This book teaches readers how to design, build, and scale reliable applications and autonomous AI agents powered by large language models (LLMs). It covers understanding LLM capabilities, architectural patterns like engines and chatbots, and essential techniques such as prompt engineering and Retrieval-Augmented Generation (RAG). The content guides users through utilizing frameworks like LangChain to create real-world systems capable of handling complex natural language tasks and orchestrating multi-step workflows.
This page is free — overview and chapter list only.
The complete book body is sold separately.
Full book: $2.99 USDC via x402 ·
Per chapter: $0.25 USDC
Buy / open complete book (HTML)
· Complete book Markdown (.md)
Agents: start with free /library/discovery.json, sample free teaser chapters,
then pay for individual chapters or the complete book URL above.
Append .md to any content URL for Markdown with YAML front matter.
Chapters
- About The Cover Illustration (Free teaser)
- Part 1 ($0.25)
- 13 Typical Llm Use Cases ($0.25)
- 24 Prompt Types ($0.25)
- 25 Reasoning In Detail ($0.25)
- 26 Prompt Structure ($0.25)
- Summary ($0.25)
- This Chapter Covers ($0.25)
- 31 Summarizing A Document Bigger Than The Context Window ($0.25)
- 313 Map ($0.25)
- 316 Mapreduce Execution ($0.25)
- 324 Creating The Document List ($0.25)
- 33 Summarization Flowchart ($0.25)
- Summary 2 ($0.25)
- This Chapter Covers 2 ($0.25)
- 41 Overview Of A Research Summarization Engine ($0.25)
- 431 Implementing Web Searching ($0.25)
- 452 Crafting Summarization Prompts ($0.25)
- 46 Initial Implementation ($0.25)
- 47 Reimplementing The Research Summary Engine In Lcel ($0.25)
- Langchain Expression Language Lcel ($0.25)
- 474 Web Research Chain ($0.25)
- 512 Agents ($0.25)
- 542 State Management And Typing ($0.25)
- 553 Step By Step Transformation Process ($0.25)
- 554 Code Comparison And Benefits Realized ($0.25)
- 611 A Basic Qa Chatbot Over A Single Document ($0.25)
- 613 The Rag Design Pattern ($0.25)
- 621 Whats A Vector Store ($0.25)
- 622 How Do Vector Stores Work ($0.25)
- 624 Most Popular Vector Stores ($0.25)
- Setting Up Chromadb Collections ($0.25)
- Splitting Content Into Granular Chunks Using Htmlsectionspli ($0.25)
- Searching Granular Chunks ($0.25)
- Comparing With Direct Semantic Search On Child Chunks ($0.25)
- Performing A Search On Granular Information ($0.25)
- Listing 86 Setting Up The Multivectorretriever ($0.25)
- Ingesting Content With Metadata ($0.25)
- 107 Retrieval Postprocessing ($0.25)
- 1112 Loading Environment Variables ($0.25)
- 115 Running The Agent Chatbot The Read Eval Print Loop ($0.25)
- Updating The Agentstate ($0.25)
- 121 Building An Accommodation Booking Agent ($0.25)
- 1211 Hotel Booking Tool ($0.25)
- 122 Building A Router Based Travel Assistant ($0.25)
- 123 Handling Multi Agent Requests With A Supervisor Componen ($0.25)
- Summary 3 ($0.25)
- This Chapter Covers 3 ($0.25)
- 131 Introduction To Mcp Servers ($0.25)
- 1312 The Solution The Model Context Protocol ($0.25)
- 1321 Essential Resources For Mcp Server Development ($0.25)
- 133 Building A Weather Mcp Server ($0.25)
- 134 Integrating The Weather Mcp Tool Into An Agent ($0.25)
- Summary 4 ($0.25)
- This Chapter Covers 4 ($0.25)
- 141 Memory ($0.25)
- 1421 Implementing Guardrails To Reject Nontravel Related Que ($0.25)
- Updating The Router Graph ($0.25)
- 1431 Long Term User And Application Memory ($0.25)
- 1434 Evaluation Of Ai Agents And Applications ($0.25)
- C11 Openai Gpt Series ($0.25)
- C14 Claude ($0.25)
- C18 Mistral ($0.25)
- C21 Model Purpose ($0.25)
- C28 Task Suitability Standard Benchmarks ($0.25)
- C29 Safety And Bias ($0.25)
- C210 A Practical Example ($0.25)
- D1 Installing Sqlite ($0.25)
- E11 Transparency ($0.25)
- E31 Limitations Of Consumer Hardware ($0.25)
- E32 Quantization ($0.25)
- Asynciorunchat Langchain Integration ($0.25)
- E5 Inference Via The Hugging Face Transformers Library ($0.25)
- Related Manning Titles ($0.25)
- React Pattern ($0.25)