Prompt Engineering for Generative AI (for True Epub) — 书籍拆解
读到哪:未读。
readState不是 read/partial 的书不能当锚。
| 项 | |
|---|---|
| 作者 | James Phoenix and Michael Taylor |
| 版次 | 2024 版 |
| 格式 | epub ｜ 文本源 epub-builtin |
| 许可 | 自购/个人收藏 |
| 来源 | 主人个人藏书,2026-08 放入收件箱 |
| 清洗 | 删页眉页脚 0 行、页码 0 行、断词接回 0 处 |
我们重写的拆解(0 章)
（还没写。拆解是这本书对我们的真正产出——底下的元数据只是索引。）
为什么收它
「五条原则」这类可直接引用的判据,适合写进讲义当规矩。
合法性
自购/个人收藏。来源:主人个人藏书,2026-08 放入收件箱。原始文件不入库,转码文本入库(私有库)。
出版方怎么说
（起草参考,不是我们的判断。真正的「覆盖什么/不覆盖什么」写进 frontmatter 的 claims / notCovered)
出版方简介(仅供起草参考,不是我们的判断):Large language models (LLMs) and diffusion models such as ChatGPT and Stable Diffusion have unprecedented potential. With this book, you'll gain a solid foundation in generative AI, including how to apply these models in practice. When first integrating LLMs and diffusion models into their workflows
它覆盖什么、不覆盖什么
（还没读到能下判断的程度。claims / notCovered 空着就是空着,不猜。)
怎么引用它
(依据: book=prompt-engineering-generative-ai §Chapter 1. The Five Principles of Prompting)
章节名对不上会被 lab:validate 拦下;页码锚(§p.123)同样可用。
结构(67 段,共 695k 字符)
| 段 | 章节 | 页 | 规模 |
|---|---|---|---|
| 01 | Praise for Prompt Engineering for Generative AI | — | 2.8k |
| 02 | Prompt Engineering for Generative AI | — | 2.0k |
| 03 | Preface | — | 12.1k |
| 04 | Chapter 1. The Five Principles of Prompting | — | 62.6k |
| 05 | What Are Text Generation Models? | — | 27.6k |
| 06 | Generating Lists | — | 14.8k |
| 07 | YAML | — | 8.5k |
| 08 | Mock CSV Data | — | 22.1k |
| 09 | Benefits of Chunking Text | — | 0.8k |
| 10 | Scenarios for Chunking Text | — | 1.0k |
| 11 | Poor Chunking Example | — | 14.4k |
| 12 | Understanding the Tokenization of Strings | — | 8.7k |
| 13 | Techniques for Improving Sentiment Analysis | — | 1.1k |
| 14 | Limitations and Challenges in Sentiment Analysis | — | 1.4k |
| 15 | Planning the Architecture | — | 1.0k |
| 16 | Coding Individual Functions | — | 1.0k |
| 17 | Adding Tests | — | 1.1k |
| 18 | Benefits of the Least to Most Technique | — | 1.1k |
| 19 | Challenges with the Least to Most Technique | — | 5.7k |
| 20 | Avoiding Hallucinations with Reference | — | 3.4k |
| 21 | Give GPTs “Thinking Time” | — | 1.7k |
| 22 | The Inner Monologue Tactic | — | 3.0k |
| 23 | Self-Eval LLM Responses | — | 21.7k |
| 24 | Introduction to LangChain | — | 2.4k |
| 25 | Environment Setup | — | 50.7k |
| 26 | Fixed-Length Few-Shot Examples | — | 0.7k |
| 27 | Formatting the Examples | — | 1.8k |
| 28 | Selecting Few-Shot Examples by Length | — | 26.2k |
| 29 | Sequential Chain | — | 2.0k |
| 30 | itemgetter and Dictionary Key Extraction | — | 9.3k |
| 31 | Structuring LCEL Chains | — | 1.7k |
| 32 | Document Chains | — | 3.9k |
| 33 | Stuff | — | 0.3k |
| 34 | Refine | — | 0.4k |
| 35 | Map Reduce | — | 0.6k |
| 36 | Map Re-rank | — | 2.7k |
| 37 | Chapter 5. Vector Databases with FAISS and Pinecone | — | 73.5k |
| 38 | Chapter 6. Autonomous Agents with Memory and Tools | — | 8.7k |
| 39 | Reason and Act (ReAct) | — | 4.1k |
| 40 | Reason and Act Implementation | — | 11.0k |
| 41 | Using Tools | — | 11.5k |
| 42 | ReAct | — | 1.0k |
| 43 | Use Cases for ReAct | — | 11.0k |
| 44 | Long-Term Memory | — | 1.3k |
| 45 | Short-Term Memory | — | 0.9k |
| 46 | Short-Term Memory in QA Conversation Agents | — | 1.9k |
| 47 | Preserving the State | — | 1.1k |
| 48 | Querying the State | — | 0.6k |
| 49 | ConversationBufferMemory | — | 5.2k |
| 50 | ConversationBufferWindowMemory | — | 0.6k |
| 51 | ConversationSummaryMemory | — | 0.8k |
| 52 | ConversationSummaryBufferMemory | — | 0.8k |
| 53 | ConversationTokenBufferMemory | — | 5.3k |
| 54 | Plan-and-Execute Agents | — | 1.6k |
| 55 | Tree of Thoughts | — | 4.9k |
| 56 | Global (Constructor) Callbacks | — | 0.9k |
| 57 | Request-Specific Callbacks | — | 0.6k |
| 58 | The Verbose Argument | — | 0.3k |
| 59 | When to Use Which? | — | 0.6k |
| 60 | Token Counting with LangChain | — | 3.5k |
| 61 | OpenAI DALL-E | — | 19.5k |
| 62 | Chapter 8. Standard Practices for Image Generation with Midjourney | — | 39.1k |
| 63 | Chapter 9. Advanced Techniques for Image Generation with Stable Diffusion | — | 69.4k |
| 64 | Chapter 10. Building AI-Powered Applications | — | 40.3k |
| 65 | Index | — | 50.3k |
| 66 | About the Authors | — | 0.7k |
| 67 | Colophon | — | 1.7k |
我们自己的读书笔记(0 篇)
（还没有。读完某章后写进 docs/prompt-engineering-generative-ai/notes/,那才是这本书对我们的产出。）
本页由 node scripts/book-build.mjs 生成:表格来自转码结果,散文来自书卡正文。不要手改本页。