LLMOps 是大型语言模型操作（Large Language Model Operations）的简称。在目前对 LLM 应用程序堆栈的看法中，它与日志记录相关。使用大型语言模型构建应用的方法多样，包括从头训练模型、微调开源模型或使用托管的 API 等，而这里展示的堆栈基于上下文学习。此外，在质朴发言中，提到了开源和闭源商业模式之争，其中涉及到了 LLMOps，但未对其进行详细阐述。
这是我们目前对LLM应用程序堆栈的看法：以下是每个项目的链接列表，供快速参考：标题依次为："Data pipelines"-数据管道"Embedding model"-嵌入模型"Vector database"-向量数据库"Playground"-沙盒环境/测试环境"Orchestration"-编排"APIs/plugins"- API接口/插件"LLM cache"-大型语言模型缓存"Logging / LLMops"-日志记录/大型语言模型操作"Validation"-验证"App hosting"-应用托管"LLM APIs(proprietary)"-专有的大型语言模型API接口"LLM APIs(open)"-开放的大型语言模型API接口"Cloud providers"-云服务提供商"Opinionated clouds"-有特定策略或观点的云服务使用大型语言模型（LLM）构建应用的方法有很多，包括从头开始训练模型、微调开源模型或使用托管的API。我们在这里展示的堆栈是基于[上下文学习](https://en.wikipedia.org/wiki/In-context_learning_(natural_language_processing))的，这是我们看到的大多数开发人员开始使用的设计模式（只有在有基础模型的情况下才可能实现）。下一部分简要解释了这种模式；经验丰富的LLM开发者可以跳过这一部分。
RPA：机器人流程自动化，是使用软件机器人或AI来自动化重复的、基于规则的业务流程。RAG：检索增强生成（Retrieval Augmented Generation），通过在生成响应之前从知识源检索相关信息来增强LLM的能力，适合需要查询数据库、文档或其他结构化/非结构化数据存储库的应用程序。ERP：用于管理和整合公司的财务、供应链、运营、报告、制造以及人力资源活动的软件系统。AI Ops：面向开发者的，构建和部署AI应用所需的基础结构和工具
As we find more uses for AI,it will rewrite scientificfields and change the way we learn about our world.Deep learning AI could improve breast cancer screeningAI could transform how diseases are detected,prevented,and treated.Doctors aretesting if deep learning can be applied to breast cancer screening.Currently,everymammogram is double-checked by radiologists but this is labour-intensive andcauses diagnosis delays.A UK medical technology company is working with theSee,for example,What are Large Language Models used for?NVIDIA,2023.Black hole pictured for first time – in spectacular detail,Nature,2019.Accelerating the race against antibiotic resistance,Deepmind,2022.Stopping malaria in its tracks,Deepmind,2022.Creating plastic-eating enzymes that could save us from pollution,Deepmind,2022.A pro-innovation approach to AI regulationNHS to test AI for the second screening,meaning greater numbers of patientscould be screened faster and clinicians could spend more time with patients andprovide faster access totreatment.33Farming efficiency increased by AI robotsApplying robotics and AI to field management can make farming more efficient,sustainable and productive.Lightweight,autonomous mapping and monitoringrobots operating across the UK can spend hours on the field in all conditions andsignificantly reduce soil compaction.These systems can digitise the field,providingfarmers with data to improve weed and pest management.If these systemsbecome widely used,they could contribute to agricultural and horticulturalproductivity,reduce the pressure of labour shortages and better preserve the