shubham0204/OnDevice-RAG-Android

A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android

47
/ 100
Emerging

Combines on-device embeddings (all-MiniLM-L6-v2), vector storage via ObjectBox, and custom whitespace-based text chunking with configurable overlap, enabling fully local RAG without cloud dependencies. Supports both remote inference (Gemini API) and local LLM execution via MediaPipe's GenAI API, with models downloadable from HuggingFace's litert-community. Built with modern Android architecture patterns and integrates Apache POI and iTextPDF for multi-format document parsing.

178 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

178

Forks

21

Language

Kotlin

License

Apache-2.0

Last pushed

Jan 03, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/shubham0204/OnDevice-RAG-Android"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.