MarkItDown
A linear, one-concept-per-lesson path through MarkItDown, Microsoft's open-source library for converting a wide range of file formats into Markdown an LLM can read, from your first .convert() call to a Gemini-backed searchable index over a full mixed document folder. 12 lessons · 3 tiers.
Prerequisites: No hard prerequisite, can be started cold. Lessons 10 and 11 assume basic familiarity with the LlamaIndex course, Lessons 1-4 (Document, VectorStoreIndex, query engines), and Lesson 11 compares directly against the LiteParse course, the same way LiteParse's own README notes its soft prerequisite on LlamaIndex.
No new API key needed, markitdown[all] ships in this project's existing setup. Lessons 6, 10, and 12 use the same GOOGLE_API_KEY every other course uses, for LLM image captioning (Lesson 6) and LlamaIndex embeddings/generation (Lessons 10 and 12).
Built on MarkItDown, the open-source library this course teaches.
Beginner
The core .convert() call, office documents, streams and URLs, and a first batch-conversion checkpoint.
Intermediate
LLM image captioning, custom converters and plugins, and format hints that can silently go wrong.
Advanced
Feeding MarkItDown into LlamaIndex, comparing it against LiteParse, and a full multi-format capstone index.