LiteParse
A linear, one-concept-per-lesson path through LiteParse, a local, open-source, Rust-backed PDF parser, from your first parse call to a mixed native+scanned pipeline feeding LlamaIndex. 14 lessons · 3 tiers.
Prerequisites: No hard prerequisite. Lessons 13-14 assume basic familiarity with the LlamaIndex course, Lessons 1-4 (Document, VectorStoreIndex), the same way the Ollama course notes its own soft prerequisite on LangChain.
No API key needed for Lessons 1-12: LiteParse's parsing runs in a local, compiled Rust extension, already installed via uv sync, against sample PDFs pre-built in sample_data/. Lessons 13-14 call Google's Gemini free tier (gemini-3.5-flash-lite) through this project's existing GOOGLE_API_KEY, the same key every other Gemini-backed course in this repo uses, once LlamaIndex enters the picture.
Built on LiteParse, the open-source library this course teaches.
Beginner
Your first parse calls, config options, and per-page layout.
Intermediate
Structured extraction: forms, images, OCR, metadata, and accessibility.
Advanced
Concurrency and a real LlamaIndex pipeline, no cloud parsing API anywhere.