Citation :

Dhruv Kumar Seth, Karan Kumar Ratra, "Hierarchical Agentic RAG Framework for Intelligent Product Discovery in Distributed E-Commerce Microservices Using MCP and Dynamic Context-Aware Vector Intelligence," International Journal of Computer Trends and Technology (IJCTT), vol. 74, no. 6, pp. 22-32, 2026. Crossref, https://doi.org/10.14445/22312803/IJCTT-V74I6P103

Abstract

Modern e-commerce platforms increasingly rely on distributed microservice architectures in which product catalog management, search, recommendation, pricing, inventory, promotions, and order fulfillment operate as independent services. Product information and operational signals are distributed across these services and must be coordinated during query processing. Consequently, product discovery extends beyond traditional search by integrating semantic relevance, user context, and real-time operational constraints across multiple services. This paper presents HAAF, a Hierarchical Agentic RAG Framework for intelligent product discovery in distributed e-commerce environments. The framework introduces collaborative multi-agent orchestration, integrated with Model Context Protocol (MCP)-based inter-service communication and Dynamic Context-Aware Vector Intelligence (DCVI). DCVI continuously captures contextual information from multiple dimensions, including user behavior, session activity, product relationships, inventory conditions, and real-time events, and combines them using an adaptive weighting mechanism. HAAF integrates Reciprocal Rank Fusion (RRF) to combine dense semantic retrieval and sparse keyword-based retrieval within a unified architecture. The framework is designed to support flexible, context-sensitive product discovery across distributed e-commerce environments and serves as an architectural foundation for future empirical evaluation and large-scale implementation.

Keywords

Agentic AI, Retrieval-Augmented Generation, E-Commerce Microservices, Intelligent Product Discovery, Model Context Protocol, Vector Databases, Multi-Agent Systems, Dynamic Context Intelligence, Reciprocal Rank Fusion, Distributed Systems.

References

[1] Patrick Lewis et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” Advances in Neural Information Processing Systems, vol. 33, pp. 9459-9474, 2020.
[Google Scholar] [Publisher Link]

[2] Vladimir Karpukhin et al., “Dense Passage Retrieval for Open-Domain Question Answering,” Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, EMNLP, pp. 6769-6781, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Akari Asai et al., “Self-RAG: Learning to Retrieve, Generate, and Critique Through Self-Reflection,” International Conference on Learning Representations Proceedings, vol. 2024, pp. 1-30, 2024.
[Google Scholar] [Publisher Link]

[4] Shunyu Yao et al., “React: Synergizing Reasoning and Acting in Language Models,” arXiv Preprint, pp. 1-33, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Qingyun Wu et al., “Autogen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation,” arXiv Preprint, pp. 1-43, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Timo Schick et al., “Toolformer: Language Models can Teach Themselves to use Tools,” Advances in Neural Information Processing Systems, vol. 36, pp. 1-13, 2023.
[Google Scholar] [Publisher Link]

[7] Xiangnan He et al., “Neural Collaborative Filtering,” arXiv Preprint, pp. 1-10, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Paul Covington, Jay Adams, and Emre Sargin, “Deep Neural Networks for Youtube Recommendations,” Proceedings of the 10^th ACM Conference on Recommender Systems, Association for Computing Machinery, New York, NY, United States, pp. 191-198, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Kelvin Guu et al., “REALM: Retrieval-Augmented Language Model Pre-Training,” Proceedings of the 37^th International Conference on Machine Learning, PMLR, vol. 119, pp. 3929-3938, 2020.
[Google Scholar] [Publisher Link]

[10] Jacob Devlin et al., “BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding,” Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, NAACL, vol. 1, pp. 4171-4186, 2019. [CrossRef] [Google Scholar] [Publisher Link]

[11] Jeff Johnson, Matthijs Douze, and Hervé Jégou, “Billion-Scale Similarity Search with GPUs,” IEEE Transactions on Big Data, vol. 7, no. 3, pp. 535-547, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Yu A. Malkov, and D.A. Yashunin, “Efficient and Robust Approximate Nearest Neighbor Search using Hierarchical Navigable Small World Graphs,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 4, pp. 824-836, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Will Hamilton, Zhitao Ying, and Jure Leskovec, “Inductive Representation Learning on Large Graphs,” Advances in Neural Information Processing Systems, vol. 30, pp. 1-11, 2017.
[Google Scholar] [Publisher Link]

[14] Petar Veličković et al., “Graph Attention Networks,” arXiv Preprint, pp. 1-12, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Model Context Protocol, What is the Model Context Protocol (MCP)?, Model Context Protocol, 2024. [Online]. Available: https://modelcontextprotocol.io/docs/getting-started/intro

[16] Jianmo Ni, Jiacheng Li, and Julian McAuley, “Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects,” Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9^th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Association for Computational Linguistics, Hong Kong, China, pp. 188-197, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Stephen Robertson, and Hugo Zaragoza, “The Probabilistic Relevance Framework: BM25 and Beyond,” Foundations and Trends in Information Retrieval, vol. 4, no. 1-2, pp. 1-59, 2009.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Weijia Shi et al., “REPLUG: Retrieval-Augmented Language Model Pre-Training,” arXiv Preprint, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Joon Sung Park et al., “Generative Agents: Interactive Simulacra of Human Behavior,” arXiv Preprint, pp. 1-22, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Balázs Hidasi et al., “Session-based Recommendations with Recurrent Neural Networks,” arXiv Preprint, pp. 1-20, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Junling Liu et al., “Is ChatGPT a Good Recommender? A Preliminary Study,” arXiv Preprint, pp. 1-10, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Fei Sun et al., “BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer,” arXiv Preprint, pp. 1-10, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Gordon V. Cormack, Charles L.A. Clarke, and Stefan Buettcher, “Reciprocal Rank Fusion Outperforms Condorcet and Individual Rank Learning Methods,” Proceedings of the 32^nd International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, New York, NY, United States, pp. 758-759, 2009.
[CrossRef] [Google Scholar] [Publisher Link] 

[24] Christopher J. Burges, Robert Ragno, and Quoc V. Le “Learning to Rank with Nonsmooth Cost Functions,” Advances in Neural Information Processing Systems, vol. 19, pp. 1-8, 2006.
[Google Scholar] [Publisher Link]

[25] Eugene Ie et al., “RecSim: A Configurable Simulation Platform for Recommender Systems,” arXiv Preprint, pp. 1-23, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Victor Sanh et al., “DistilBERT, a Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter,” arXiv Preprint, pp. 1-5, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Jianguo Wang et al., “Milvus: A Purpose-Built Vector Data Management System,” Proceedings of the 2021 International Conference on Management of Data, Association for Computing Machinery, New York, NY, United States, pp. 2614-2627, 2021.
[CrossRef] [Google Scholar] [Publisher Link]