Image Analyzer

Example

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:
  max_tokens: 50
  provider: 01JAAFDSVEJEBMESBP62QP156T # Pick in UI
  message: Describe the image
  image_entity:
    - camera.front_door # Replace with your camera's entity_id
  include_filename: false

Action Reference

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

For all available models see: 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
  max_tokens: 1000
  provider: 01JAAFDSVEJEBMESBP62QP156T
  include_filename: true

Parameter Reference

Parameter	Required	Description	Default
provider	Yes	The AI provider configuration
model	No	Model used for processing the image(s).
message	Yes	The prompt to send along with the image(s).
remember	No	Remember the analyzed event	false
use_memory	No	Use information stored in memory to provide additional context. Memory must be set up.	false
image_file	No*	The path to the image file(s). Each path must be on a new line.
image_entity	No*	An alternative to image_file for providing image input.
include_filename	Yes	Whether to include the filename in the request.	false
target_width	No	Width to downscale the image to before encoding.	1280
max_tokens	Yes	The maximum number of response tokens to generate.	1000
generate_title	No	Generate a title. (Used for notifications and remembered events)	false
expose_images	No	Save key frame to /config/media/llmvision/snapshots. File path is included in response as key_frame. If used together with remember images will be deleted after retention_time set in Timeline. Otherwise this folder will use a lot of disk space!	false