Docling
A linear, one-concept-per-lesson path through docling, the IBM/LF AI open-source document-conversion library, from your first convert() call to a folder-to-queryable-chunks RAG ingestion pipeline. 18 lessons · 3 tiers.
Prerequisites: Comfortable writing basic Python (functions, imports, running a script). This teaches docling concepts, not coding. Lesson 16 assumes no prior LlamaIndex experience, it's introduced there.
No API key is required for the core conversion pipeline, docling's layout, table, and OCR models run locally (the first run downloads a few hundred megabytes of model weights, then reuses the local cache). Lesson 16 makes real Gemini API calls and needs a GOOGLE_API_KEY in a .env file at the project root, the same free tier used throughout this repo (get one at aistudio.google.com/apikey).
Built on docling, the open-source library this course teaches.
Beginner
Your first conversions, and what DoclingDocument actually holds.
Intermediate
Pipeline options, tables, OCR, and chunking for RAG.
Advanced
Enrichment, performance, and closing the loop with LlamaIndex.