מבנה ללא-מבנה - סדריק קליבורן, Red Hat

תקציר מקורי באנגליתModern organizations generate vast amounts of data stored in diverse and often unstructured formats, such as PDFs, scanned documents, and proprietary file types. For engineers working with AI, the challenge isn’t just about extracting text but also about preserving the structure, context, and relationships within the data. Whether fine-tuning models or building retrieval-augmented generation (RAG) pipelines, effective document processing is essential for creating AI applications that bring value. This live demo session is all about the techniques and open source tools needed to transform unstructured documents into structured formats like JSON or Markdown, ready for AI workflows. You’ll learn how to handle challenges like multi-page tables, image-heavy layouts, and scanned documents using