Retrieval-Augmented Generation Architecture for Indonesian Academic Regulation Question Answering: A Microservices-Based Implementation
Indonesian higher-education institutions operate under a dense and frequently updated body of academic regulations—national standards, institutional statutes, and study-program handbooks—that students and staff must consult accurately. General-purpose large language models answer such questions fluently but without provenance, and they hallucinate rules that do not exist. This paper proposes a retrieval-augmented generation (RAG) architecture for Indonesian academic-regulation question answering, deployed as a set of loosely coupled microservices: an API gateway, a RAG orchestrator, an embedding and retrieval subsystem backed by a FAISS vector index, a generation subsystem, and an offline ingestion pipeline. The retrieval layer combines lexical BM25 and vector similarity through reciprocal rank fusion, so that regulation passages are grounded and citable. We evaluate the retrieval core—the component that determines whether generated answers can be grounded—on an original corpus of 20 synthetic Indonesian academic-regulation passages and 30 labeled questions. Vector retrieval attains Recall@1 of 0.867, MRR@10 of 0.902, and nDCG@5 of 0.915, outperforming BM25 (0.800, 0.865, 0.898) on early precision, while BM25 is an order of magnitude faster and reaches perfect Recall@5. Retrieval latency for all configurations remains below one millisecond on a single node. The microservices decomposition lets the index be rebuilt when regulations change without redeploying the generation service. Results indicate that a hybrid retrieval core is a sound and inexpensive foundation for grounded, citable regulation question answering, and that the architecture is deployable on modest institutional infrastructure.