Modern warehouse operations depend heavily on effective inventory management because manual procedures frequently result in mistakes and inefficiency. This study investigates the possibility of an AI- inventory management system powered by drone-assisted integrated with barcode detection, decoding, and optical character recognition (OCR). Our objective is to automate error detection, inventory level checks, and product placement verification to reduce human interaction and increase accuracy. The main components of the study are text recognition using OCR models, barcode decoding using the Pyzbar library, and barcode detection using the YOLOv8 model. After training and validating on a variety of barcode and QR code datasets, YOLOv8 achieved a mean average precision (mAP@0.5) of 0.97 for barcodes, a precision of 0.858, and a recall of 0.907. When using Pyzbar for barcode decoding, it was able to correctly decode 75% of all barcodes and 93% of the YOLOv8 identified barcodes. EasyOCR achieved a character-level accuracy of 0.91 and an exact match accuracy of 0.56 for text recognition, outperforming Tesseract and TrOCR. This study contributes to Saudi Vision 2030 by supporting digital transformation in logistics and aligning with the Sustainable Development Goals (SDGs), particularly Goal 9. Through automation, improved resource efficiency, and sustainable practices, this project not only advances warehouse management but also fosters economic diversification and innovation.