#!/usr/bin/env python3 """ Swagger UI Documentation Server for Memory Module Detection API This server provides interactive API documentation similar to Mini SpecsComply Pro. """ import os import io import base64 from flask import Flask, request, jsonify from flask_cors import CORS from flask_restx import Api, Resource, fields, reqparse from PIL import Image import numpy as np from werkzeug.utils import secure_filename from werkzeug.datastructures import FileStorage import tempfile import logging import time from datetime import datetime from inference_utils import MemoryModuleDetector # Configure logging logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) # Initialize Flask app for Swagger UI only app = Flask(__name__) CORS(app) # Initialize Flask-RESTX API with professional styling api = Api( app, version='1.0.0', title='Memory Module Detection API', description=''' 🔍 **AI-Powered Memory Module Detection System** Professional computer vision API for detecting memory modules in motherboard images using YOLOv8. **Features:** - Real-time memory module detection - 99.5% accuracy with YOLOv8 Nano - Multiple input formats (upload, base64, hardcoded test) - Confidence threshold control - Annotated image output **Use Cases:** - Electronic waste recycling facilities - Hardware inventory management - Quality control in manufacturing - Educational computer vision projects ''', doc='/', prefix='/api/v1', contact='Memory Module Detection Team', contact_email='support@memorydetection.ai' ) # Configuration UPLOAD_FOLDER = 'uploads' ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg', 'gif', 'bmp'} MODEL_PATH = 'runs/detect/memory_module_detection/weights/best.pt' HARDCODED_IMAGE_PATH = 'training/memory/out1.png' # Initialize detector detector = MemoryModuleDetector(MODEL_PATH) # Create upload folder os.makedirs(UPLOAD_FOLDER, exist_ok=True) def allowed_file(filename): """Check if file extension is allowed.""" return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS def image_to_base64(image): """Convert PIL image to base64 string.""" buffered = io.BytesIO() image.save(buffered, format="PNG") img_str = base64.b64encode(buffered.getvalue()).decode() return img_str # Create namespaces with descriptions ns_health = api.namespace('health', description='đŸĨ Health Check Operations') ns_detection = api.namespace('detection', description='🔍 Memory Module Detection Operations') ns_info = api.namespace('info', description='ℹī¸ API Information') # Define comprehensive API models detection_bbox = api.model('DetectionBBox', { 'x1': fields.Float(required=True, description='Top-left X coordinate'), 'y1': fields.Float(required=True, description='Top-left Y coordinate'), 'x2': fields.Float(required=True, description='Bottom-right X coordinate'), 'y2': fields.Float(required=True, description='Bottom-right Y coordinate'), 'confidence': fields.Float(required=True, description='Detection confidence score'), 'class': fields.String(required=True, description='Detected class name') }) detection_result = api.model('DetectionResult', { 'success': fields.Boolean(required=True, description='Whether detection was successful'), 'detections': fields.List(fields.Nested(detection_bbox), description='List of detected memory modules with coordinates'), 'num_detections': fields.Integer(description='Number of memory modules detected'), 'annotated_image': fields.String(description='Base64 encoded annotated image with bounding boxes'), 'confidence_threshold': fields.Float(description='Confidence threshold used for detection'), 'test_image_path': fields.String(description='Path to the test image (for hardcoded tests)'), 'processing_time_ms': fields.Float(description='Processing time in milliseconds') }) error_response = api.model('ErrorResponse', { 'error': fields.String(required=True, description='Detailed error message'), 'success': fields.Boolean(required=True, description='Always false for errors'), 'error_code': fields.String(description='Error classification code') }) health_response = api.model('HealthResponse', { 'status': fields.String(required=True, description='Overall health status', enum=['healthy', 'degraded', 'unhealthy']), 'model_loaded': fields.Boolean(required=True, description='Whether the YOLOv8 model is loaded'), 'model_path': fields.String(description='Path to the loaded model'), 'timestamp': fields.String(required=True, description='Current timestamp in ISO format'), 'uptime_seconds': fields.Float(description='API uptime in seconds'), 'memory_usage_mb': fields.Float(description='Current memory usage in MB') }) model_info = api.model('ModelInfo', { 'architecture': fields.String(description='Model architecture name'), 'version': fields.String(description='Model version'), 'classes': fields.List(fields.String, description='Detectable object classes'), 'input_size': fields.String(description='Expected input image size'), 'model_loaded': fields.Boolean(description='Model loading status'), 'accuracy_metrics': fields.Raw(description='Model performance metrics') }) api_info_response = api.model('ApiInfoResponse', { 'name': fields.String(required=True, description='API service name'), 'version': fields.String(required=True, description='API version'), 'description': fields.String(required=True, description='API description'), 'model_info': fields.Nested(model_info, description='Information about the ML model'), 'endpoints': fields.List(fields.String, description='Available API endpoints'), 'supported_formats': fields.List(fields.String, description='Supported image formats'), 'max_file_size': fields.String(description='Maximum file upload size'), 'rate_limits': fields.Raw(description='API rate limiting information') }) # ============================================================================ # API RESOURCES # ============================================================================ @ns_health.route('') class HealthCheck(Resource): @ns_health.doc('health_check') @ns_health.marshal_with(health_response) def get(self): """ đŸĨ **Check API Health Status** Returns comprehensive health information including model status, uptime, and system metrics. Use this endpoint to monitor API availability and performance. """ import psutil import time return { 'status': 'healthy' if detector.model is not None else 'degraded', 'model_loaded': detector.model is not None, 'model_path': MODEL_PATH, 'timestamp': datetime.now().isoformat(), 'uptime_seconds': time.time() - start_time, 'memory_usage_mb': psutil.Process().memory_info().rss / 1024 / 1024 } @ns_info.route('') class ApiInfo(Resource): @ns_info.doc('api_info') @ns_info.marshal_with(api_info_response) def get(self): """ ℹī¸ **Get Comprehensive API Information** Returns detailed information about the API capabilities, model specifications, supported formats, and available endpoints. """ return { 'name': 'Memory Module Detection API', 'version': '1.0.0', 'description': 'AI-powered memory module detection system for motherboard images using YOLOv8', 'model_info': { 'architecture': 'YOLOv8 Nano', 'version': '8.0.196', 'classes': ['memory_module'], 'input_size': '640x640', 'model_loaded': detector.model is not None, 'accuracy_metrics': { 'mAP50': 0.995, 'precision': 1.0, 'recall': 0.984, 'inference_time_ms': 37 } }, 'endpoints': [ '/api/v1/health', '/api/v1/info', '/api/v1/detection/upload', '/api/v1/detection/hardcoded', '/api/v1/detection/base64' ], 'supported_formats': ['PNG', 'JPG', 'JPEG', 'GIF', 'BMP'], 'max_file_size': '16MB', 'rate_limits': { 'requests_per_minute': 60, 'concurrent_requests': 10 } } # File upload parser with detailed documentation upload_parser = reqparse.RequestParser() upload_parser.add_argument( 'file', location='files', type=FileStorage, required=True, help='📁 Image file containing motherboard to analyze (PNG, JPG, JPEG, GIF, BMP)' ) upload_parser.add_argument( 'confidence', type=float, default=0.8, help='đŸŽ¯ Confidence threshold for detection (0.0-1.0, default: 0.8)' ) @ns_detection.route('/upload') class DetectionUpload(Resource): @ns_detection.doc('upload_detection') @ns_detection.expect(upload_parser) @ns_detection.marshal_with(detection_result, code=200) @ns_detection.marshal_with(error_response, code=400) @ns_detection.marshal_with(error_response, code=500) def post(self): """ 📤 **Upload Image for Memory Module Detection** Upload a motherboard image and get real-time memory module detection results. **Process:** 1. Upload image file (max 16MB) 2. AI processes image with YOLOv8 3. Returns detected memory modules with bounding boxes 4. Includes annotated image with visual markers **Supported Formats:** PNG, JPG, JPEG, GIF, BMP """ # This endpoint connects to the main API return {'error': 'This is documentation only. Use the main API at port 5002', 'success': False}, 501 # Global start time for uptime calculation start_time = time.time() if __name__ == '__main__': import time print("🚀 Starting Memory Module Detection API Documentation Server...") print("📚 Swagger UI available at: http://localhost:5003/") print("🔗 Main API running at: http://localhost:5002") print("📖 Interactive documentation with professional interface") app.run(host='0.0.0.0', port=5003, debug=True)