Launching today
Self-Hosted RAG with Llama 3
100% offline RAG for engineers who can't use cloud AI
1 follower
100% offline RAG for engineers who can't use cloud AI
1 follower
A Dockerized RAG system built with Ollama, ChromaDB, and Streamlit — for engineers handling sensitive documents (datasheets, specs, NDAs) that can't be pasted into ChatGPT. No cloud dependency. No API fees. No data leaving your machine. Ask questions about your technical docs in plain English, get answers grounded in your own files. Built for controls engineers, automation teams, and anyone who needs a private alternative to cloud AI tools for document Q&A.
Hey Product Hunt 👋
I'm Phil, a Senior Automation Engineer working in industrial automation. I built this because I kept running into the same problem: engineering docs, datasheets, and specs that I couldn't paste into ChatGPT due to NDA restrictions — but I still wanted AI-assisted search over them.
So I built a fully offline RAG stack: Docker + Ollama (running Llama 3) + ChromaDB for vector search + Streamlit for the UI. No API calls, no data leaving your machine, no monthly fees.
It's built for engineers, technical writers, or anyone who works with sensitive documents and wants local AI search without the cloud dependency.
Happy to answer any technical questions — how it handles PDFs, context window limits, deployment on different hardware, whatever you're curious about. And if you've tried something similar, I'd love to hear what worked (or didn't) for you.