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