Developer & DevOps

[2/3] Media preparation (two types) for anomaly detection (crops data set)

48 nodes 209 120 Automatic trigger
Download

Workflow Description

Advanced workflow for preparing two distinct media types for anomaly detection in crop datasets. Combines manual triggers, HTTP requests, and custom code logic to process raw media data into normalized training datasets.

How it works

  1. 1.Initiate workflow manually and retrieve initial media data via HTTP request from data source
  2. 2.Split media into two separate type-based streams and apply specialized processing logic to each
  3. 3.Merge processed results into unified output format ready for anomaly detection model

Use cases

  • Prepare multi-source crop images and sensor data for plant health anomaly detection systems
  • Standardize heterogeneous media inputs before applying machine learning anomaly models

Requirements

  • HTTP-accessible media data sources with clear type classification and metadata
  • Development capability to customize processing logic for each media type's unique characteristics

Service Value

Ready-made workflow template for automation delivery and service execution.

Apps Used

Manual Trigger HTTP Request Code Set Split Out Merge Note

Details

Trigger Automatic trigger
Nodes 48
Apps 7
Views 209
Downloads 120

How to Use

  1. 1.Click "Download Template"
  2. 2.Open your n8n dashboard
  3. 3.Go to Workflows > Import from File
  4. 4.Select downloaded file and configure credentials

Nodes Used (48)

/

When clicking ‘Test workflow’

Manual Trigger

#1

Total Points in Collection

HTTP Request

#2

Cluster Distance Matrix

HTTP Request

#3

Scipy Sparse Matrix

Code

#4

Set medoid id

HTTP Request

#5

Get Medoid Vector

HTTP Request

#6

Prepare for Searching Threshold

Set

#7

Searching Score

HTTP Request

#8

Threshold Score

Set

#9

Set medoid threshold score

HTTP Request

#10

Split Out1

Split Out

#11

Merge

Merge

#12

Textual (visual) crop descriptions

Set

#13

Embed text

HTTP Request

#14

Get Medoid by Text

HTTP Request

#15

Set text medoid id

HTTP Request

#16

Prepare for Searching Threshold1

Set

#17

Threshold Score1

Set

#18

Searching Text Medoid Score

HTTP Request

#19

Medoids Variables

Set

#20

Text Medoids Variables

Set

#21

Qdrant cluster variables

Set

#22

Info About Crop Clusters

Set

#23

Crop Counts

HTTP Request

#24

Sticky Note

Sticky Note

#25

Sticky Note1

Sticky Note

#26

Sticky Note2

Sticky Note

#27

Sticky Note3

Sticky Note

#28

Sticky Note4

Sticky Note

#29

Sticky Note5

Sticky Note

#30

Sticky Note6

Sticky Note

#31

Sticky Note8

Sticky Note

#32

Sticky Note9

Sticky Note

#33

Split Out

Split Out

#34

Sticky Note10

Sticky Note

#35

Sticky Note11

Sticky Note

#36

Sticky Note12

Sticky Note

#37

Sticky Note13

Sticky Note

#38

Sticky Note14

Sticky Note

#39

Set text medoid threshold score

HTTP Request

#40

Sticky Note15

Sticky Note

#41

Sticky Note16

Sticky Note

#42

Sticky Note17

Sticky Note

#43

Sticky Note18

Sticky Note

#44

Sticky Note19

Sticky Note

#45

Sticky Note20

Sticky Note

#46

Sticky Note21

Sticky Note

#47

Sticky Note22

Sticky Note

#48