Airgapped Offline RAG
Run LLMs Locally with Llama, Mistral, & Gemini. 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. I've built an airgapped Retrieval-Augmented Generation (RAG) system for question-answering on documents, running entirely offline with local inference.
Open source
Reactions (1)
Similar products
by description similarity
Demystifying Advanced RAG Pipelines
github.comAn LLM-powered advanced RAG pipeline built from scratch
Alerting in realtime RAG
github.comspot changes to LLM answers, using few tokens
Text-To-Speech, RAG, and LLMs. All local!
RAGless
github.comsimilar to RAG, but $0 LLM API costs at runtime
RAGatouille
github.coma simple lib to use&train top retrieval models in RAG apps