Hi all
After one of the latest updates to HA image processing has stopped working.
I managed to fix it (mostly) but cannot figure out how to attach multiple images that are sent to AI - gui section only allows to select a single image, though it implies that you can select multiple…
Here is my yaml code:
action: ai_task.generate_data
data:
  entity_id: ai_task.google_ai_task
  attachments:
    media_content_id: media-source://media_source/local/driveway1_snapshot1.jpg
    media_content_type: image/jpeg
    metadata:
      title: driveway1_snapshot1.jpg
      thumbnail: null
      media_class: image
      children_media_class: null
      navigateIds:
        - {}
        - media_content_type: app
          media_content_id: media-source://media_source
  task_name: Driveway motion analysis
  instructions: |2-
            Motion has been detected, compare and very briefly describe what you see
            in the following sequence of images from my driveway camera number 1.
            What do you think caused the motion alarm? If a person or car is
            present, describe them in detail. If a car is detected in the pictures
            also include license plate details. Do not describe stationary objects
            or buildings. If you see no obvious causes of motion, reply with "No
            Obvious Motion Detected." Your message needs to be short enough to fit
            in a phone notification.
response_variable: generated_content