Nybble™
All courses

Guided Course

understandtheorycode

Embeddings, End to End

One-hot to Matryoshka, TF-IDF to contrastive fine-tuning, text to audio to graphs — every technique with its formula, every generation with the failure that ended it.

0/23
Start course
23 lessons
  1. 1. The problem embeddings solve7 min
  2. 2. A coordinate system for meaning8 min
  3. 3. Reading a real embedding6 min
  4. 4. What makes an embedding good6 min
  5. 5. One-hot vectors and the bag of words6 min
  6. 6. TF-IDF, and how far counting can take you6 min
  7. 7. word2vec: meaning from company7 min
  8. 8. GloVe, and fastText's fix for unknown words6 min
  9. 9. The context problem: ELMo and BERT6 min
  10. 10. Sentence-BERT and the contrastive turn7 min
  11. 11. Where embeddings sit inside an LLM7 min
  12. 12. What is the difference between an LLM and an embedding model?5 min
  13. 13. How modern embedding models are trained7 min
  14. 14. Fine-tuning, part 1: getting the data right8 min
  15. 15. Fine-tuning, part 2: the training run6 min
  16. 16. Embeddings in action6 min
  17. 17. Every modality: images, audio and video7 min
  18. 18. Embeddings as graphs6 min
  19. 19. The other embeddings, and what they are all for6 min
  20. 20. How to choose an embedding model6 min
  21. 21. MTEB, and how to read a leaderboard5 min
  22. 22. Evaluation metrics for embeddings6 min
  23. 23. Embeddings in RAG, and shipping them7 min
  24. Key takeaways4 min
  25. How to get certified3 min
  26. 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 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