Agnostic Multi-Source Retrieval-Augmented Generation for Documents and Database Question Answering
Jurnal Ragam Pengabdian · 29.07.2026 · 3 (2) · 4851-4886
DOI: 10.62710/qw0ytn73 ↗Kurz gefasst
Fachartikel in der Zeitschrift Jurnal Ragam Pengabdian, online erschienen am 29.07.2026. Verfasst von Krisna Dwi Setya Adi und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
Key personnel turnover creates knowledge gaps in document-based service organizations, where information is distributed across technical specifications, operational databases, and team discussions. This study develops a multi-source Retrieval-Augmented Generation (RAG) based Question Answering (QA) system that automatically integrates heterogeneous knowledge sources through a unified source parameter. Using the Adapter Pattern, the system converts PDF/TXT documents and PostgreSQL tables into a common representation, builds a FAISS vector index, retrieves relevant context, and generates grounded answers with Gemini 2.5 Flash. Evaluation employs eight metrics and three composite scores: Knowledge Transfer Effectiveness (KTE), Multi-Source Retrieval Score (MSRS), and Answer Quality Index (AQI). Experiments were conducted on the BOND_SYS dataset using 25 Indonesian questions covering specification documents, an 8-table PostgreSQL database, and 908 developer discussion messages. Results show perfect retrieval performance (Precision@K = 1.000; MRR = 1.000) across all scenarios. The full hybrid configuration achieves the highest Overall score (0.373), while Scenario C records the highest MSRS (0.825). Scenario E obtains ROUGE-L = 0.181 and BLEU-1 = 0.196 using five manually curated reference answers. Two baseline comparisons further support this contribution: a zero-shot LLM without retrieval correctly answered only 8% of questions, while a BM25 keyword-search baseline, competitive on single-source scenarios, was outperformed on cross-referencing tasks, underscoring the added value of dense multi-source retrieval. The findings demonstrate that integrating formal documents, structured databases, and discussion logs enhances knowledge transfer and question answering for organizational support and employee onboarding.
Zitieren
APA
Adi, K. D. S., & Siregar, I. M. (2026). Agnostic Multi-Source Retrieval-Augmented Generation for Documents and Database Question Answering. Jurnal Ragam Pengabdian, 3(2), 4851-4886. https://doi.org/10.62710/qw0ytn73
Vancouver
Adi KDS, Siregar IM. Agnostic Multi-Source Retrieval-Augmented Generation for Documents and Database Question Answering. Jurnal Ragam Pengabdian. 2026;3(2):4851-4886. doi:10.62710/qw0ytn73
BibTeX
@article{Adi2026,
author = {Adi, Krisna Dwi Setya and Siregar, Ivan Michael},
title = {Agnostic Multi-Source Retrieval-Augmented Generation for Documents and Database Question Answering},
journal = {Jurnal Ragam Pengabdian},
year = {2026},
volume = {3},
number = {2},
pages = {4851--4886},
doi = {10.62710/qw0ytn73}
}
EUVIMED