Data Analyzer

Update sensors using AI

Image to sensor

Action Reference

data_analyzer updates a sensor based in image input. (Added in v1.3.1)

For example you could create a sensor to monitor how many cars are parked, monitor your 3D print quality or the license plate of the car in your driveway.

Use helpers to create virtual sensors!

Supported sensors

• number and input_number

• text and input_text

• select and input_select

• input_boolean

Usage

Action Reference

service: llmvision.data_analyzer
data:
  provider: 01J99F4T99PA1XGQ4CTQS3CP8H  # Select in UI dropdown
  model: gpt-4o-mini
  message: What is the car's license plate?
  sensor_entity: input_text.last_license_plate
  image_entity: 
    - image.garage_car
  image_file: |-
    /config/www/weather_chart.jpg
  max_tokens: 5 # A low value is recommended
  target_width: 1280
  detail: high
  temperature: 0.1 # Recommeded for accuracy
  include_filename: true # Include image/camera name in request

The provider id will not be the same for you. Switch to UI mode and select one of your configurations. If you don't see any, you need to set up at least one provider!

More Examples and blueprints: https://llm-vision.gitbook.io/examples/

For all available models see: https://llm-vision.gitbook.io/getting-started/choosing-the-right-model