/

Google Cloud Vision

Google Cloud Vision logo

Google Cloud Vision

Vision detection for image labeling, face and landmark detection, OCR and explicit content tagging.

Overview

Google Cloud Vision API enables developers to integrate vision detection features into applications, including image labeling, face and landmark detection, optical character recognition (OCR), and explicit content tagging. Your coworker can label images, detect faces and landmarks, and read text with OCR. They act through the account you connect, so they only see what that account can see.

Setup steps

  1. Sign in to Backdrop at app.backdropagent.com and open the AI coworker you want to give access to

  2. Go to its Settings tab (on the coworker's page, not the workspace Settings in the sidebar)

  3. Under Connect more, search for Google Cloud Vision and click Connect

  4. Connect your Google Cloud Vision account when prompted

  5. You land back on the Settings tab with Google Cloud Vision marked Connected and its settings open

  6. Optionally add a label (for example "Marketing account") so you can tell connected accounts apart

  7. If Google Cloud Vision supports changes, use Allow editing to choose: on lets your coworker create, update and delete in Google Cloud Vision, off keeps it read-only

  8. Try it: ask your coworker in Slack or in Backdrop chat to pull something from Google Cloud Vision