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

Architectural Evolution of Retrieval-Augmented Generation Engines: A Deep Dive into a Reactive gRPC Framework with Quarkus

, , , ,

DOI: http://dx.doi.org/10.15439/2026F0273

Citation: Sumera Batool, , , ,

Full text

Abstract. Recent advances in Artificial Intelligence (AI) have accelerated the use of Large Language Models (LLMs) in domain-specific applications, including healthcare. However, standalone LLMs remain limited by outdated internal knowledge and the risk of hallucinated responses. Retrieval-Augmented Generation (RAG) addresses this limitation by grounding generation in external knowledge sources.This paper presents the design and evaluation of a reactive gRPC-based engine implemented with Quarkus for low-latency clinical inquiry processing. The study focuses on inter-service communication efficiency through Protocol Buffers, asynchronous execution with SmallRye Mutiny, and native-oriented deployment characteristics. A key design distinction is that the current prototype employs a mock retrieval component for controlled evaluation of the communication layer rather than a production-grade vector store. Experimental results indicate that the architecture maintains sub-100 ms average latency under high concurrency while sustaining high throughput and low resource overhead, demonstrating its suitability for real-time decision-support pipelines.

References

  1. P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel, S. Riedel, and D. Kiela, “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” in Advances in Neural Information Processing Systems (NeurIPS), 2020.
  2. gRPC Authors, “gRPC: A high-performance RPC framework,” Available: https://grpc.io
  3. Quarkus Team, “Quarkus: Supersonic subatomic Java,” Available: https://quarkus.io
  4. S. Vinoski, “Java and gRPC: High performance microservices,” IEEE Internet Computing, vol. 22, no. 4, pp. 92–96, 2018.
  5. H. Newman, “Building reactive systems with asynchronous communication patterns,” IEEE Software, vol. 37, no. 2, pp. 66–72, 2020.
  6. N. M. Josuttis, SOA in Practice: The Art of Distributed System Design. Sebastopol, CA, USA: O’Reilly Media, 2007.
  7. H. Qayyum, S. T. H. Rizvi, M. Naeem, U. B. Khalid, M. Abbas, and A. Coronato, “Enhancing diagnostic accuracy for skin cancer and COVID-19 detection: A comparative study using a stacked ensemble method,” Technologies, 2024.
  8. A. Ismail, M. Naeem, M. H. Syed, M. Abbas, and A. Coronato, “Advancing patient care with an intelligent and personalized medication engagement system,” Information, 2024.
  9. 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.2279-2296.
  10. 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.
  11. 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.