Usage

Learn how to use LLM Vision

Available Actions

LLM Vision exposes five actions (previously called services):

1. image_analyzer: Analyzes image files, image and camera entities

2. video_analyzer: Analyzes video files and Frigate events

3. stream_analyzer: Records and analyzes camera entities

4. data_analyzer: Updates a sensor value based on images

5. remember: Store custom events in LLM Vision Timeline

Response

image, video, stream and data analyzers will return a response value:

title: White SUV seen
response_text: >-
  The image shows a white SUV parked on a driveway.
key_frame: /config/media/llmvision/snapshots/0b9ff287-0.jpg

Depending on your configuration, not all keys may be present. Refer to the parameter reference of each action to learn more.

Accessing the response

To access it, set response_variable in your automation or script to e.g. response.

To get e.g. the generated title use {{response.title}}.

Using Snapshots in your own Automations

Since v1.5.1 LLM Vision stores snapshots in the more secure /media folder.

In your own automations use the following template for snapshot paths:

{{ response.key_frame.replace('/config', '') }}

Where response is the response variable of an analyzer action with expose_images enabled.