LLM Vision | Getting Started
  • 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
  • Introduction
  • Supported sensors
  • Action Reference
  • Paramter Reference

Was this helpful?

  1. Usage

Data Analyzer

Update sensors using AI

PreviousStream AnalyzerNextRemember

Last updated 2 months ago

Was this helpful?

Introduction

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.

Supported sensors

  • number and input_number

  • text and input_text

  • select and input_select

  • input_boolean

Action Reference

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
  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!

Paramter 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).

use_memory

No

Use information stored in memory to provide additional context. Memory must be set up.

false

sensor_entity

Yes

The sensor to update

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.

100

temperature

Yes

Randomness of the output.

0.5

Use to create virtual sensors!

For all available models see:

helpers
Choosing the right model
Image to sensor