Build a RAG chatbot on your own laptop with Ollama and pgvector
Index your own docs, store embeddings in Postgres, and answer questions with a local model. No API keys, no cloud bill, about an hour of work.
Hands-on tutorials, honest tool comparisons and founder stories, written by the people who teach our courses.
Index your own docs, store embeddings in Postgres, and answer questions with a local model. No API keys, no cloud bill, about an hour of work.
Route OpenAI-compatible calls to local and hosted models through one endpoint, with keys and logs in one place.
All three run open models on your own machine. Here is where each one fits, where it gets in your way, and how to choose in five minutes.
A small VPS, Docker and a reverse proxy are enough to host every internal tool a two-person startup needs. Here is the weekend plan.
Notes from Hour 07: resource naming, streaming responses and versioning when model outputs change shape.
Notes from Hour 01 of Learning Development with AI: where AI speeds you up, and the skills that matter more than ever.
Every tutorial on this blog comes from a lesson in one of these courses. Take the full path when you want structure, projects and feedback.
Plan, build, test and ship AI-powered apps with a modern open-source stack.
Set up the server, tools and automations a small company runs on, without a big team.