Nybble™
All courses

Guided Course

buildarchitecturetheory

Vector Databases, Inside and Out

Algorithms, architecture, and operations — from HNSW internals to production at scale.

0/17
Start course
17 lessons
  1. 1. The similarity search problem8 min
  2. 2. Distance metrics and vector spaces8 min
  3. 3. Embedding models — choosing and evaluating10 min
  4. 4. HNSW: the production default9 min
  5. 5. IVF: cluster-based search9 min
  6. 6. Quantization: compressing vectors for scale8 min
  7. 7. DiskANN and beyond: billion-scale search8 min
  8. 8. Architecture of a vector database9 min
  9. 9. Metadata filtering and hybrid search10 min
  10. 10. Multi-vector search and late interaction9 min
  11. 11. pgvector: the Postgres-native vector store10 min
  12. 12. Choosing a vector database9 min
  13. 13. Ingestion pipelines and corpus management10 min
  14. 14. Scaling and multi-tenancy8 min
  15. 15. Security and compliance12 min
  16. 16. Operations and observability9 min
  17. 17. Building a production vector search service11 min

About Nybble™

The AI space moves fast.
Nybble™ is how you keep up — and stay sharp.

Snack

What happened. In two minutes.

The AI news cycle moves at a pace no one can keep up with. Snack distills what launched, what shipped, and what matters — every day, without the filler.

Go to Snack
Stack

The concepts behind the headlines.

News tells you what. Stack tells you why and how. From RAG architectures to agentic evals, these are the ideas that will shape what you build next.

Go to Stack
Hack

Prove you actually get it.

Reading about LangChain is not the same as knowing it. Hack challenges you with production-grade questions, then shows you the references that make the answer stick.

Go to Hack