五类真实场景的RAG系统实践，验证了多语言、可解释性设计的有效性。
Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation
- 融合OCR与向量检索，用领域适配大模型增强知识调用
- 100人测试显示系统在准确性与易用性上表现良好
- 总结12条实操教训，适合部署RAG的团队参考
检索增强生成（RAG）系统正成为将大语言模型（LLM）与外部知识结合的关键方法，以解决事实准确性和上下文相关性问题。然而，缺乏基于真实应用场景、由普通用户参与评估并系统记录经验教训的实证研究。本文展示了五个面向治理、网络安全、农业、工业研究和医疗诊断领域的具体RAG应用。每个系统均集成多语言OCR、基于向量嵌入的语义检索以及领域适配的LLM，通过本地服务器或云API部署以满足不同用户需求。一项基于网络的评估共涉及100名参与者，从六个维度（易用性、相关性、透明度、响应速度、准确性、推荐意愿）对系统进行评价。结合用户反馈与开发经验，我们总结出十二条关键经验，揭示了影响RAG系统可靠性与可用性的技术、运营与伦理挑战。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems are emerging as a key approach for grounding Large Language Models (LLMs) in external knowledge, addressing limitations in factual accuracy and contextual relevance. However, there is a lack of empirical studies that report on the development of RAG-based implementations grounded in real-world use cases, evaluated through general user involvement, and accompanied by systematic documentation of lessons learned. This paper presents five domain-specific RAG applications developed for real-world scenarios across governance, cybersecurity, agriculture, industrial research, and medical diagnostics. Each system incorporates multilingual OCR, semantic retrieval via vector embeddings, and domain-adapted LLMs, deployed through local servers or cloud APIs to meet distinct user needs. A web-based evaluation involving a total of 100 participants assessed the systems across six dimensions: (i) Ease of Use, (ii) Relevance, (iii) Transparency, (iv) Responsiveness, (v) Accuracy, and (vi) Likelihood of Recommendation. Based on user feedback and our development experience, we documented twelve key lessons learned, highlighting technical, operational, and ethical challenges affecting the reliability and usability of RAG systems in practice.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。