Hasty Briefsbeta

Show HN: Offline RAG System Using Docker and Llama 3 (No Cloud APIs)

3 hours ago
https://github.com/PhilYeh1212/Local-AI-Knowledge-Base-Docker-Llama3
Copy Link
  • #Local AI
  • #RAG
  • #Docker
  • BLACK FRIDAY SALE: 15% OFF all source codes with code BLACKFRIDAY.
  • Production-grade, 100% offline RAG architecture for chatting with proprietary documents (PDF, TXT, Markdown) using a local LLM.
  • Microservices architecture, fully containerized with Docker Compose for one-click deployment.
  • Components include Ollama (Meta Llama 3 8B), mxbai-embed-large embeddings, ChromaDB vector database, Python + Streamlit backend/frontend.
  • Features: 100% privacy, GPU acceleration (NVIDIA CUDA), smart ingestion, context-aware chat, one-click setup.
  • Recommended hardware: Windows 10/11 (WSL2) or Linux (Ubuntu), 16GB+ RAM, NVIDIA RTX 3060 (8GB VRAM) or higher.
  • Includes complete source code, Docker configuration, setup guide, and premium support.
  • Available for one-time payment on Gumroad with lifetime usage.
AboutLogin