llabusch93/ObsidianRAG

ObsidianRAG MCP Server

A high-performance, Docker-based RAG (Retrieval-Augmented Generation) server designed to turn your local Obsidian vault into an intelligent, queryable knowledge base.

This server acts as a long-term memory, allowing you to perform semantic searches and ask complex questions about your own notes. It's built to be used as a secure, local MCP (Model Context Protocol) tool with the Gemini CLI.

---

Features

• 🧠 Intelligent Search: Uses Google's state-of-the-art text-embedding-004 model to understand the meaning of your notes, not just keywords.
• 🔒 Private & Secure: Your notes are indexed and stored in a local vector database. Only the text for embedding generation is sent to the Google API, and your API key is stored locally.
• 🚀 Optimized for Apple Silicon: The Docker container is explicitly built for the linux/arm64 architecture to ensure maximum performance on M-series Macs.
• 📦 Containerized & Simple: The entire application is managed via Docker Compose, making setup and teardown a breeze.
• 💾 Persistent Knowledge: The vector database is stored in a persistent Docker volume, so your knowledge base survives container restarts.
• 🔧 Dynamic Configuration: Easily configure the path to your Obsidian vault via an environment file.

Getting Started

These instructions will get you a copy of the project up and running on your local machine.

Prerequisites

• Docker (or an alternative like OrbStack)
• An active Google AI API Key. You can get one from Google AI Studio.

Installation

1. Clone the repository:

   git clone https://github.com/your-username/ObsidianRAG.git
   cd ObsidianRAG
   

2. Configure your environment:

   • Rename the example environment file:

     mv .env.example .env
     

   • Open the .env file with a text editor and add your Google API Key and the absolute path to your Obsidian vault.

     # Your Google AI API Key for generating embeddings
     GOOGLE_API_KEY="AIzaSy..."
     
     # The absolute path to your local Obsidian Vault directory
     OBSIDIAN_VAULT_PATH="/path/to/your/vault"
     

3. Build and run the server:

   • From the project's root directory, run the following command:

     docker-compose up --build -d
     

   • The first time you run this, Docker will build the image and download all dependencies. The server will then start in the background.
   • On the first launch, the server will begin indexing your entire vault. This may take a few minutes depending on the size of your vault. You can monitor the progress with:

     docker-compose logs -f
     

Usage

This server is designed to be used as a tool within the Gemini CLI.

1. Open your Gemini CLI settings.json file.

2. Add the following configuration to the "tools" array:

   {
     "tool_type": "MCP",
     "name": "obsidian_vault",
     "display_name": "Obsidian Vault",
     "description": "Queries my personal knowledge management system (Obsidian) for notes, concepts, and connections. Useful for complex questions based on my personal knowledge.",
     "url": "http://localhost:8000/mcp",
     "is_enabled": true
   }
   

3. Restart the Gemini CLI to apply the changes.

4. Query your knowledge base! You can now ask questions directly from the CLI:

   /tool obsidian_vault What are my most important notes on artificial intelligence?
   

   /tool obsidian_vault Summarize my thoughts on project management.
   

License

This project is licensed under the MIT License - see the file for details.