Build a Personal Search Engine
Using Claude Code, pg_textsearch, and pgvector to build a powerful search engine.
Postgres now has two powerful ways to search:
- Google-level keyword search
- Vector search
Both of these work because of two open source extensions: pg_textsearch and pgvector (or pgvectorscale).
In this course, we'll vibe code a personal search engine command line tool together.
The first part of the course is very beginner friendly then starts to ramp around lesson 12 to get into the meat of using the app.
The final project is a search engine bot that can add links, crawl them, power a web app, an MCP server, and, of course, a hybrid search that combines keyword search and vector search.
You can fork the bot right now and go, at /bots/search-engine.
Ready to begin?
Lifetime access to this course
or get access to 500+ courses with a membership