Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to transform complex documents into structured data for AI applications in this hands-on technical workshop featuring Docling, an open source Python package that has gained over 25,000 GitHub stars for document parsing and export. Discover how to streamline document AI workflows by converting PDFs, DOCX, PPTX, HTML, images, and Markdown files into structured Markdown or JSON formats. Master Docling's deep document understanding capabilities that accurately capture page layouts, reading order, and tables essential for complex document analysis. Explore integration with popular AI frameworks including LlamaIndex, LangChain, and InstructLab to power retrieval-augmented generation (RAG), question-answering systems, and large language model training. Practice using OCR support for extracting data from scanned or image-based documents and utilize the developer-friendly command-line interface for quick and consistent document processing. Build your first custom document ingestion pipeline through practical exercises led by IBM Research experts Peter Staar and Cesar Berrospi, gaining the skills needed to leverage this rapidly growing tool that's reshaping how developers approach document AI in the era of artificial intelligence advancement.
