Vecy APP offers tools for leveraging large language models (LLMs) directly on devices. Users can select from a range of small LLMs (from 0.5B to 3.5B parameters) and engage in conversations with documents stored locally. The app automatically processes files (PDFs, DOCX documents, images, etc.) within the Documents, Download, and DCIM directories to generate embedding vectors, which are stored locally on the device. These embedding vectors are crucial for RAG (retrieval-augmented generation) capabilities, enhancing the LLM's ability to provide more accurate and relevant responses when queries are related to the local files.