Build a Private RAG Pipeline For Free: No Cloud, No Data Leaks, No Limits
You already have the infrastructure. Here is how to put it to work.
Welcome, the OSINT Jobs team here.
In the last issue, we talked about getting Ollama and Open WebUI running locally. This issue picks up where that left off, namely using that setup to build a retrieval-augmented generation (RAG) pipeline.
RAG lets a local model answer questions using documents you provide rather than relying solely on its training data.
For investigative and intelligence work, that matters. You feed the model your source material, and it draws on that material to respond. The model does not reach the internet. The documents stay on your machine.
Missed last week?
Before we get into it, here is last week's tradecraft and industry news roundup:
OSINT Tradecraft Tips & Industry News
Everything you need to know from the past seven days.
Monetization Archive identifies and tracks monetized social media accounts on Facebook and Instagram | explore here | HT Aleksandra B.
GDELT will migrate its services to Google Spanner using Gemini 3 Pro for architectural design and development | read here
Researchers using CYGNSS satellites identified 85 GPS jammers in the Persian Gulf | explore here
