---
schema: 1
type: video
title: 'Structuring the Unstructured - Cedric Clyburn, Red Hat'
description: >-
  Modern 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 context-aware methods
  with Docling, part of the Linux AI & Data Foundation. Speakers: - Cedric
  Clyburn (Red Hat): Cedric Clyburn (@cedricclyburn) is a Senior Developer
  Advocate at Red Hat and open-source contributor (vLLM, Podman) who helps
  developers adopt emerging technologies through speaking, workshops, and
  community leadership (as an organizer of Kubernetes Community Day New York).
  X/Twitter: https://x.com/cedricclyburn LinkedIn:
  linkedin.com/in/cedricclyburn/ GitHub: github.com/cedricclyburn
canonical: 'https://liquidgold.cc/watch/-x5GEVnkuRw'
markdown: 'https://liquidgold.cc/watch/-x5GEVnkuRw.md'
llms: 'https://liquidgold.cc/watch/-x5GEVnkuRw/llms.txt'
parent: 'https://liquidgold.cc/channel/aidotengineer.md'
channel: aidotengineer
updated: '2026-10-24T09:13:36.847Z'
language: null
children: []
videoId: '-x5GEVnkuRw'
durationSeconds: 1241
publishedAt: '2026-06-28T16:30:39.000Z'
searchChunks:
  - ordinal: 0
    text: null
    startSeconds: 10
    endSeconds: 107
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=10'
    heldReason: rights
  - ordinal: 1
    text: null
    startSeconds: 118
    endSeconds: 249
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=118'
    heldReason: rights
  - ordinal: 2
    text: null
    startSeconds: 118
    endSeconds: 249
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=118'
    heldReason: rights
  - ordinal: 3
    text: null
    startSeconds: 261
    endSeconds: 371
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=261'
    heldReason: rights
  - ordinal: 4
    text: null
    startSeconds: 261
    endSeconds: 371
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=261'
    heldReason: rights
  - ordinal: 5
    text: null
    startSeconds: 261
    endSeconds: 371
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=261'
    heldReason: rights
  - ordinal: 6
    text: null
    startSeconds: 382
    endSeconds: 495
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=382'
    heldReason: rights
  - ordinal: 7
    text: null
    startSeconds: 382
    endSeconds: 495
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=382'
    heldReason: rights
  - ordinal: 8
    text: null
    startSeconds: 495
    endSeconds: 506
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=495'
    heldReason: rights
  - ordinal: 9
    text: null
    startSeconds: 506
    endSeconds: 618
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=506'
    heldReason: rights
  - ordinal: 10
    text: null
    startSeconds: 506
    endSeconds: 618
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=506'
    heldReason: rights
  - ordinal: 11
    text: null
    startSeconds: 628
    endSeconds: 731
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=628'
    heldReason: rights
  - ordinal: 12
    text: null
    startSeconds: 628
    endSeconds: 731
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=628'
    heldReason: rights
  - ordinal: 13
    text: null
    startSeconds: 731
    endSeconds: 742
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=731'
    heldReason: rights
  - ordinal: 14
    text: null
    startSeconds: 742
    endSeconds: 822
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=742'
    heldReason: rights
  - ordinal: 15
    text: null
    startSeconds: 742
    endSeconds: 822
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=742'
    heldReason: rights
  - ordinal: 16
    text: null
    startSeconds: 834
    endSeconds: 969
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=834'
    heldReason: rights
  - ordinal: 17
    text: null
    startSeconds: 834
    endSeconds: 969
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=834'
    heldReason: rights
  - ordinal: 18
    text: null
    startSeconds: 980
    endSeconds: 1069
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=980'
    heldReason: rights
  - ordinal: 19
    text: null
    startSeconds: 1069
    endSeconds: 1081
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=1069'
    heldReason: rights
  - ordinal: 20
    text: null
    startSeconds: 1175
    endSeconds: 1241
    watch: 'https://liquidgold.cc/watch/-x5GEVnkuRw?t=1175'
    heldReason: rights
---


# Structuring the Unstructured - Cedric Clyburn, Red Hat

Modern 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 context-aware methods with Docling, part of the Linux AI & Data Foundation. Speakers: - Cedric Clyburn (Red Hat): Cedric Clyburn (@cedricclyburn) is a Senior Developer Advocate at Red Hat and open-source contributor (vLLM, Podman) who helps developers adopt emerging technologies through speaking, workshops, and community leadership (as an organizer of Kubernetes Community Day New York). X/Twitter: https://x.com/cedricclyburn LinkedIn: linkedin.com/in/cedricclyburn/ GitHub: github.com/cedricclyburn

Canonical: https://liquidgold.cc/watch/-x5GEVnkuRw · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md)

> Search chunk text is held until public-source provenance is verified.

## Document chunks

> Missing: no stored document chunks are available.