Wandering RAG

by wandermyz

AI/Data & Knowledge RAG CLI Qdrant Notion Obsidian Apple Notes

Wandering RAG is a CLI tool for personal RAG that retrieves data from various sources like Notion, Obsidian, and Apple Notes. It stores the data in Qdrant and exposes it as an MCP server.

View on GitHub

Last updated: N/A

What is Wandering RAG?

Wandering RAG is a command-line tool designed for personal Retrieval Augmented Generation (RAG). It indexes and retrieves information from your personal notes and documents stored in various applications, making it accessible for question answering.

How to use Wandering RAG?

Install using uv pip install -e .. 2. Run a Qdrant server using Docker Compose. 3. Copy .env.example to .env and configure the paths to your Markdown folders or Obsidian vaults. 4. Use the CLI subcommands to index your data (e.g., ./wandering-rag md index) and run the MCP server (./wandering-rag mcp run-server). 5. Configure Claude Desktop to use the MCP server.

Key features of Wandering RAG

Indexes Markdown files
Supports Notion (WIP)
Exposes data as an MCP server
Uses Qdrant for vector storage
CLI interface

Use cases of Wandering RAG

Answering questions based on your personal notes
Integrating personal knowledge into AI assistants like Claude
Creating a searchable knowledge base from multiple sources
Quickly retrieving information from your notes via command line

FAQ from Wandering RAG

What is Qdrant?

Qdrant is a vector database used to store and search embeddings of your documents.

What is MCP?

MCP stands for Multi-Context Provider, a protocol used for integrating with AI assistants like Claude Desktop.

How do I configure the tool for Obsidian?

Specify the path to your Obsidian vault in the .env file.

Does it support other note-taking apps?

Currently, it supports Markdown files and Notion (WIP).

How do I update the index after making changes to my notes?

Run the appropriate index command (e.g., ./wandering-rag md index) to re-index your data.