I developed a desktop application that automates the full document processing pipeline. The app scans documents via SANE-compatible scanners, extracts text with OCR, analyzes content using a local LLM (qwen2.5:14b via Ollama), normalizes article names via Elasticsearch, and stores structured data in MySQL and CouchDB. Users can visualize results in Kibana and interact with the application through a Tkinter GUI. The project is fully containerized with Docker for easy deployment and cross-platform compatibility.