Landscape image classification via vector search and KN

This automation enables landscape type classification from image URLs without training a model. It uses multimodal embeddings from Voyage AI and vector search in Qdrant to identify the closest matches and classify the input image via majority voting. Designed for satellite imagery analysis, geospatial data processing, and computer vision research.

## Who it´s for
- Satellite imagery analysts
- Developers building image classification systems
- Computer vision researchers
- Companies working with geospatial data

## What the automation does
- Accepts an image URL as input via execute_workflow_trigger
- Generates a multimodal embedding using Voyage AI API
- Queries Qdrant Cloud for nearest vector neighbors
- Classifies the image based on label majority vote among neighbors
- In case of a tie, increases the number of neighbors until consensus is reached
- Returns the predicted landscape category (e.g., ´agricultural´, ´forest´)

## What´s included
- Ready-to-use n8n workflow
- Trigger logic for execute_workflow_trigger
- Integrations with Voyage AI, Qdrant Cloud, and Google Cloud Storage
- Basic setup and adaptation guide

## Requirements for setup
- n8n account (cloud or self-hosted)
- Voyage AI API key
- Qdrant Cloud instance with pre-loaded vector database
- Image storage (e.g., Google Cloud Storage) accessible via public URL

## Benefits and outcomes
- High accuracy classification without model training (up to 93.24%)
- Automated processing of large image batches
- Flexible foundation for extension (new classes, sources)
- Scalable due to cloud-native architecture
- Time savings on manual labeling and review

## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via Telegram: @gleb923.