ryanfreckleton

This option needs to be documents.

Sure! Apologies for the late response. I’ll post right before I start implementing, in case anyone else wants to take it on.

I've got a branch that reduces this startup time to about a third of what it is by using a memoize decorator. The big culprit is running `conda info --json`,...

Sorry it took me a while to get back to this: I've got a fork at https://github.com/ryanfreckleton/vim-conda/tree/develop which has the modifications to use a caching system which gives quite good...

Awesome, thanks! I will :)

Pull-request open at https://github.com/cjrh/vim-conda/pull/24 I'd like at least one other person to look at it and someone to test it on windows before I merge.

Merged. Could someone on windows please test to see if performance increases?

For what it's worth, litellm seems to be an OpenAI style API wrapper around multiple LLMs, include Claude Opus. https://github.com/BerriAI/litellm/

Probably https://github.com/kagisearch/vectordb would be a better fit than Chroma or the other systems. I've had some success with other experiments running HTML documentation through html2markdown and then summarizing it into...