This paper presents a novel approach to support complex maintenance procedures through a dialogue-driven digital assistant using an ontology-based retrieval augmented generation method. The core of the proposed system relies on the strong formalisation capabilities of the graph-based Web Ontology Language (OWL), combined with various retrieval algorithms and different Large Language Models (LLMs) to determine the most useful context for answering user queries. To do this, we use the popular principle of Retrieval Augmented Generation (RAG). Graph traversal enriches the contextual knowledge, enabling more accurate and context-aware responses. An evaluation using an OWL example ontology and an extensive Q&A dataset demonstrates the improved retrieval quality achieved by combining classical and vector-based semantic matching methods. The community-driven analysis of generation quality illustrates the usability of an OWL-based assistant for maintenance procedures on the basis of contexts and LLMs of varying configurations.