
打开任何在生产中真正保持稳定的LLM应用程序的源码,你会发现那个令人印象深刻的提示词只是其中最小的部分。提示词周围的是工程:约束输出的模式,为未知事实咨询的索引,执行操作的工具,以及在发布前捕获回归的评估。这些外围代码——而不是巧妙的咒语——将一次好的回答转化为你可以信赖的系统。 本课程将那些外围代码教为一组持久的原语。API表面作为稳定契约,在每几个月轮换的模型名称下:消息、结构化输出、流式处理、提示缓存以及伴随而来的令牌和延迟计算。嵌入、ANN索引、混合检索和交叉编码器重排序作为将模型锚定到你自己数据的标准方式,并将分块和摄入视为一等工程而非笔记本黑客技巧。函数调用、代理循环、幂等工具效果以及模型上下文协议作为让模型在真实系统上行动的标准方式,包括能力范围和需要可逆性时的人机循环。以及工程循环——黄金数据集、带有已知偏见的LLM-as-a-judge、RAG评估三元组、追踪和致命三连防御——将“它曾经工作过”转化为你可以信任的证据。 你将完成五个实战构建:带引用的文档问答、大规模结构化提取、带只读工具的内部助手、带变动工具的客户操作代理以及多步骤研究代理。通过三十九节课,你建立它们底层的习惯:给定用例,选择正确的原语,组合它们,评估它们,发布。
Leena Shah’s portfolio reads less like a catalog of models than a record of bottlenecks removed: customer-support teams searching thousands of documents, analysts waiting on manual summaries, and product managers unsure whether an AI answer can be trusted. She has addressed those problems with retrieval-augmented assistants, multimodal extraction, voice agents, and tool-using workflows, pairing Python and FastAPI services with vector databases, cloud infrastructure, and evaluation suites that measure grounding, latency, safety, and cost. Leena has also fine-tuned open models for private environments, introduced human-review loops and production guardrails, and worked alongside product, security, and domain specialists to turn rough prototypes into monitored features. Her strength lies in recognizing where AI can genuinely improve a workflow—and engineering the surrounding system so that improvement survives contact with real users.
Too basic.
太好了,简单明了!
love it
super useful