The Internet of Drones (IoD) is transforming autonomous aerial missions in applications like disaster response, agriculture, and infrastructure monitoring. Traditional Unmanned Aerial Vehicle (UAV) decision-making systems are typically challenged by real-time responsiveness, safety, and interpretability. In this study, we propose a new hybrid decision-making system that fuses Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) for improved UAV autonomy. By leveraging real-time sensor readings and past mission logs, our system allows drones to make contextual decisions with greater reliability and interpretability. Our suggested methodology is realized in an IoD platform, where LLMs produce adaptive commands by learning context-dependent information from a structured knowledge graph. Experimental tests, performed in both simulation and real-world settings, show that our framework greatly enhances decision accuracy. The LLM-RAG system realized 92% decision accuracy that led to its 94% mission success rate in dynamic environments. The system further guarantees auditable decision-making by tracing all UAV actions back to their retrieved historical context. The findings show the promise of integrating LLM with RAG in real-time UAV operations, an interpretable and scalable solution for tomorrow’s autonomous drone missions. Future research will concentrate on optimization of computational efficiency, integration of edge-based inference, and expansion to multi-agent UAV coordination.