Rohit Ghumare
d1cb9d1933
Book pipeline: six-volume EPUB/PDF compilation built by CI from lesson sources (book/, scripts/build_book.py, themed title pages with edition stamps, site-matching print theme), attached to every GitHub release. Homepage Books section and README section link the latest release. Fundamentals-first headline policy across the course: 16 lesson titles and 30+ taglines/section headings now lead with the concept (agent state machines, actor model, role-based teams, memory paging, serving engine internals, permission modes); framework and product names are demoted to attributed in-body examples. README, ROADMAP, quizzes, and prerequisite references synced. New agent-memory taxonomy section maps memory types to representative implementations. Vendor-neutral model policy: runnable defaults read the LLM_MODEL env var with undated aliases; dated snapshot ids removed; multi-provider phrasing in the setup lesson. Lessons deepened with original material: prediction-game origins of perplexity (05/16), scripted-era chatbot lineage 1950-2001 (05/17), causal-triangle derivation from prefix averaging plus GPT-5 date fix (07/07). Three new animated site figures back them (figures-history.js). llms.txt now carries per-lesson raw markdown links so agents can fetch full lesson text directly. Bug fixes verified with executed repros: capstone solved flag keyed to test results, 405B cost estimator overflow, f-string crash on Python <3.12, no-torch demo path, negative stable BCE, all-zero stationary distribution, inverted Cohens d, per-lesson quiz panel, lesson-fetch retry with honest errors, decision-trees doc completed, editor shortcuts, rustc run command, Docker python3.12 build with doc sync, git lesson fork flow, FIPA receiver field, fnm under Rosetta, 15 curl-verified link fixes, remaining imdb dataset id spot.
1.9 KiB
Book Pipeline
The course compiles into a six-volume book series. The book is a companion, not a replacement: interactive figures, graded quizzes, and runnable code stay on the website and in this repository, and every chapter ends with the links that take the reader there.
Volumes
Defined in volumes.json. Each volume maps to a band of phases:
| Vol | Title | Phases |
|---|---|---|
| 1 | Foundations | 00-02 |
| 2 | Deep Learning | 03, 04, 06 |
| 3 | Language | 05, 07 |
| 4 | Large Language Models | 08-11 |
| 5 | Agents | 12-16 |
| 6 | Production | 17-19 |
Build
python3 scripts/build_book.py # all volumes, EPUB
python3 scripts/build_book.py --volume language
python3 scripts/build_book.py --pdf # adds PDF (needs xelatex + DejaVu fonts)
Requires pandoc. Optional: @mermaid-js/mermaid-cli (mmdc) to render mermaid diagrams as images; without it they become web-edition pointers. Output lands in dist/book/.
CI (.github/workflows/build-book.yml) builds EPUBs on every push that touches phases/, and EPUB + PDF on releases, attaching both to the release.
What the assembler does per lesson
- Lesson
# titlebecomes a chapter; phases become unnumbered part pages. figureblocks (interactive JS widgets) become boxed pointers to the lesson's web edition.- Mermaid blocks render to SVG when mmdc is available, otherwise become web pointers.
## Ship Itsections are replaced with a pointer to the repo artifact.## Exercisesgains a starter-code link into the lesson'scode/directory.- Every chapter closes with a Continue Online box: web edition, code, quiz.
- Asset image paths are rewritten so pandoc embeds the lesson SVGs.
The machine-readable index agents use to navigate the course (site/llms.txt, generated by site/build.js on deploy) links each lesson's raw markdown, and the book's "Learning with an AI" front page tells readers how to point their assistant at it.