Using Copilot for Obsidian with a local LLM and vector store

"There are now several Obsidian plugins available that allow you to use local LLMs instead of a commercial LLM provider", so PKM explorer tries Copilot for Obsidian plugin on his Windows laptop, because this plugin "not only offers the possibility to have a question and answer dialogue ... but also lets you [index your vault]... you can query the content... has three modes of operation:

• Chat — default conversation with the installed LLM
• Long Note QA — to ask questions about the active note in your vault
• Vault QA (beta) — to ask questions about all information in your vault, based on an indexed version of the vault... uses your entire vault as context"

It can also perform NLP on selected text.

It works with multiple LLM providers via API, as well as local LLMs via Ollama or LM Studio... "you can use a local embedding model to index your vault". The full article provides more detail on installation and configuration and then provides one example per mode - TL:DR; seems to be accurate, but slow on the mid-range laptop used:

• Long Note QA mode: several minutes
• Vault QA mode: ~9 minutes