vincentkoc/airgapped-offfline-rag

Secure, locally-run Retrieval-Augmented Generation system for document-based question-answering, utilizing Llama 3, Mistral, and Gemini models with a user-friendly Streamlit interface.

55
/ 100
Established

Leverages llama.cpp for CPU-optimized inference of quantized GGUF models, with LangChain orchestrating the RAG pipeline and ChromaDB storing document embeddings via Sentence Transformers. Supports streaming responses and configurable model selection, with Docker containerization for reproducible deployment across environments.

No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

80

Forks

25

Language

Python

License

GPL-3.0

Last pushed

Feb 16, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/vincentkoc/airgapped-offfline-rag"

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