LLM Vision | Getting Started
FeaturesExamplesGitHub
  • Introduction
  • Installation
  • Setup
    • Providers
      • Cloud Providers
      • Self-hosted Providers
      • Memory
      • Timeline
    • Timeline Card
    • Blueprint
    • Asking about Events
  • Usage
    • Image Analyzer
    • Video Analyzer
    • Stream Analyzer
    • Data Analyzer
    • Remember
  • Choosing the right model
Powered by GitBook
On this page
  • Available Actions
  • Response
  • Accessing the response

Was this helpful?

Usage

Learn how to use LLM Vision

PreviousAsking about EventsNextImage Analyzer

Last updated 1 month ago

Was this helpful?

Available Actions

LLM Vision exposes five actions (previously called services):

  1. : Analyzes image files, image and camera entities

  2. : Analyzes video files and Frigate events

  3. : Records and analyzes camera entities

  4. : Updates a sensor value based on images

  5. : Store custom events in LLM Vision Timeline

Response

image_analyzer, video_analyzer and stream_analyzer will return a response value:

title: White SUV seen
response_text: >-
  The image shows a white SUV parked on a driveway.
key_frame: /config/www/llmvision/front_door.jpg

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

remember does not return a response. Instead it directly updates the selected sensor entity.

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}}.

image_analyzer
video_analyzer
stream_analyzer
data_analyzer
remember