面向开发者的大型语言模型入门
本课程是安德鲁· Ng 与 OpenAI 联合推出的三门大型语言模型系列课程的中文改编版本。课程涵盖提示工程、使用 ChatGPT API 构建系统、LangChain 应用开发，以及利用 LangChain 访问私有数据。课程为如何利用大语言模型的能力构建具备摘要、推理、转换、扩展和聊天功能的应用程序，提供了清晰且易于理解的入门指导。
课程概述
📚 内容概要
本课程是吴恩达（Andrew Ng）与 OpenAI 联合开发的三部分大型语言模型（LLM）系列课程的中文版。课程涵盖提示工程、基于 ChatGPT API 构建系统、LangChain 应用开发，以及利用 LangChain 访问私有数据等内容。课程深入浅出地介绍了如何利用大模型能力，开发具备摘要、推理、转换、扩展和聊天功能的应用程序。
掌握提示工程与 LangChain 框架，成为大模型时代的 AI 应用开发者。
🎯 学习目标
- 区分基础大模型（Base LLMs）与指令微调大模型（Instruction Tuned LLMs）。
- 运用四种具体策略编写清晰且明确的指令（使用分隔符、结构化输出、条件检查、少样本提示）。
- 通过指定任务步骤并要求独立解决问题，实现让模型“有时间思考”的策略。
- 实现结构化文本处理：从单个或多个文档中总结并提取特定信息，同时控制输出长度与重点。
- 执行自动化文本分析：通过提示实现情感分类、识别特定情绪，并完成零样本主题分类。
- 实现多模态转换：在不同语言间翻译、转换数据格式（如 JSON 到 HTML），并程序化修正语法与拼写错误。
- 区分基础大模型与指令微调大模型，理解分词对模型行为的影响。
- 使用 System、User 和 Assistant 消息角色构建结构化系统架构，定义模型人格。
- 应用分类与内容审核技术，评估用户输入的安全性并进行路由处理。
- 实现提示链（Prompt Chaining）：将复杂任务分解为可管理的子任务，以提升可靠性并降低成本。
课程 共 8 课时 · 预计 24.0h
课程
Lesson
This lesson introduces the shift from base LLMs to instruction-tuned models, emphasizing the importance of clear, specific prompting and iterative refinement to achieve reliable results. Developers will learn to treat models as literal assistants by using techniques like delimiters, chain-of-thought reasoning, and structured output to improve accuracy and minimize hallucinations.
This lesson introduces the five core prompting primitives—summarizing, inferring, transforming, expanding, and chatbots—that enable developers to build structured AI-driven workflows. You will learn how to manage LLM state, use delimiters for precision, and choose the right techniques to extract data or analyze sentiment effectively.
This lesson explores how LLMs process information through numerical tokens rather than individual characters, explaining why techniques like hyphenation are necessary for tasks requiring granular detail. It also distinguishes between base models, which focus on pattern prediction, and instruction-tuned models, which are optimized through human feedback to act as reliable assistants.
This lesson introduces prompt chaining and task decomposition as superior alternatives to complex, single-prompt workflows. You will learn how to build modular, cost-effective pipelines that improve reliability and debuggability by integrating dynamic data retrieval, safety moderation, and step-by-step logic.
This lesson introduces LangChain as a modular framework for managing LLM interactions, highlighting how abstractions like ChatOpenAI and ChatPromptTemplate help developers overcome the stateless nature of models. You will learn to manage conversation history, configure temperature for deterministic or creative outputs, and use templates to separate logic from content for scalable application development.
This lesson introduces LangChain orchestration, teaching you how to move beyond single prompts by linking components into sequential pipelines and logic-driven router chains. You will learn to build scalable AI applications by mastering modular workflows that connect models, prompts, and external data to handle complex, multi-step tasks.
This lesson explores the Retrieval-Augmented Generation (RAG) pipeline, focusing on how to ingest, split, and vectorize private data to provide LLMs with relevant, up-to-date context. You will learn to use document loaders to standardize various file formats into structured objects and apply effective chunking strategies to ensure semantic meaning is preserved for accurate retrieval.
This lesson explores advanced Retrieval-Augmented Generation (RAG) techniques designed to overcome the limitations of basic semantic search, such as redundancy and context window constraints. You will learn how to implement tools like Maximum Marginal Relevance (MMR), self-querying, and contextual compression to provide the LLM with a more diverse, filtered, and efficient knowledge base.