{
  "title": "Contextualize using files",
  "video_id": "a-EK-j8zdTg",
  "published": "2024-04-23T09:36:13+0000",
  "complexity": "Easy",
  "old_url": "https://workflows-of-ai.com/workflow/contextualize-using-files",
  "description": "Use the Unstructured module and AI Interpolator to turn PDF, Excel and image files into HTML, table fields or Markdown in Drupal.",
  "subtitle": "Turn PDFs, Excel sheets and photos into HTML, tables or Markdown in Drupal with the Unstructured module.",
  "summary": "The Unstructured module sends files to Unstructured, as SaaS or self-hosted, and gets back text, Markdown or HTML. A PDF becomes HTML in CKEditor, an Excel file fills a Table Field, and a photo of a receipt becomes a Markdown table with the hi_res Chipper model. Output format, strategy, splitting and image extraction settings are explained along the way.",
  "categories": [
    "Drupal AI"
  ],
  "intro_html": "<p>Unstructured IO is a service that takes structured files like PDF files, PowerPoints, Excel sheets, Word documents and Markdown files and generates structure into text, Markdown or HTML.</p><p>It can also take unstructured files like photos of tables or text and turn those into structured content.</p><p>Introducing a way to improve your site search, contextualize for AI or create webpages using the HTML mode inside Drupal.</p><p>The service can be self-hosted or be set up using Unstructured SaaS.</p><p>The module: <a href=\"https://www.drupal.org/project/unstructured\">https://www.drupal.org/project/unstructured</a><br>The documentation: <a href=\"https://www.drupal.org/docs/extending-drupal/contributed-modules/contributed-module-documentation/ai-interpolator/ai-interpolator-unstructured\">https://www.drupal.org/docs/extending-drupal/contributed-modules/contributed-module-documentation/ai-interpolator/ai-interpolator-unstructured</a><br>Unstructured website: <a href=\"https://unstructured.io/\">https://unstructured.io/</a></p>",
  "intro_added": false,
  "chapters": [
    "0:00 What Unstructured IO does",
    "1:06 The Unstructured module",
    "2:43 Three ways to use it",
    "6:25 Installing the modules",
    "7:45 PDF to HTML field",
    "9:06 Output format and strategy",
    "11:37 API key and first test",
    "14:28 Excel to Table Field",
    "16:25 Receipt photo to Markdown",
    "17:48 Choosing a hi_res model"
  ],
  "corrections": [
    [
      "AI interpolator",
      "AI Interpolator"
    ],
    [
      "for a interpolator",
      "for AI Interpolator"
    ],
    [
      "enable the aor",
      "enable the AI Interpolator"
    ],
    [
      "AI Lor",
      "AI Interpolator"
    ],
    [
      "CK editor",
      "CKEditor"
    ],
    [
      "Y wig",
      "WYSIWYG"
    ],
    [
      "Mark Time",
      "Markdown"
    ],
    [
      "hris",
      "hi_res"
    ],
    [
      "hress",
      "hi_res"
    ],
    [
      "strategy Hest",
      "strategy hi_res"
    ],
    [
      "hus model",
      "hi_res model"
    ],
    [
      "detectron Tu",
      "Detectron2"
    ],
    [
      "with o X",
      "with ONNX"
    ],
    [
      "use TCT",
      "use Tesseract"
    ],
    [
      "open AI",
      "OpenAI"
    ]
  ],
  "ai_note": "The video and the introduction are Marcus's own, first published on workflows-of-ai.com. AI wrote the subtitle, the summary and the video chapters from the transcript, and corrected misheard names in YouTube's automatic captions."
}