Graph RAG

unlisted

by Ripnrip

Interactive GPU-accelerated graph visualization with Graph RAG — ask questions about your vault using knowledge graph-enhanced retrieval.

Updated 2mo agoMIT
View on GitHub

Graph RAG for Obsidian

GPU-accelerated knowledge graph visualization with Graph RAG

Graph RAG for Obsidian Banner

TypeScript React License Portfolio

🚀 Overview

An interactive, GPU-accelerated knowledge graph visualization with Graph RAG (Retrieval-Augmented Generation) for Obsidian. Powered by cosmos.gl.

🧠 How Graph RAG Works

Graph RAG Architecture

Graph RAG combines vector similarity search with knowledge graph traversal to provide richer, more contextual answers from your vault. Instead of just finding notes that are semantically similar to your question, it also explores the connections between those notes to synthesize comprehensive answers.

✨ Features

  • GPU Rendering: Handles massive vaults smoothly via cosmos.gl
  • Local Indexing: SQLite-backed vector embeddings
  • Contextual Chat: Ask your vault questions and get cited, graph-aware answers

For plugin developers

Search results and similarity scores are powered by semantic analysis of your plugin's README. If your plugin isn't appearing for searches you'd expect, try updating your README to clearly describe your plugin's purpose, features, and use cases.