Rich Hein writes about transforming an inexpensive mini PC into a private, local LLM system designed to index and search personal documents for his household. By using tools like Ollama, Open WebUI, and Syncthing, he created a way for family members to query their digital files—such as bills or manuals—using natural language from any device on the home network without sending sensitive data to the cloud.
- The setup uses Gemma 3 12B running via Ollama on an AMD Ryzen 5 7640HS mini PC.
- Syncthing is used to automatically sync a specific "AI-Search" folder across multiple devices in the house.
- A custom PowerShell script acts as a file watcher to automatically feed new files into Open WebUI's Knowledge Base via API.
- Current search speeds are approximately one minute per query due to using integrated graphics rather than a dedicated GPU.
- The setup uses Gemma 3 12B running via Ollama on an AMD Ryzen 5 7640HS mini PC.
- Syncthing is used to automatically sync a specific "AI-Search" folder across multiple devices in the house.
- A custom PowerShell script acts as a file watcher to automatically feed new files into Open WebUI's Knowledge Base via API.
- Current search speeds are approximately one minute per query due to using integrated graphics rather than a dedicated GPU.
An AI-powered document search agent that explores files like a human would — scanning, reasoning, and following cross-references. Unlike traditional RAG systems that rely on pre-computed embeddings, this agent dynamically navigates documents to find answers.
The article explores whether combining a command-line agent (like Claude Code or Gemini CLI) with Unix-like file system tools and SemTools is sufficient for complex tasks, particularly document search. It details a benchmark testing the limits of coding agents with and without SemTools, focusing on search, cross-referencing, and temporal analysis. The conclusion is that CLI access is powerful and SemTools enhances agent capabilities for document search and RAG.
