Logo PTI Logo FedCSIS

Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 47

Prototype of a Microservice-Based Decision Support System Using Natural Language Interaction and Mock RAG Inference Engine

, , , ,

DOI: http://dx.doi.org/10.15439/2026F6029

Citation: Daniyal Qasim Khan, , , ,

Full text

Abstract. This paper presents a microservice-based decision support system designed for natural language interaction and efficient service communication. The proposed architecture integrates REST for external client interaction and gRPC for internal service-to-service communication, enabling a clear separation between user-facing components and inference logic. To validate the architectural design without the overhead of full AI deployment, a Mock Retrieval-Augmented Generation (RAG) inference engine is introduced, simulating structured reasoning behavior while maintaining compatibility with future real-world RAG integration. The system processes natural language queries and produces structured outputs including diagnosis labels, keyword extraction, follow-up questions, and emergency indicators. Experimental evaluation under simulated workloads demonstrates a significant reduction in latency and improved throughput when using gRPC for internal communication compared to a REST-only design. The results highlight the effectiveness of protocol-aware service decomposition in improving system performance and scalability. The proposed architecture provides a flexible and extensible foundation for integrating advanced AI-driven inference systems in future implementations.

References

  1. P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W. Yih, T. Rocktäschel, S. Riedel, and D. Kiela, “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” in Advances in Neural Information Processing Systems, 2020.
  2. S. Newman, Building Microservices. Sebastopol, CA, USA: O’Reilly Media, 2015.
  3. gRPC Authors, “gRPC Documentation,” online documentation.
  4. Quarkus Team, “Quarkus Documentation,” online documentation.
  5. Google, “Protocol Buffers Language Guide,” online documentation.
  6. Qayyum, H., Rizvi, S.T.H., Naeem, M., Khalid, U.B., Abbas, M. and Coronato, A., 2024. Enhancing diagnostic accuracy for skin cancer and covid-19 detection: A comparative study using a stacked ensemble method. Technologies, 12(9), p.142.
  7. A. Gao, C. Chen, J. Wang, and Y. Liu, “A Survey on RetrievalAugmented Text Generation,” arXiv preprint, 2023.
  8. Zaman Khan, H., Naeem, M., Guarasci, R., Bint-Khalid, U., Esposito, M. and Gargiulo, F., 2024. Enhancing text classification using BERT: A transfer learning approach. Computación y Sistemas, 28(4), pp.22792296.
  9. D. Jurafsky and J. H. Martin, Speech and Language Processing. Draft online edition.
  10. Ismail, A., Naeem, M., Khalid, U.B. and Abbas, M., 2025. Improving adherence to medication in an intelligent environment using reinforcement learning. Journal of Reliable Intelligent Environments, 11(1), p.3.
  11. C. Richardson, Microservices Patterns. Manning Publications, 2018.
  12. Ismail, A., Naeem, M., Syed, M.H., Abbas, M. and Coronato, A., 2024. Advancing patient care with an intelligent and personalized medication engagement system. Information, 15(10), p.609.
  13. M. Luo, J. Chen, and K. Li, “A Comparative Study of REST and gRPC for Microservice Communication,” in Proc. Int. Conf. on Cloud and Service Engineering, 2021.
  14. E. Turban, R. Sharda, and D. Delen, Decision Support and Business Intelligence Systems. Pearson, 2011.
  15. Rizvi, S.T.H., Kanwal, N. and Naeem, M., 2025. Bridging simplicity and sophistication using glinear: A novel architecture for enhanced time series prediction. Digital Signal Processing, p.105702.
  16. Shehzad, F., Minutolo, A. and Esposito, M., 2024. Designing and evaluating a dual-stream transformer-based architecture for visual question answering. IEEE Access, 12, pp.195561-195574.
  17. Shehzad, F., Mennella, C., Esposito, M. and Minutolo, A., 2026. Efficient multimodal learning using BERT and vision transformers for visual question answering on peripheral blood cells. Discover Artificial Intelligence, early access.
  18. Y. Liu et al., “Retrieval-Augmented Generation for Large Language Models: A Survey,” arXiv, 2023.
  19. S. Newman, Monolith to Microservices. O’Reilly, 2019.