Course · Coming soon
pgvector for TypeScript
Learn how to build vector search that returns better results, stays fast as data grows, and is ready for production in a TypeScript codebase.
You've done the hello-world. You have pgvector installed, you ran a similarity query, and it sort of works. Now you're in the messy middle: results that aren't quite right, queries slowing down as your table grows, and no clear path to something you'd trust in production.
This course gives you the practical steps to improve relevance, choose the right indexing strategy, measure quality, and operate the system without adding a separate vector database.
No spam. One email when it launches.
Sound familiar?
- —“My similarity results look plausible but feel off. How do I actually debug relevance?”
- —“My table is growing and queries are slowing down. Which index do I pick?”
- —“How do I combine keyword search with vector search?”
- —“My embedding model got updated. Do I need to re-embed everything?”
- —“Every tutorial uses Python. Where is the TypeScript version?”
- —“How do I prove this system works reliably? How do I benchmark and eval?”
Each chapter turns one of these stuck points into a practical decision you can make in your own codebase.
What you'll learn
The Foundation
Build the mental model you need to make good decisions: what embeddings represent, when Postgres is enough, and how semantic similarity behaves in real applications.
Setup & Your First Query
Go from an empty database to a working TypeScript flow: connect through the tools you already use, store embeddings safely, and run your first similarity search with confidence.
Making It Good: Relevance & Quality
Learn why plausible-looking results fail, how to improve them, and how to debug relevance when users cannot find what they expect.
Making It Fast: Indexing
Understand the tradeoffs behind IVFFlat and HNSW so you can choose an index, tune it, and keep search responsive as your data grows.
Making It Real: Hybrid Search & Patterns
Combine vector similarity with full-text search, filters, RAG patterns, and practical schema design so the feature fits the product instead of staying a demo.
Evals & Benchmarking
Create a repeatable way to tell whether search is improving: build eval sets, measure recall and relevance, compare changes, and catch quality regressions before users do.
Production Operations
Know what to watch after launch: index maintenance, embedding model upgrades, re-embedding decisions, monitoring, and alerts for the problems that quietly degrade search.
Why this course
TypeScript-first
Work in the stack you already use. Examples, ORM choices, and implementation details are written for TypeScript backend engineers.
Move past the prototype
Get a path from a working similarity query to a feature you can explain, tune, monitor, and trust in production.
Learn in the order problems appear
Start by getting search working, then improve relevance, speed it up, combine it with product constraints, and prepare it for real traffic.
Make better tradeoffs
Understand why each choice matters so you can adapt the patterns to your data, your users, and your latency requirements.
Evals and benchmarking
Stop guessing whether search is better. Learn how to measure quality, compare changes, and protect relevance as the system evolves.
Useful before you buy anything
The public chapters are designed to help you solve real implementation problems. Paid extras will add depth, templates, and project files.
Join the waitlist
One email when the course is ready. No drip sequences, no sales funnel.