1. Establish Isolated Knowledge Libraries
Organize your work by creating isolated Knowledge Libraries for different projects (e.g., Q1 Financials, Thesis Research). Drag and drop PDFs, TXT files, Markdown notes, images with embedded text, or direct web captures. Each library remains mathematically separated in the local app database.
2. On-Device Chunking and Vectorization
Once imported, the app splits your documents into short paragraphs. It then runs a local embeddings model to map the meaning of each section and saves these in your device's secure SQLite database. No servers, no accounts, and no data leaks.
3. Local Semantic Context Retrieval (RAG)
When you ask a question, the app does a fast, offline semantic search across your library to find the exact pages that match. This lets you query thousands of pages in seconds, on device, without needing a high-bandwidth connection.
4. Grounded Local Reasoning
The retrieved document chunks are appended directly into the local LLM prompt as ground-truth context rules. This dramatically reduces model hallucination and guides the local AI to draft precise, highly cited summaries, compare conflicting paragraphs, or conduct broad-spectrum Q&A safely.