Article Open Access

Vectorized Enterprise Knowledge Systems: Transforming Organizational Intelligence Using Retrieval-Augmented AI

Ananda Kumar Dey

Abstract


Large-scale liquefied natural gas (LNG) projects represent some of the most logistically complex undertakings in industrial engineering, requiring the coordinated fabrication of tens of thousands of pipe spools across geographically distributed facilities while maintaining strict cost, schedule, quality, and regulatory requirements. Despite advances in digital manufacturing, limited research has examined how integrated material requirements planning (MRP) systems support synchronized fabrication at mega-project scale. This paper investigates the implementation of an integrated MRP framework at Fabrication & Manufacturing facilities supporting LNG projects, where approximately 100,000 pipe spools were fabricated across six production facilities using a centralized planning and distributed execution architecture. The proposed framework aligns with Advanced Work Packaging (AWP) principles recommended by the Construction Industry Institute (CII), ISA-95 enterprise-control integration standards, and ASME/API engineering compliance requirements to enhance coordination between planning, procurement, inventory management, and shop-floor execution. The implementation introduces a bidirectional integration model between the MRP system and the Manufacturing Execution System (MES), enabling real-time synchronization of production schedules, material availability, fabrication status, and inventory data across all participating facilities. Furthermore, a centralized pre-buy material distribution strategy minimizes procurement uncertainty and improves supply chain responsiveness. Empirical results demonstrate an 18–25% reduction in procurement lead time, a 20–30% increase in fabrication productivity through AWP-aligned sequencing, and improved schedule reliability across multi-site operations. The integrated digital planning architecture also enhanced resource utilization, reduced production bottlenecks, and strengthened cross-facility coordination. These findings establish integrated MRP implementation as a critical enabler of efficient mega-scale LNG fabrication delivery and provide a practical, scalable, and replicable framework for engineering, procurement, and construction (EPC) contractors managing highly complex industrial projects


Keywords


Cloud Modernization, Embedding Models, Enterprise Data Platform Architecture, Generative AI, Hybrid Retrieval

References


P. Lewis et al., "Retrieval-augmented generation for knowledge-intensive NLP tasks," Adv. Neural Inf. Process. Syst., vol. 33, pp. 9459–9474, 2020.

E. Karakurt and A. Akbulut, "Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) for Enterprise Knowledge Management and Document Automation: A Systematic Literature Review," Appl. Sci., vol. 16, no. 1, p. 368, 2025.

V. Karpukhin et al., "Dense passage retrieval for open-domain question answering," in Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), 2020, pp. 6769–6781.

A. Alansari and H. Luqman, "Large language models hallucination: A comprehensive survey," Comput. Sci. Rev., vol. 61, p. 100970, 2026.

V. Magesh, F. Surani, M. Dahl, M. Suzgun, C. D. Manning, and D. E. Ho, "Hallucination-free? Assessing the reliability of leading AI legal research tools," J. Empir. Leg. Stud., vol. 22, no. 2, pp. 216–242, 2025.

H. Choi, J. Kim, S. Joe, and Y. Gwon, "Evaluation of BERT and Albert sentence embedding performance on downstream NLP tasks," in 2020 25th International Conference on Pattern Recognition (ICPR), 2021, pp. 5482–5487.

N. Muennighoff, N. Tazi, L. Magne, and N. Reimers, "Mteb: Massive text embedding benchmark," in Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023, pp. 2014–2037.

S. Bruch, S. Gai, and A. Ingber, "An analysis of fusion functions for hybrid retrieval," ACM Trans. Inf. Syst., vol. 42, no. 1, pp. 1–35, 2023.

C. Sharma, "Retrieval-augmented generation: A comprehensive survey of architectures, enhancements, and robustness frontiers," arXiv Prepr. arXiv2506.00054, 2025.

A. Singh, A. Ehtesham, S. Kumar, T. T. Khoei, and A. V Vasilakos, "Agentic retrieval-augmented generation: A survey on agentic rag," arXiv Prepr. arXiv2501.09136, 2025.

D. Edge et al., "From local to global: A graph rag approach to query-focused summarization," arXiv Prepr. arXiv2404.16130, 2024.

M. Dehghankar and A. Asudeh, "HENN: A Hierarchical Epsilon Net Navigation Graph for Approximate Nearest Neighbor Search," arXiv Prepr. arXiv2505.17368, 2025.

T. Taipalus, "Vector database management systems: Fundamental concepts, use-cases, and current challenges," Cogn. Syst. Res., vol. 85, p. 101216, 2024.

Q. Chen et al., "Spann: Highly-efficient billion-scale approximate nearest neighborhood search," Adv. Neural Inf. Process. Syst., vol. 34, pp. 5199–5212, 2021.

H. Jin, J. Lee, S. Piao, S. Seo, S. Kwon, and S. Park, "Efficient Approximate Nearest Neighbor Search via Data-Adaptive Parameter Adjustment in Hierarchical Navigable Small Graphs," in 2025 Design, Automation & Test in Europe Conference (DATE), 2025, pp. 1–7.

M. K. U. Achyar, A. R. Pratama, and others, "RAG Chatbot Architecture for Law & Crime News Using Hybrid Retrieval and Small Language Model," in 2025 5th International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA), 2025, pp. 588–593.

A. J. Oche, A. G. Folashade, T. Ghosal, and A. Biswas, "A systematic review of key retrieval-augmented generation (rag) systems: Progress, gaps, and future directions," arXiv Prepr. arXiv2507.18910, 2025.

L. Aluso and J. O. Enyejo, "Leveraging NLP and Retrieval-Augmented Generation (RAG) Models for Automated Business Intelligence Query Resolution," Int J Sci Res Sci Eng Technol, vol. 11, no. 4, pp. 534–557, 2024.

S. Packowski, I. Halilovic, J. Schlotfeldt, and T. Smith, "Optimizing and evaluating enterprise retrieval-augmented generation (rag): A content design perspective," in Proceedings of the 2024 8th International Conference on Advances in Artificial Intelligence, 2024, pp. 162–167.

S. Pandit, R. N. Ravikumar, N. Joshi, S. Pandit, S. Kishore, and S. Aarthi, "Retrieval-Augmented Generation (RAG) for Enterprise Intelligence: Architectures, Applications, and Future Trends," in Leveraging LLMs for Business Innovation: Practical Solutions and Future Trends, IGI Global Scientific Publishing, 2026, pp. 69–106.

A. Nagori, R. A. Casonatto, A. Gautam, A. M. S. Cheruvu, and R. Kamaleswaran, "Open-Source Agentic Hybrid RAG Framework for Scientific Literature Review," arXiv Prepr. arXiv2508.05660, 2025.

F. Gao, S. Xu, W. Hao, and T. Lu, "KA-RAG: Integrating Knowledge Graphs and Agentic Retrieval-Augmented Generation for an Intelligent Educational Question-Answering Model," Appl. Sci., vol. 15, no. 23, p. 12547, 2025.

Y. S. Aluri, "Retrieval-Augmented Engineering Systems for Enterprise Knowledge Intelligence," Am. Int. J. Comput. Sci. Technol., vol. 6, no. 2, pp. 84–95, 2024.

C. Cheerla, "Advancing retrieval-augmented generation for structured enterprise and internal data," arXiv Prepr. arXiv2507.12425, 2025.




DOI: https://doi.org/10.52088/ijesty.v6i2.1845

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Ananda Kumar Dey

International Journal of Engineering, Science, and Information Technology (IJESTY) eISSN 2775-2674