🤖 SMARTDRIVE - AI Service

Intelligent Content Analysis and Metadata Generation Service

📋 Overview

The AI Service is the intelligence layer of the SMARTDRIVE platform, providing advanced content analysis, metadata generation, and AI-powered insights for uploaded files. It integrates with Google Gemini AI, AWS Rekognition, and AWS Textract to deliver comprehensive file understanding.

🏗️ Architecture

┌─────────────────┐    ┌──────────────┐    ┌─────────────┐
│ File Storage    │───▶│   AI Service │───▶│ Google      │
│ Service         │    │              │    │ Gemini AI   │
└─────────────────┘    └──────────────┘    └─────────────┘
                              │
                              ▼
                       ┌─────────────┐
                       │ AWS         │
                       │ Rekognition │
                       └─────────────┘
                              │
                              ▼
                       ┌─────────────┐
                       │ AWS         │
                       │ Textract    │
                       └─────────────┘

✨ Features

🖼️ Image Analysis

• Object Detection using AWS Rekognition
• Face Recognition and analysis
• Text Extraction from images (OCR)
• Image Labeling and classification
• Content Moderation and safety checks

📄 Document Analysis

• Text Extraction using AWS Textract
• Document Structure analysis
• Form Data extraction
• Table Recognition and parsing
• Handwriting Recognition

🧠 AI-Powered Insights

• Content Summarization using Gemini AI
• Keyword Extraction and tagging
• Entity Recognition and classification
• Sentiment Analysis
• Topic Modeling

🔍 Metadata Generation

• Comprehensive Tags and categories
• Content Descriptions and summaries
• Search Optimization metadata
• Accessibility information
• Content Quality scoring

🛠️ Technology Stack

• Framework: Spring Boot 3.2
• Language: Java 17
• AI Services: Google Gemini AI, AWS Rekognition, AWS Textract
• Storage: AWS S3
• Message Queue: AWS SQS
• Monitoring: OpenTelemetry, Micrometer
• Documentation: OpenAPI 3.0 (Swagger)

🚀 Quick Start

Prerequisites

• Java 17+
• Docker & Docker Compose
• AWS Account with Rekognition and Textract access
• Google Cloud Account with Gemini AI API access

Environment Variables

# AWS Configuration
AWS_ACCESS_KEY_ID=your_access_key
AWS_SECRET_ACCESS_KEY=your_secret_key
AWS_REGION=us-east-1

# Google Gemini AI
GEMINI_API_KEY=your_gemini_api_key
GEMINI_BASE_URL=https://generativelanguage.googleapis.com/v1

# AWS Services
S3_BUCKET_NAME=smartdrive-uploads

# Service Configuration
SERVER_PORT=8082

Local Development

# Clone the repository
git clone <repository-url>
cd ai-service

# Build the project
./gradlew build

# Run with Docker Compose
docker compose up -d

# Or run locally
./gradlew bootRun

Docker Deployment

# Build Docker image
docker build -t smartdrive-ai-service .

# Run container
docker run -p 8082:8082 \
  -e AWS_ACCESS_KEY_ID=your_key \
  -e AWS_SECRET_ACCESS_KEY=your_secret \
  -e GEMINI_API_KEY=your_gemini_key \
  smartdrive-ai-service

📡 API Endpoints

Generate Metadata

POST /api/v1/metadata/generate
Content-Type: application/json

{
  "contentId": "uuid",
  "s3Key": "uuid-document.pdf",
  "fileName": "document.pdf",
  "contentType": "application/pdf",
  "size": 1024000
}

# Response
{
  "contentId": "uuid",
  "tags": ["document", "pdf", "business"],
  "summary": "Business document containing quarterly reports...",
  "imageLabels": ["text", "document", "paper"],
  "imageObjects": ["person", "chart", "graph"],
  "imageText": ["Q1 2024", "Revenue", "$1.2M"],
  "extractedText": "Quarterly Report Q1 2024...",
  "processingStatus": "COMPLETED"
}

Process Image

POST /api/v1/images/analyze
Content-Type: multipart/form-data

# Response
{
  "labels": ["person", "office", "business"],
  "objects": ["person", "desk", "computer"],
  "faces": ["adult", "male", "smiling"],
  "text": ["Meeting", "Schedule", "9:00 AM"]
}

Process Document

POST /api/v1/documents/extract
Content-Type: multipart/form-data

# Response
{
  "text": "Extracted text content...",
  "tables": [{"headers": ["Name", "Value"], "rows": [...]}],
  "forms": [{"key": "Date", "value": "2024-01-01"}]
}

🔧 Configuration

Application Properties

server:
  port: 8082

spring:
  application:
    name: ai-service

app:
  s3:
    bucket-name: ${S3_BUCKET_NAME:smartdrive-uploads}
  gemini:
    api-key: ${GEMINI_API_KEY}
    base-url: ${GEMINI_BASE_URL:https://generativelanguage.googleapis.com/v1}
  ai:
    max-image-size: 5MB
    supported-image-types:
      - image/jpeg
      - image/png
      - image/gif
    supported-document-types:
      - application/pdf
      - image/tiff
      - image/png

AI Service Configuration

@Configuration
public class AiConfig {
    @Bean
    public RekognitionClient rekognitionClient() {
        return RekognitionClient.builder().build();
    }
    
    @Bean
    public TextractClient textractClient() {
        return TextractClient.builder().build();
    }
}

📊 Monitoring

Health Checks

GET /actuator/health
GET /actuator/health/aws-rekognition
GET /actuator/health/aws-textract
GET /actuator/health/gemini-ai

Metrics

• Processing Success Rate: smartdrive.ai.processing.success.rate
• Processing Time: smartdrive.ai.processing.time
• AI Service Latency: smartdrive.ai.service.latency
• Error Rate: smartdrive.ai.error.rate

Logging

logging:
  level:
    com.smartdrive.aiservice: INFO
    software.amazon.awssdk: INFO
  pattern:
    console: "%d{HH:mm:ss.SSS} [%X{traceId:-}] %-5level %logger{20} - %msg%n"

🔒 Security

API Security

• Rate Limiting for AI API calls
• Input Validation and sanitization
• Content Filtering and moderation
• Privacy Protection for sensitive content

Data Protection

• Secure API Keys management
• Content Encryption in transit
• Audit Logging for all AI operations
• GDPR Compliance for data processing

🧪 Testing

Unit Tests

./gradlew test

Integration Tests

./gradlew integrationTest

AI Service Testing

# Test image analysis
curl -X POST http://localhost:8082/api/v1/images/analyze \
  -F "[email protected]"

# Test document extraction
curl -X POST http://localhost:8082/api/v1/documents/extract \
  -F "[email protected]"

🚀 Deployment

Docker Compose

version: '3.8'
services:
  ai-service:
    build: .
    ports:
      - "8082:8082"
    environment:
      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
      - GEMINI_API_KEY=${GEMINI_API_KEY}
    depends_on:
      - elasticsearch
      - redis

Kubernetes

apiVersion: apps/v1
kind: Deployment
metadata:
  name: ai-service
spec:
  replicas: 3
  selector:
    matchLabels:
      app: ai-service
  template:
    metadata:
      labels:
        app: ai-service
    spec:
      containers:
      - name: ai-service
        image: smartdrive/ai-service:latest
        ports:
        - containerPort: 8082
        env:
        - name: GEMINI_API_KEY
          valueFrom:
            secretKeyRef:
              name: ai-credentials
              key: gemini-api-key

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🆘 Support

• Documentation: SMARTDRIVE Docs
• Issues: GitHub Issues
• Discussions: GitHub Discussions

---

Built with ❤️ by the SMARTDRIVE Team
🌐 Website • 📚 Docs • �� GitHub