Workflow Overview

This is an Unmanned Aerial Vehicle (UAV) Image-Based Crop Health Monitoring workflow template built on N8N. The workflow receives farmland images captured by drones and leverages AI technologies for intelligent analysis, enabling automated monitoring and recording of crop health conditions. The system integrates vector database storage, AI-powered question-answering, and data logging capabilities to support precision agriculture.

Core Features

1. Intelligent Image Analysis

• Receives farmland image data collected by drones
• Uses AI to analyze crop health status
• Builds a knowledge base to support intelligent queries

2. Vectorized Storage

• Converts analysis results into vector data
• Stores vectors in a Supabase vector database
• Supports efficient semantic retrieval

3. Intelligent Conversation System

• AI-powered Q&A based on the Anthropic Claude model
• Context-aware memory functionality
• Capable of querying historical analysis data

Detailed Node Analysis

Input Nodes

Node Name	Type	Description
Webhook	n8n-nodes-base.webhook	POST endpoint /drone_image_crop_health for receiving drone image data

Data Processing Nodes

Node Name	Type	Description
Splitter	textSplitterCharacterTextSplitter	Splits long text into chunks of 400 characters with 40-character overlap
Embeddings	embeddingsOpenAi	Generates text vector embeddings using OpenAI

Storage Nodes

Node Name	Type	Description
Insert	vectorStoreSupabase	Inserts vector data into the Supabase database index drone_image_crop_health
Query	vectorStoreSupabase	Queries relevant information from the vector database

AI Intelligence Nodes

Node Name	Type	Description
Tool	toolVectorStore	Vector store tool for use by the AI Agent
Memory	memoryBufferWindow	Conversation memory buffer to maintain contextual continuity
Chat	lmChatAnthropic	Anthropic Claude language model
Agent	agent	AI intelligent agent integrating tools and memory

Output Nodes

Node Name	Type	Description
Sheet	googleSheets	Appends processing results to a Google Sheets log sheet

Auxiliary Nodes

Node Name	Type	Description
Sticky	stickyNote	Workflow annotation note titled "Drone Image Crop Health"

Data Flow Diagram

[Webhook receives data]
        ↓
    ┌───┴───┐
    ↓       ↓
[Text Splitting] [Memory Buffer]
    ↓           ↓
[Vector Embedding] ↓
    ↓           ↓
    ├→[Store in Supabase]
    ↓           ↓
[Query Vector DB] ↓
    ↓           ↓
[Create Tool]   ↓
    ↓           ↓
    └→[AI Agent]←[Claude Model]
           ↓
    [Log to Google Sheets]

Technology Stack

Services Used

1. OpenAI API – Text vectorization
2. Supabase – Vector database storage
3. Anthropic Claude – AI conversational model
4. Google Sheets – Data logging

Key Configuration Parameters

• Text splitting: Chunk size of 400 characters with 40-character overlap
• Vector index name: drone_image_crop_health
• Trigger method: Webhook POST request
• Execution order: v1 version

Application Scenarios

Primary Use Cases

1. Precision Agriculture Monitoring – Real-time analysis of crop growth conditions
2. Pest & Disease Early Warning – Early detection of crop health issues
3. Yield Prediction – Harvest forecasting based on health data
4. Farm Management Decision Support – Data-driven planting recommendations

Business Value

• Improves agricultural production efficiency
• Reduces manual field inspection costs
• Enables data-driven farm management
• Builds an agricultural knowledge base

Deployment Requirements

Required API Credentials

1. OpenAI API key
2. Supabase database credentials
3. Anthropic API key
4. Google Sheets OAuth2 authentication

Prerequisites

1. Create a Supabase vector database table
2. Configure Google Sheets document ID
3. Set up the Webhook endpoint
4. Initialize the vector index

Enhancement Suggestions

1. Add Image Recognition – Integrate computer vision models to process images directly
2. Real-Time Alerting System – Implement anomaly detection and notification features
3. Data Visualization – Build dashboards to display analysis results
4. Multi-Source Data Fusion – Incorporate weather, soil, and other multidimensional data
5. Batch Processing – Support parallel analysis of multiple images

Summary

This workflow template demonstrates how modern AI technologies can be applied to agriculture. By combining drone image acquisition, vectorized storage, intelligent analysis, and automated logging, it establishes a complete crop health monitoring system. The system not only handles real-time data but also provides intelligent query services through an AI conversational interface, offering robust technical support for precision agriculture.