Exploring the possibilities of Obsidian Copilot with LM Studio.
I’m using the llama-3.2-3b-instruct model. After a few successful prompts in ‘vault QA’ mode, I get the (no status code or body) error.
The LM Studio console reports The number of tokens to keep from the initial prompt is greater than the context length.
With my limited understanding my guess is I need to clear some kind of cache or start with a clean context, but how do I do this? Or is it something else that’s causing this behavior?