All courses

Guided Course

buildarchitecturetheory

Vector Databases, Inside and Out

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

0/18
Start course
18 lessons
  1. 1. The similarity search problem7 min
  2. 2. Distance metrics and vector spaces7 min
  3. 3. Embedding models — choosing and evaluating11 min
  4. 4. How embedding models are trained8 min
  5. 5. HNSW: the production default8 min
  6. 6. IVF: cluster-based search8 min
  7. 7. Quantization: compressing vectors for scale7 min
  8. 8. DiskANN and beyond: billion-scale search7 min
  9. 9. Architecture of a vector database8 min
  10. 10. Metadata filtering and hybrid search9 min
  11. 11. Multi-vector search and late interaction8 min
  12. 12. pgvector: the Postgres-native vector store8 min
  13. 13. Choosing a vector database8 min
  14. 14. Ingestion pipelines and corpus management9 min
  15. 15. Scaling and multi-tenancy6 min
  16. 16. Security and compliance12 min
  17. 17. Operations and observability7 min
  18. 18. Building a production vector search service10 min
  19. Key takeaways4 min
  20. How to get certified3 min
  21. Your certificate