AI-RAG-Bot — chat with your documents. 100% local, 100% private, $0 to run
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built AI-RAG-Bot is a local "chat with your documents" assistant: drop files into a folder, ask questions in your terminal, and get answers grounded strictly in those files. It reads .txt , .pdf , and images — and for scanned PDFs and photos of documents, it runs OCR (Tesseract + OpenCV), so even a…
AI-RAG-Bot is a locally-hosted Retrieval-Augmented Generation (RAG) system designed for intelligent document question answering. It allows users to drop files into a folder and ask questions in their terminal to receive answers grounded strictly in those files. The system supports .txt, .pdf, and image formats, with OCR capabilities for scanned PDFs and photos of documents. This makes even a photographed receipt searchable knowledge.
The AI-RAG-Bot project is built using open-source components like Ollama, ChromaDB, PyMuPDF, OpenCV, Tesseract OCR, and the all-MiniLM-L6-v2 model from sentence-transformers. It processes documents, creates vector embeddings, stores them locally, and leverages an LLM to generate answers. The entire pipeline is open-source, enabling users to swap models or embedders with ease.
Key benefits include privacy, cost-efficiency, and offline functionality. Since no sensitive data leaves the laptop, it offers a secure alternative to cloud-based AI services. Additionally, running everything locally removes the need for per-query API bills, making it a $0/month solution. The project also emphasizes freedom of choice, allowing users to easily swap models or embedders as needed.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
