what is lumen fr?

Lumen is a desktop app for Windows that lets you chat with your own PDF documents and get answers pulled directly from them, instead of searching through the files by hand. You can load several PDFs into a session at once, add more files one at a time without losing what you already loaded, and remove individual files from a checklist in the sidebar whenever you want. When Lumen answers a question, it tells you exactly which file and page number the answer came from, so you can check the source yourself. The app can run in two modes: an online mode that uses a cloud based AI service, and an offline mode that keeps everything on your own computer. In offline mode, the system that turns your documents into searchable data runs locally using a small model called all-MiniLM-L6-v2, so your files and their contents never have to leave your PC. This approach is known as retrieval augmented generation, a technique where the AI looks up relevant pieces of your documents before answering, rather than relying only on what it already knows. For Windows users who do not want to set up Python, the project offers a ready made executable file you can download from the Releases page and run immediately. For anyone who wants to run it from source, the README walks through cloning the repository, creating a Python virtual environment, installing the required packages, and adding an API key to a configuration file if you want to use the online mode. The README also shows how to package the app into a single standalone Windows executable using a tool called PyInstaller. The interface is built with CustomTkinter, a library for building desktop windows and menus, and the document search backend uses LangChain along with a local database called ChromaDB to store and search the document data. The README does not state a license for this project.