KhoPhi

This is something I'd be interested to see. Perhaps I could help with its implementation for use. Heck, I'd be interested to see Ollama and Qdrant approach as that is...

@zainhoda I'll take a shot at it, this week and see how it goes. Quickly, I see both examples you include above to be needing some form of API key....

Noted. Thanks for the heads up. Will get to it as soon as possible.

@zainhoda Running the script above gives me this response in my terminal, using phi (the model I have at the moment) ``` [{'role': 'system', 'content': 'The user provides a question...

I do not know if that's expected behavior.  I'm trying to use `llama2` and it's been running for 15 minutes plus now. cc @zainhoda > However, after the answer...

cc @zainhoda Using the Ollama Python Client in the `ollama/__init__.py` like so: ``` from ..base import VannaBase import ollama as OllamaClient class Ollama(VannaBase): def __init__(self, config=None): if config is None...

Running the Ollama appears to work well (on my machine so far). The issue I had from above: https://github.com/vanna-ai/vanna/issues/167#issuecomment-1922539899 no longer exists. Since you started with the `major-refactor` branch, I'd...

This appears to have been resolved, no? I see the `connect_to_sqlite` function in the `base.py` file

@Cam-B Any idea where one can track the bug for any updates? Edit: I've tried both the local AI and Ollama, for both the chatchain and embeddings and still get...

I re-installed a new WSL, and everything is working as expected, on GPU, no endpoint errors.