Design and Implementation of a Regional Culinary Community Platform with AI-Assisted Question Answering: A Case Study of Xunwei Zhanjiang
DOI:
https://doi.org/10.64549/jaai-ii.v1i2.124Keywords:
Regional culinary culture, Community platform, Web application, Conversational AI, System designAbstract
Digital platforms for regional culinary culture need to connect information about local dishes and places with community participation and accessible exploration services. This study presents the design and implementation of Xunwei Zhanjiang, a community-oriented web platform that integrates regional food discovery, user interaction, and AI-assisted culinary enquiry. Built with Next.js, React, Drizzle ORM, and MySQL, the platform organizes culinary information through district-based displays and structured food cards, alongside community features for sharing posts, commenting, bookmarking, and following users. A server-side integration with Dify enables natural-language enquiries about local cuisine and suggested food itineraries. The system incorporates standardized API responses, input validation, cookie-based authentication, and database uniqueness constraints to support consistent interactions and prevent duplicate social relationships. Preliminary functional checks confirmed successful operation of selected content retrieval endpoints, user login and profile retrieval, access restrictions, and the integrated AI enquiry interface. These observations support the feasibility of bringing structured culinary content, community interaction, and conversational assistance together within a regional web application. However, they do not establish improvements in recommendation quality, cultural engagement, or performance at scale. Further work will address implementation gaps and evaluate response quality, system performance, and usability through systematic testing and user studies.
References
Agrawal, A., Kedia, N., Panwar, A., Mohan, J., Kwatra, N., Gulavani, B., Tumanov, A. and Ramjee, R., 2024. Taming throughput-latency tradeoff in LLM inference with Sarathi-Serve. In: 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pp.117–134. Available at: https://www.usenix.org/conference/osdi24/presentation/agrawal.
Asai, A., Wu, Z., Wang, Y., Sil, A. and Hajishirzi, H., 2024. Self-RAG: Learning to retrieve, generate, and critique through self-reflection. In: The Twelfth International Conference on Learning Representations. Available at: https://openreview.net/forum?id=hSyW5go0v8.
Es, S., James, J., Espinosa Anke, L. and Schockaert, S., 2024. RAGAs: Automated evaluation of retrieval augmented generation. In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pp.150–158. doi: 10.18653/v1/2024.eacl-demo.16.
Guo, Z., Xia, L., Yu, Y., Ao, T. and Huang, C., 2025. LightRAG: Simple and fast retrieval-augmented generation. In: Findings of the Association for Computational Linguistics: EMNLP 2025, pp.10746–10761. doi: 10.18653/v1/2025.findings-emnlp.568.
Horng, J.S. and Tsai, C.T., 2010. Government websites for promoting East Asian culinary tourism: A cross-national analysis. Tourism Management, 31(1), pp.74–85. doi: 10.1016/j.tourman.2009.01.009.
Jannach, D., 2023. Evaluating conversational recommender systems: A landscape of research. Artificial Intelligence Review, 56, pp.2365–2400. doi: 10.1007/s10462-022-10229-x.
Jannach, D., Manzoor, A., Cai, W. and Chen, L., 2021. A survey on conversational recommender systems. ACM Computing Surveys, 54(5), Art. no. 105, pp.1–36. doi: 10.1145/3453154.
Lewis, P. et al., 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Advances in Neural Information Processing Systems, 33, pp.9459–9474.
Liu, N.F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F. and Liang, P., 2024. Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics, 12, pp.157–173. doi: 10.1162/tacl_a_00638.
Wang, X. et al., 2024. Searching for best practices in retrieval-augmented generation. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp.17716–17736. doi: 10.18653/v1/2024.emnlp-main.981.
Xiang, Z. and Gretzel, U., 2010. Role of social media in online travel information search. Tourism Management, 31(2), pp.179–188. doi: 10.1016/j.tourman.2009.02.016.
Zhan, Q., Liang, Z., Ying, Z. and Kang, D., 2024. InjecAgent: Benchmarking indirect prompt injections in tool-integrated large language model agents. In: Findings of the Association for Computational Linguistics: ACL 2024, pp.10471–10506. doi: 10.18653/v1/2024.findings-acl.624.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 YiZhi Cai
This work is licensed under a Creative Commons Attribution 4.0 International License.
CC Attribution 4.0