Motivation

Part curiosity — I like gardening, math, geology, history, psychology, and now this. Part continued employment. I don’t shine at working faster or adopting the coolest tools. I am, however, capable of thinking critically and asking why, even when it bothers everyone else.

AI will disrupt the technology landscape. It’s also opening opportunities. We have to figure out what they are.

Software engineers don’t work the way they did five years ago. Five years ago I was reprojecting maps in tile servers. Today I develop data pipelines for robotic applications. I want to be ready for whatever comes next.

Ollama lets you run large language models locally with a single command.

Quick start

ollama run llama3

Why local?

• No API keys or rate limits.
• Data stays on your machine.
• Works offline.

Models I use

• llama3 — general purpose
• codellama — code generation
• nomic-embed-text — embeddings for vector search

ChromaDB is an embedding database for building search and retrieval systems.

How I use it

I chunk documentation (VyOS, Hugo) into paragraphs, embed them with nomic-embed-text via Ollama, and store the vectors in ChromaDB for semantic search.

Stack

Documents → Chunker → Ollama embeddings → ChromaDB → Query API

Key concepts

• Collection: a named group of embeddings (like a table).
• Document: the raw text stored alongside the vector.
• Metadata: key-value pairs for filtering results.