{
  "title": "Image Categorization",
  "video_id": "KpF-oavOL_0",
  "published": "2024-01-31T09:55:14+0000",
  "complexity": "Normal",
  "old_url": "https://workflows-of-ai.com/workflow/image-categorization",
  "description": "Categorize images in Drupal with AI Interpolator and OpenAI Vision: media images get terms for body type, color and doors.",
  "subtitle": "Let GPT Vision look at each image and pick categories from your taxonomy, so a backlog of thousands of images gets tagged.",
  "summary": "Marcus installs AI Interpolator OpenAI with Composer, enables Media and adds a car tags vocabulary with body types, colors and door counts. A taxonomy field on the image media type uses the OpenAI taxonomy rule with GPT Vision, so the image itself is the context. Saving a car image fills in two to four matching tags.",
  "categories": [
    "Drupal AI"
  ],
  "intro_html": "<p>The workflow in this example is very simple and very similar to previous workflows. The idea is that we have a lot of images in our backlog, or that we just don't have time to categorize images in our editorial process. Let's automate it.</p><p>It takes advantage of OpenAI Vision to do the job.</p><p>It reads the image and then it can do actions for you based on your prompt, in this case a prompt specifically for the taxonomy field.</p><p>You end up with magic that takes the job away from you.</p>",
  "intro_added": false,
  "chapters": [
    "0:00 Too many images to tag",
    "1:34 The AI Interpolator OpenAI plugin",
    "2:23 Installing with Composer",
    "3:05 Enabling modules and the OpenAI key",
    "4:40 A car tags vocabulary",
    "6:25 Taxonomy field on image media",
    "7:38 Using the image as context",
    "9:20 Testing with car photos"
  ],
  "corrections": [
    [
      "druple",
      "Drupal"
    ],
    [
      "doxal",
      "Docksal"
    ],
    [
      "AI inator",
      "AI Interpolator"
    ],
    [
      "AI interpolator",
      "AI Interpolator"
    ],
    [
      "engine X",
      "nginx"
    ],
    [
      "open AI",
      "OpenAI"
    ],
    [
      "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."
}