Vecy

Vecy is an Android AI app made for anyone who wants to chat with powerful language models without giving up their privacy. It lets you talk with fully-private LLMs and with the files stored on your own phone, including documents and photos, so your personal data never has to leave your device.

The app quietly does the heavy lifting for you: it automatically processes and indexes local files on your phone, and you can also upload files directly whenever you need to. To make every conversation more useful, Vecy offers RAG tools for processing local files, which enhance the quality and relevance of the LLM's responses.

You can choose from a range of small LLMs, from 0.5B to 3.5B parameters, and engage in natural conversations with documents stored locally. Whether you want to ask questions about a report, dig through your downloads, or explore your photos, the answers stay grounded in your own files while everything remains on your device.

Vecy automatically processes files such as PDFs, DOCX documents, and images found in 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, boosting the LLM's ability to provide more accurate and relevant responses whenever your questions relate to the local files on your phone.