Robin Boone

It could also be the swapping from LLM to embedding model and back that makes it very slow see my PR #1800

I think my PR #540 offers a decent solution to this :)

> @TheR1D I thought there was a way for me to assign reviewers but I can't find it. The button appears on the top right of this page, but only...

> @Robinsane is this using custom commands like [here](https://docs.continue.dev/customization/slash-commands#custom-commands-use-natural-language)? We did recently change the format to be much more flexible, so that you will have to add the {{{ input...

For me it's very slow too, and I keep getting the error below after a certain amount of time: (posted at #1723) `chipgpt | Traceback (most recent call last): chipgpt...

This can be closed, using Ollama embeddings in my own project as we speak :)

Small update: It's not that random. Seems to happen with the same files each time.

I think it must somehow break on special characters? Since it happens to the same files each time... I inspected the Documents; the embedding field is always set to None...

I have a feeling Documents / pages must break because of a weird character? Next step is probably trying to convert the text field of failing Docs to e.g. UTF-8...

It's been fixed. No clue why though, could be any of the following: * restarting ollama * deleting and pulling the embedding model again * increasing my context window in...