The Ultra-lightweight, Offline RAG for Low-Spec PCs. No Docker. No Vector DB. No Node.js. Just pure Python + BM25 + Vanilla JS.
Ask questions about your documents. Everything runs on your machine — no cloud, no accounts, no data leaving your device.
Why choose LocalSift?
- 🪶 Featherweight: Runs on a 4GB RAM laptop. Extraction happens in memory.
- 🔒 Privacy-First: 100% offline. Connects only to local LLMs (Ollama/KoboldCpp) via
127.0.0.1. - 🧠 Smart Retrieval: Uses a custom BM25 algorithm in pure JS instead of heavy Vector Databases.
- 🎯 Relative Filtering: Automatically discards irrelevant document chunks that fall below 50% of the best BM25 score.
- 📄 Multi-format: Reads PDF, ODT, DOCX, TXT, MD, CSV.
- Download the latest release
LocalSift-v1.1.1.zipfrom the Releases page and extract it. - Start Ollama (or KoboldCpp) on your machine.
- Run LocalSift:
- Double-click
LocalSift.desktop(Linux) - Or run
bash start_localsift.shin your terminal.
- Double-click
- Open your browser at
http://127.0.0.1:8200/index.html.
- Upload: The Python backend extracts text from your files using standard libraries (and
pypdf). - Search: The frontend uses BM25 to find the most relevant paragraphs.
- Filter: Only the fragments that score above the relative threshold are passed to the AI.
- Generate: The local LLM answers using only the provided context, with strict anti-hallucination guardrails.
Issues and pull requests are welcome! Please check the .github folder for templates. Multilingual documentation improvements are especially appreciated.