Created
November 17, 2025 06:33
-
-
Save peyanski/4592aadb68b1fdce7875a527164fb8b6 to your computer and use it in GitHub Desktop.
Takes a snapshot from the top street camera and uses AI to identify cars and people.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| alias: AI Analyse Top Street Camera Snapshot | |
| description: >- | |
| Takes a snapshot from the top street camera and uses AI to identify cars and | |
| people. | |
| triggers: | |
| - trigger: state | |
| entity_id: | |
| - binary_sensor.top_street_motion | |
| to: | |
| - "on" | |
| - trigger: state | |
| entity_id: | |
| - input_button.start_automation | |
| enabled: false | |
| conditions: [] | |
| actions: | |
| - action: ai_task.generate_data | |
| metadata: {} | |
| data: | |
| task_name: What is on the snapshot | |
| instructions: >- | |
| tell me what are you seeing on the security camera snapshot. How many | |
| cars and what types and colors and how many persons are you seeing? | |
| entity_id: ai_task.ollama_ai_task_qwen3_vl_235b_cloud | |
| attachments: | |
| media_content_id: media-source://camera/camera.top_street_fluent | |
| media_content_type: application/vnd.apple.mpegurl | |
| metadata: | |
| title: Top Street Fluent | |
| thumbnail: /api/camera_proxy/camera.top_street_fluent | |
| media_class: video | |
| children_media_class: null | |
| navigateIds: | |
| - {} | |
| - media_content_type: app | |
| media_content_id: media-source://camera | |
| response_variable: ai_response | |
| - action: persistent_notification.create | |
| metadata: {} | |
| data: | |
| message: "{{ ai_response.data | default('No image.') }}" | |
| title: Top Street Security camera | |
| mode: single |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment