Vecy: On-device AI & LLM APP for RAG
FreePrivate AI chat with local files on Android
About Vecy: On-device AI & LLM APP for RAG
Vecy is an Android AI app that allows users to chat with fully-private LLMs and local files (documents, photos). It automatically processes and indexes local files on the phone, and users can also directly upload files. Vecy offers RAG tools for processing local files to enhance LLM responses. 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.
How to Use
Install the Vecy app on your Android device. The app automatically processes files in the Documents, Download, and DCIM directories. You can also upload files directly. Select an LLM and start chatting with your local files.
Key Features
- Chat with fully-private LLMs
- Process and index local files automatically
- Direct file upload
- RAG tools for enhanced LLM responses
- Image search
Use Cases
- Chatting with local documents and images using a private LLM.
FAQ
What is RAG and how does Vecy use it? NoFilterGPT Unfiltered, uncensored, anonymous AI chat service with absolute privacy.
Key Features
Pros & Cons
- Fully private: all data processing and storage happens locally on the device
- RAG integration retrieves relevant file context for more accurate answers
- Supports multiple file formats including PDF, DOCX, and images
- Works offline once models are downloaded (no internet needed for inference)
- Direct file upload and automatic directory scanning for ease of use
- Limited to Android operating system
- Relies on small parameter LLMs (0.5B–3.5B) which may not match larger models in performance
- Automatic file indexing may consume device storage and battery
- No cloud backup or synchronization
Best For
Alternatives to Vecy: On-device AI & LLM APP for RAG
ReActGPT
Enhance LLM accuracy with thought-action-observation training
servisbot.com
Hybrid Agentic AI Designed Around Human Control
GPT Duel
Watch GPT models argue with each other
adversa.ai
Ship AI without shipping risk
eLLMo - Enterprise Lg Language Model Ops
Private LLM with RAG for Enterprise
Airbyte
The Context Layer for AI Agents