Nybble™
SnackStackHack
Vector Databases, Inside and Out

Lesson 18 of 18

Lessons

  1. 1. The similarity search problem
  2. 2. Distance metrics and vector spaces
  3. 3. Embedding models — choosing and evaluating
  4. 4. How embedding models are trained
  5. 5. HNSW: the production default
  6. 6. IVF: cluster-based search
  7. 7. Quantization: compressing vectors for scale
  8. 8. DiskANN and beyond: billion-scale search
  9. 9. Architecture of a vector database
  10. 10. Metadata filtering and hybrid search
  11. 11. Multi-vector search and late interaction
  12. 12. pgvector: the Postgres-native vector store
  13. 13. Choosing a vector database
  14. 14. Ingestion pipelines and corpus management
  15. 15. Scaling and multi-tenancy
  16. 16. Security and compliance
  17. 17. Operations and observability
  18. 18. Building a production vector search service
  19. Key takeaways
  20. How to get certified
  21. Your certificate

Building a production vector search service

Free account

Read this lesson

The opening lessons of every course are free — this one needs an account. Sign in and the full course opens.

  • Every lesson, start to finish
  • Progress saved across devices
  • Bits per lesson, plus a bonus for finishing

Free · your email is used for progress only.

Nybble™ — built for the people building AI.

AboutTermsPrivacyContact
SnackStackHack
Message Nybble