Blueprint
Last updated
Was this helpful?
Last updated
Was this helpful?
A blueprint is a script or automation configuration with certain parts marked as configurable. This makes it easy to share them so you don't have to start from scratch.
Event Summary is updated with every LLM Vision update. To keep your automations compatible and to get new features, you should re-import blueprints after LLM Vision updates. See for more information.
Say hello to intelligent security event notifications! AI understands what happens in the video, decides whether you should be notified and sends you notifications with a preview and summary of what happened.
Customize your notification preferences by choosing to receive all updates or utilizing AI to filter for important events only. This can be configured using the important
parameter. Using AI will add a slight delay to your notifications (<5 seconds when using OpenAI).
When an event is detected, you'll receive a notification with basic information including the camera name. Event summarization continues in the background and the notification is updated once the summary is available.
You can customize which dashboard opens in the Home Assistant app when you tap the notification using the tap_navigate
parameter.
Additionally, a cooldown can be set. This prevents the automation from running too often, which may result in excessive cost from your AI provider.
For additional configuration, see the reference below.
Run Conditions Section
run_conditions
All conditions must be true in order for the blueprint to run
[]
cooldown
Time to wait before running automation again
10 minutes
Camera & Sensor Section
camera_entities
List of camera entities to monitor
[]
trigger_state
Automation starts when camera changes to this state
recording
motion_sensors
Set if cameras don't change state (Frigate)
[]
duration
Duration to record for analysis (seconds)
5
max_frames
How many frames to analyze
3
AI Section
remember
Stores event in Timeline
false
use_memory
Use stored information for context
false
message
Model prompt for video analyzer
Long default prompt about summarizing events
provider
Provider to use for analysis
model
Which model to use
target_width
Downscale images width
1280
max_tokens
Maximum tokens to generate
20
temperature
Randomness level
0.1
Notification Section
notify
Send notification to phone
true
condition_notify
Condition to notify device
[]
notify_device
Devices to send notification to
[]
notification_delivery
Controls how notifications are delivered
Dynamic
preview_mode
Choose between live preview or snapshot
Snapshot
file_path
File path for snapshot storage
Media Folder - Secured
tap_navigate
Dashboard to navigate on notification tap
/lovelace/0
delay_notification
Time before sending another notification (in seconds)
60
Experimental Section
important
Use AI to classify events by importance
false
additional_actions
Additional actions after AI analysis
[]
Notifications will play a live preview of the camera (iOS only, Android will show a snapshot). If you use Frigate, the needs to be installed.