The Research Engine
Understanding how Vault Intelligence finds, ranks, and synthesizes information from your notes.
Hybrid Search Architecture
The Researcher uses a three-stage pipeline to ensure it finds relevant information even if you use different terminology than your notes.
GARS: Graph-Augmented Relevance Score
Most RAG (Retrieval-Augmented Generation) systems only look at similarity (text matching). Vault Intelligence adds two critical dimensions:
- Similarity: Does the note text match the query?
- Centrality: Is this note a "hub" or "authority" in your vault structure?
- Activation: Is this note connected to other relevant notes?
This ensures that a core definition note (e.g., "Project Alpha MOC") ranks higher than a random daily log mentioning "Project Alpha", even if the daily log has more keyword matches.
Privacy and processing
- Local Indexing: Your vault's search index is built and stored entirely on your device (
data/folder). - Cloud Reasoning: When you chat, only the relevant snippets of text (found by the local index) are sent to the Google Gemini API for answer generation.
- No Training: Data sent to the API is used strictly for generating the response and is not used to train Google's models.