 on/api/chat
in ollama server Chunks are however returned.I think the solution is to be able to specify an embedding model along with the chat model.