longy2k / obsidian-bmo-chatbot

Generate and brainstorm ideas while creating your notes using Large Language Models (LLMs) from Ollama, LM Studio, Anthropic, OpenAI, Mistral AI, and more for Obsidian.
https://ko-fi.com/longy2k
MIT License
262 stars 32 forks source link

Feature request: Retrieval Augmented Generation (across all notes) #31

Open peterlionelnewman opened 6 months ago

peterlionelnewman commented 6 months ago

Adding retrieval to this plugin would be super powerful!

https://js.langchain.com/docs/get_started/introduction

Is something like this in the works? Potentially the chat interface could all for selection of the llm's access, with retrieval across: retrieval on current note, all of current note, retrieval across all notes, or no retrieval. this would also optimise token usage for the input on the current note.

Thanks for the great work

peterlionelnewman commented 6 months ago

Hello again, I found this plugin which implements retrieval to some degree that might be helpful: https://github.com/glovguy/obsidian-gpt-zettelkasten/tree/main

Thanks again,

christopher-harwell commented 5 months ago

This would be a really nice feature to have. Honestly, the only complaint I have is that I can't use my entire Vault for reference. Otherwise, it is a wonderful plugin. Thanks.