The semantic capabilities of large language models (LLMs) have the potential to enable rich analytics and reasoning over vast knowledge corpora. Unfortunately, existing systems either empirically optimize expensive LLM-powered operations with no performance guarantees, or serve a limited set of row-wise LLM operations, providing limited robustness, expressiveness and usability. We introduce semantic operators, the first formalism for declarative and general-purpose AI-based transformations based on natural language specifications (e.g., filtering, sorting, joining or aggregating records using natural language criteria). Each operator opens a rich space for execution plans, similar to relational operators. Our model specifies the expected behavior of each operator with a high-quality gold algorithm, and we develop an optimization framework that reduces cost, while providing accuracy guarantees with respect to a gold algorithm. Using this approach, we propose several novel optimizations to accelerate semantic filtering, joining, group-by and top-k operations by up to $1,000\times$. We implement semantic operators in the LOTUS system and demonstrate LOTUS' effectiveness on real, bulk-semantic processing applications, including fact-checking, biomedical multi-label classification, search, and topic analysis. We show that the semantic operator model is expressive, capturing state-of-the-art AI pipelines in a few operator calls, and making it easy to express new pipelines that match or exceed quality of recent LLM-based analytic systems by up to $170\%$, while offering accuracy guarantees. Overall, LOTUS programs match or exceed the accuracy of state-of-the-art AI pipelines for each task while running up to $3.6\times$ faster than the highest-quality baselines. LOTUS is publicly available at https://github.com/lotus-data/lotus.

翻译：大型语言模型（LLM）的语义能力具有对海量知识库进行丰富分析与推理的潜力。然而，现有系统要么通过经验性方法优化昂贵的LLM操作而缺乏性能保证，要么仅支持有限的行级LLM操作，导致其鲁棒性、表达能力和可用性受限。本文提出语义算子——首个基于自然语言规范（例如：使用自然语言条件进行记录筛选、排序、连接或聚合）的声明式通用AI转换形式化模型。每个算子如同关系型算子般开辟了丰富的执行计划空间。我们的模型通过高质量黄金算法规范每个算子的预期行为，并开发了在保证黄金算法精度的同时降低成本的优化框架。基于该方法，我们提出了多项创新优化技术，将语义筛选、连接、分组和Top-k操作的执行速度提升高达$1,000$倍。我们在LOTUS系统中实现了语义算子，并在实际批量语义处理应用中验证了LOTUS的有效性，包括事实核查、生物医学多标签分类、搜索和主题分析。实验表明，语义算子模型具有强大的表达能力，仅需少量算子调用即可实现最先进的AI流程，并能轻松构建质量超越近期基于LLM的分析系统达$170\%$的新流程，同时提供精度保证。总体而言，LOTUS程序在各任务中达到或超越了最先进AI流程的精度，且运行速度比最高质量基线快达$3.6$倍。LOTUS已在https://github.com/lotus-data/lotus开源发布。