Enterprise Knowledge Intelligence Through Cloud-Based Retrieval-Augmented Generation and Vector Database Architectures

Main Article Content

Dr.M.Vijay Anand

Abstract

The increasing volume of enterprise data generated through digital platforms, business applications, document repositories, and operational systems has created significant challenges in knowledge discovery, information retrieval, and organizational decision-making. Traditional information management systems often struggle to provide accurate, contextually relevant, and real-time access to distributed enterprise knowledge. This research proposes a cloud-based Enterprise Knowledge Intelligence framework integrating Retrieval-Augmented Generation (RAG) with scalable vector database architectures to improve organizational information accessibility, semantic search capabilities, and intelligent knowledge utilization. The proposed framework combines document ingestion, preprocessing, embedding generation, vector indexing, semantic retrieval, and large language model integration to deliver context-aware responses using enterprise-specific knowledge sources. Cloud infrastructure provides scalable storage, computational resources, distributed processing, and automated deployment capabilities to support growing enterprise information requirements. The research investigates the effectiveness of vector database architectures in managing high-dimensional embeddings, optimizing similarity searches, and improving retrieval performance across heterogeneous data environments. The methodology adopts a design-oriented research approach involving architectural development, experimental implementation, and comparative performance evaluation. Key evaluation parameters include retrieval accuracy, response relevance, query latency, scalability, infrastructure utilization, and operational cost. The proposed framework aims to establish a reliable and scalable knowledge intelligence architecture that improves enterprise productivity, supports informed decision-making, and enables secure access to organizational knowledge through intelligent cloud-based information retrieval.

1 2

Article Details

Section

Articles

How to Cite

Enterprise Knowledge Intelligence Through Cloud-Based Retrieval-Augmented Generation and Vector Database Architectures. (2026). International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 9(4), 1669-1677. https://doi.org/10.15662/IJRPETM.2026.0904013

References

1. Shao, Z., Zhao, R., Yuan, S., Ding, M., & Wang, Y. (2022). Tracing the evolution of AI in the past decade and forecasting the emerging trends. Expert Systems with Applications, 209, Article 118221. https://doi.org/10.1016/j.eswa.2022.118221

2. Bellundagi, M. (2024). An intelligent digital transformation framework for smart enterprises using AI and cloud computing. International Journal of Humanities and Information Technology, 6(3), 178–197.

3. Kommineni, R. (2026). Guarded autonomy for alert-driven remediation: Context-aware decisions and crash-safe execution in multi-cloud Kubernetes. International Journal of Engineering & Extended Technologies Research, 8(1), 262–268.

4. Bheemisetty, N. (2025). A unified hybrid architecture for real-time risk detection and cloud cost optimization in banking and healthcare. International Journal of Scientific Research in Engineering & Technology, 5(6), 188–194. https://doi.org/10.59256/ijsreat.20250506028

5. Kannan, K. S., Sunitha, G., Deepa, S. N., Babu, D. V., & Avanija, J. (2022). A multi-objective load balancing and power minimization in cloud using bio-inspired algorithms. Computers and Electrical Engineering, 102, 108225.

6. Namdeo, A. (2025). Explainable AI dashboards for regulatory governance BI. International Journal of Emerging Trends in Computer Science and Information Technology, 6(2), 168–174. https://doi.org/10.63282/3050-9246.IJETCSIT-V6I2P118

7. Aragani, V. M., Maroju, P. K., & Mudunuri, L. N. R. (2024, December). Implementing Non-functional Production Regression Testing with Kubernetes. In International Conference on Information and Communication Technology for Competitive Strategies (pp. 231-244). Singapore: Springer Nature Singapore.

8. Kopparthi, G. S., Dhanalakshmi, C., Chandel, P., Mamoria, P., & Mohideen, A. S. (2026). Ethical AI in Education: Balancing Automation with Human-Centered Learning. International Journal of Computer Information Systems & Industrial Management Applications, 18, 936.

9. Karuturi, Y. (2025). Kubernetes-based containerization framework for SAP S/4HANA workloads in hybrid cloud environments. International Research Journal of Innovative Engineering, 9(6), 17985–17995.

10. Gadige, C. D. (2024). Event-driven CRM architecture for real-time order fulfillment and product provisioning. International Journal of Engineering & Extended Technologies Research (IJEETR), 6(2), 7968-7978.

11. Pal, A. (2026). Neural network-based financial modeling for cash flow prediction and revenue forecasting. American International Journal of Computer Science and Technology, 8(2), 37–47. https://doi.org/10.63282/3117-5481/AIJCST-V8I2P104

12. Reddy, K. V. (2024). Formal Verification with ABV: A Superior Alternative to UVM for Complex Computing Chips. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 10(6), 90-98.

13. Randhi, K. S. (2022). A scalable integration framework for enterprise application metadata aggregation and synchronization. International Journal of Research Publications in Engineering, Technology and Management, 5(2), 6564–6581.

14. Gazi, M. S., Tasnim, M., Enayet, M. A., Chowdhury, J. A., Ullah, S., Akter, A., Rahman, M. R., & Khan, M. A. N. (2024). A novel framework for memory-resident malware investigation and forensic evidence reconstruction. International Journal of Research and Applied Innovations, 7(3), 10910–10921.

15. Karrothu, A. (2025). Policy-as-code framework for automated security and compliance enforcement in cloud-native infrastructure. International Journal of Research Publications in Engineering, Technology and Management, 8(6), 13496–13511.

16. Ravichandran, S., & Kandasamy, V. (2025). Optimized Attention Augmented Residual Convolutional Neural Network with Fa-Resnet for Fabric Defect Detection. Journal of Control Engineering and Applied Informatics, 27(4), 3-15.

17. Uddandarao, D. P., Konatham, M. R., & Vadlamani, R. K. (2025). Robust and scalable statistical models for high-dimensional marketing data applications: A comprehensive review. In 2025 IEEE 5th International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT) (pp. 1-8). IEEE. https://doi.org/10.1109/icerect65215.2025.11377070

18. Shaik, N. (2025). Securing kubernetes: An integrated approach to ai-driven threat detection and EBPFbased security monitoring. International Journal of Research and Applied Innovations, 8(2), 11289-11294.

19. Manoharan, D. (2026). Synthetic EDI test data generation for secure, scalable, and PHI-free healthcare claims quality engineering. Journal of International Crisis and Risk Communication Research, 9(1), 358–371.

20. Jinna, K. R., & Kondisetty, K. (2023). Autoscaling economics for persistent inference workloads: Evaluating resource-, event-and schedule-driven scaling on Kubernetes. International Journal of Research and Applied Innovations, 6(2), 8628-8638.

21. Ambati, K. C. (2024). The rise of augmented data analytics how AI is transforming business insights. International Journal of Computer Technology and Electronics Communication, 7(6), 10068–10076.

22. Ponugoti, M. (2023). Frameworks for ensuring compliance in digital platform governance. International Journal of Engineering & Extended Technologies Research (IJEETR), 5(6), 7575-7586.

23. Neela, S. (2025). A next-generation middleware architecture for seamless enterprise integration and real-time analytics. International Journal of Engineering & Extended Technologies Research (IJEETR), 7(6), 11332-11336.

24. Basavala, S. R. (2025). Continuous application security posture management through AI-driven risk correlation and vulnerability prioritization. International Journal of Research Publications in Engineering, Technology and Management, 8(3), 12175–12187.

25. Beeram, S. (2023). Energy efficiency and carbon-aware workload scheduling in Azure. International Journal of Research and Applied Innovations, 6(5), 9626–9628. https://doi.org/10.15662/IJRAI.2023.0605019

26. Kopparthi, G. S. (2022). AI in healthcare: Unlocking the potential of predictive analytics. Journal of Computational Analysis and Applications, 30(2), 1183–1193. https://eudoxuspress.com/index.php/pub/article/view/5508

27. Pal, A. (2025). From months to weeks: How embedded-finance platforms are re-engineering the way brands become banks. International Journal of Advances in Signal and Image Sciences, 11(6s), 2096–2104.

28. Singh, I. K. (2025). AI-assisted ontology development: Automating enterprise vocabulary management using large language models and SPARQL. American International Journal of Computer Science and Technology, 7(1), 163–174. https://doi.org/10.63282/3117-5481/AIJCST-V7I1P114

29. Mahajan, A. S. (2025). Decision-first enterprises: Transforming business through intelligent data systems. Book Rivers.

30. Kalakoti, M. K. R. (2023). AI-driven infrastructure orchestration for large-scale e-commerce platforms during global product launches. International Journal of Computer Technology and Electronics Communication, 6(4), 7388–7399.

31. Ahuja, D. (2025). Securing Container Isolation in Multi-Tenant Environments. Journal of Computer Science and Technology Studies, 7(10), 225-232.

32. Thakur, N., Singh, A., & Sangal, A. L. (2022). Cloud services selection: A systematic review and future research directions. Computer Science Review, 46, Article 100514. https://doi.org/10.1016/j.cosrev.2022.100514