Classify land-use images from URL using KNN and Qdrant

This automation template enables land-use classification of satellite imagery without training machine learning models. It takes an image URL as input and returns a land-use category using multimodal embeddings and vector search. Ideal for analysts and engineers who need fast, accurate image classification without model development.

## Who it´s for
- Satellite image processing specialists
- Developers of automated image classification systems
- Researchers in remote sensing
- Companies using land-use analysis
- Engineers building computer vision pipelines without ML training

## What the automation does
- Accepts an image URL as input via execute_workflow_trigger
- Generates image embedding using Voyage AI API
- Queries nearest neighbors in Qdrant Cloud via vector search
- Performs majority voting on neighbor labels to determine image class
- In case of a tie, iteratively increases neighbor count until consensus
- Returns final land-use class (e.g., ´forest´, ´airplane´, ´denseresidential´)

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

## Requirements for setup
- n8n account or instance
- Voyage AI API key
- Access to Qdrant Cloud (or self-hosted instance)
- Image storage (e.g., Google Cloud Storage)

## Benefits and outcomes
- No model training required — leverages pre-trained embedding models
- High accuracy through KNN and vector similarity search
- Automatic tie resolution improves result reliability
- Scalable — easily integrated into existing CV pipelines
- Saves time on building custom classification systems
- Supports dynamic neighbor expansion for higher confidence

## 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.