Designing End-to-End Retrieval-Augmented Generation(RAG) Workflows for Knowledge-Intensive Applications
DOI:
https://doi.org/10.15662/IJEETR.2025.0705009Keywords:
Retrieval-Augmented Generation, Knowledge-Intensive Applications, Framework, Information Retrieval, Natural Language Generation, AI Workflows, Knowledge IntegrationAbstract
Creating effective workflow processes on Knowledge-Intensive Applications (KIAs) is now critical towards the utilization of the full potential of retrieval-augmented generation (RAG) models. The study provides a detailed model of the end-to-end RAG processes development and use and aims to optimize the communication between the retrieval and the generation processes to improve the efficiency of the knowledge integration during the complex tasks. The suggested framework focuses on modularity and scalability which allows it to be easily integrated with different sources of knowledge, including document corpora and databases. The workflow will be developed to support the efficient retrieval of information with the help of advanced indexing and ranking methods and then generate high-quality responses using the pre-trained language models. An important feature of the design is the feedback loop between retrieval and generation that is iterative in nature and which makes the model adapt and improve with time. Other issues and prospects of life cycle RAG systems in different applications examined in this paper include the automated customer support, decision-making tools, and research assistants. The comparison of the framework shows that there are overwhelming improvements in accuracy of tasks, relevancy of responses, and the overall performance of the system in comparison to the traditional models. The findings offer practical findings to be considered in the future development of knowledge-oriented AI programs, where it is important to foster knowledge retrieval and content generation.
References
1. Abrahamyan, D., Fard, F.H.: StackRAG agent: improving developer answers with retrieval-augmented generation. In: 2024 IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 893–897. IEEE Computer Society, Los Alamitos (2024). DOI: 10.1109/ICSME58944.2024.00098
2. Chintalapudi, S. (2025). From backend to business: Fullstack architectures for self-serve RAG and LLM workflows. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 8(3), 12121–12132.
3. Ahmed, M., et al.: Codeqa: advanced programming question-answering using llm agent and rag. In: 2024 6th Novel Intelligent and Leading Emerging Sciences Conference (NILES), pp. 494–499 (2024). DOI: 10.1109/NILES63360.2024.10753267
4. Alam, H.M.T., Srivastav, D., Kadir, M.A., Sonntag, D.: Towards interpretable radiology report generation via concept bottlenecks using a multi-agentic rag (2025). arXiv:2412.16086
5. Barnett, S., Kurniawan, S., Thudumu, S., Brannelly, Z., Abdelrazek, M.: Seven failure points when engineering a retrieval-augmented generation system. In: Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN ’24, pp. 194–199. Association for Computing Machinery, New York (2024). DOI: 10.1145/3644815.3644945
6. Chen, J., Xu, D., Fei, J., Feng, C.M., Elhoseiny, M.: Document haystacks: vision-language reasoning over piles of 1000+ documents (2024). arXiv:2411.16740
7. Chirkova, N., Rau, D., Déjean, H., Formal, T., Clinchant, S., Nikoulina, V.: Retrieval-augmented generation in multilingual settings. In: Li, S., et al. (eds.) Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024), pp. 177–188. Association for Computational Linguistics, Bangkok (2024). DOI: 10.18653/v1/2024.knowllm-1.15
8. Fan, W., et al.: A survey on rag meeting llms: towards retrieval-augmented large language models. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’24, pp. 6491–6501. Association for Computing Machinery, New York (2024). DOI: 10.1145/3637528.3671470
9. Gamage, G., et al.: Multi-agent rag chatbot architecture for decision support in net-zero emission energy systems. In: 2024 IEEE International Conference on Industrial Technology (ICIT), pp. 1–6 (2024). DOI: 10.1109/ICIT58233.2024.10540920
10. Guo, Z., Xia, L., Yu, Y., Ao, T., Huang, C.: Lightrag: simple and fast retrieval-augmented generation (2024). arXiv:2410.05779
11. Gupta, S., Ranjan, R., Singh, S.N.: A comprehensive survey of retrieval-augmented generation (rag): evolution, current landscape and future directions (2024). arXiv:2410.12837
12. Jang, J., Li, W.S.: Au-rag: agent-based universal retrieval augmented generation. In: Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, SIGIR-AP 2024, pp. 2–11. Association for Computing Machinery, New York (2024). DOI: 10.1145/3673791.3698416
