VaultAI
An AI chatbot plugin for Obsidian using the Gemini API for note summarization, content generation, and more. Enhance your workflow with AI assistance like the Notion AI bot.
Install / Use
/learn @0xneobyte/VaultAIREADME
VaultAI - AI Writing Assistant for Obsidian
<a href="https://deepwiki.com/0xneobyte/VaultAI">
<img alt="Ask DeepWiki" src="https://deepwiki.com/badge.svg" />
</a>
Transform your note-taking with an intelligent AI writing assistant powered by Google's Gemini AI. VaultAI brings deep editor integration, custom prompts, and seamless content generation directly to your Obsidian workspace.
Key Features
- 🧠 RAG (Retrieval Augmented Generation) - Search across your entire vault with AI-powered semantic search using Google's Gemini File Search API. Ask questions and get answers grounded in your notes with citations
- ⚙️ Model Configuration - Fine-tune AI responses with customizable temperature, top-K, top-P, and token limits (Configuration Guide)
- Deep Editor Integration - AI responses insert directly at your cursor position with real-time context awareness
- Custom Prompts System - Create reusable prompts with smart placeholders for repeated workflows
- Keyboard Shortcuts - Access all features via hotkeys and Command Palette integration
- Modern Interface - Sleek, resizable chat interface with full-page mode
- Secure & Private - Your API key and chat history stay local in your vault
Quick Start
Installation
- Install from Obsidian Community Plugins by searching "VaultAI"
- Get your Gemini API key from Google AI Studio
- Configure the API key in Settings → VaultAI
Basic Usage
- Press
Ctrl/Cmd+Shift+Vto toggle chat - Click the pin button to enable Insert Mode for cursor-based insertion
- Use Command Palette (
Ctrl/Cmd+P) for quick AI commands
🧠 RAG - Vault-Wide AI Search
Transform your entire vault into an AI-powered knowledge base! VaultAI now supports RAG (Retrieval Augmented Generation) using Google's Gemini File Search API.
How It Works
VaultAI indexes your vault and uses semantic search to find relevant notes when you ask questions. The AI then provides answers grounded in your actual notes with citations.
Setup RAG
- Open Settings → VaultAI → RAG Settings
- Toggle "Enable RAG" to ON
- Choose folder to index (use
/for entire vault) - Click "Sync Now" and wait for completion
- In chat, click the 🧠 button to enable RAG mode
Features
- Smart Sync - Only uploads new or modified files
- Flexible Indexing - Index entire vault or specific folders
- Citation Support - Responses indicate sources from your vault
- Progress Tracking - Real-time sync status updates
Note: Inspired by Discussion #22 - turning your vault into something like Google Notebook LM!
Documentation
For comprehensive guides, examples, and troubleshooting:
- Installation Guide
- Getting Started
- Deep Editor Integration
- Custom Prompts Guide
- Keyboard Shortcuts
- Troubleshooting
Requirements
- Obsidian v0.15.0 or higher
- Google Gemini API key (free tier available)
Support
If you find this plugin helpful:
Contributing
Contributions are welcome! Please see our Contributing Guide for details.
License
MIT License - see LICENSE file for details.
Made by Neo
<p><a href="https://www.buymeacoffee.com/0xneobyte"> <img align="left" src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" width="150" alt="0xneobyte" /></a></p><br><br>Related Skills
apple-reminders
347.6kManage Apple Reminders via remindctl CLI (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.
notion
347.6kNotion API for creating and managing pages, databases, and blocks.
openhue
347.6kControl Philips Hue lights and scenes via the OpenHue CLI.
sag
347.6kElevenLabs text-to-speech with mac-style say UX.
