Structuring the Unstructured - Cedric Clyburn, Red Hat
Open-source tool Docling extracts structure from unstructured enterprise documents to power RAG and agent systems.
“unstructured data is becoming this new context layer for AI”
Red Hat's Cedric Clyburn demonstrates Docling, a Linux Foundation open-source tool for parsing, extracting, and chunking unstructured documents like PDFs into LLM-friendly formats such as markdown and JSON. It matters because most enterprise data is unstructured and must be transformed before it can serve as context for RAG and agentic AI, with open-source tooling avoiding proprietary data-sharing concerns.