your-papa/obsidian-Smart2Brain
An Obsidian plugin to interact with your privacy focused AI-Assistant making your second brain even smarter!
What it solves
This plugin transforms Obsidian notes into a "smart second brain" by allowing users to interact with their personal knowledge base using an AI assistant. It eliminates the need for manual prompt editing by giving the AI direct access to the user's notes, while offering a privacy-focused approach that can operate completely offline.
How it works
The project implements a Retrieval-Augmented Generation (RAG) pipeline. It embeds your notes into vectors and retrieves the most relevant sections based on the similarity to your query. The AI then generates answers based on these retrieved notes, providing reference links back to the original Obsidian notes for traceability.
Who it’s for
Obsidian users who want to leverage LLMs to query their personal knowledge base, specifically those who prioritize data privacy and the ability to run models locally via Ollama.
Highlights
- Local-First AI: Supports Ollama for completely offline, private AI interactions.
- RAG Integration: Automatically retrieves relevant notes to ground AI responses in your own data.
- ** uma own data.**
- Flexible LLM Choice: Compatible with both local models and OpenAI's ChatGPT.
- Traceable Answers: Provides Obsidian links as references to the source notes used in the answer.
- Customizable UI: Offers 'comfy' and 'compact' chat views for different user preferences.