Image Analyzer

Example Action

Once you have set up at least one provider and have at least one camera in Home Assistant, you can test LLM Vision:

Minimal working example

action: llmvision.image_analyzer
data:
  include_filename: true
  max_tokens: 50
  temperature: 0.2
  provider: 01JAAFDSVEJEBMESBP62QP156T # Pick in UI
  message: Describe the image
  image_entity:
    - camera.front_door # Replace with your camera's entity_id

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

Action Reference

The provider id will not be the same for you. Switch to UI mode and select one of your configurations

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

Action Reference

action: llmvision.image_analyzer
data:
  model: gpt-4o-mini
  message: Describe the image
  image_file: |-
    /config/www/tmp/front_door.jpg
    /config/www/tmp/garage.jpg
  image_entity:
    - camera.front_door
    - camera.garage
  target_width: 1280
  detail: low
  max_tokens: 100
  temperature: 0.2
  provider: 01JAAFDSVEJEBMESBP62QP156T
  include_filename: true