Section 4 chapters · 14 lessons
Generative AI
What an LLM is and isn't, the autoregressive loop, structured outputs, RAG that doesn't break, evals that mean something, and self-hosting at the edge of the GPU.
0 / 14 lessons
- 01
Foundations
4 lessons - 01 What an LLM is
- 02 The autoregressive loop
- 03 Sampling: temperature, top-k, top-p
- 04 Structured outputs
- 02
Prompting & Tools
3 lessons - 05 Prompt patterns that work
- 06 Few-shot & chain-of-thought
- 07 Function/tool calling
- 03
RAG
5 lessons - 08 Embeddings
- 09 Vector databases
- 10 RAG basics
- 11 Advanced RAG
- 12 RAG evaluations
- 04
Operations
2 lessons - 13 Cost & latency engineering
- 14 Self-hosting with vLLM