▶
Executionexec_in
Trigger
Automation/LLM/Vision
Uses vision LLM to extract structured data from a screenshot
Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.
Trigger
Vision-capable LLM model
Screenshot as base64 PNG, JPEG, WebP or GIF (a data URL is fine). Ignored when Image is connected
Screenshot as an image, e.g. from the Screenshot node. Takes precedence over the base64 Screenshot
JSON Schema describing what to extract (or example JSON)
Optional extraction hint
Continue
Extracted structured data, validated against the schema