دانلود کتاب الگوهای طراحی هوش مصنوعی مولد

If you’re an AI engineer building generative AI (GenAI) applications, you’ve likely experienced the frustrating gap between the ease of creating impressive prototypes and the complexity of deploying them reliably in production. While foundational models make it easy to build compelling demos, production systems demand solutions to fundamental challenges: hallucinations that compromise accuracy, inconsistent outputs that break downstream processes, knowledge gaps that limit enterprise applicability, and reliability issues that make systems unsuitable for critical applications. This book bridges that gap by providing 32 battle-tested design patterns that address the recurring problems you’ll encounter when building productiongrade GenAI applications. These patterns aren’t theoretical constructs— they codify proven solutions that are often derived from cutting-edge research and refined by practitioners who have successfully deployed GenAI systems at scale. Supervised machine learning (ML) involves training a problem-specific model on a large training dataset of example inputs and outputs—but GenAI applications rarely include a training phase. Instead, they commonly use general-purpose foundational models. This book is focused on design patterns for AI applications that are built on top of foundational models, such as Open AI’s GPT, Anthropic’s Claude, Google’s Gemini, or Meta’s Llama. In this book, we cover the entire AI engineering workflow. After an introduction in Chapter 1, Chapter 2 provides practical patterns for controlling content style and format (including Logits Masking [Pattern 1] and Grammar [Pattern 2]). Chapter 3 and Chapter 4 cover integrating external knowledge through sophisticated retrieval-augmented generation (RAG) implementations, from Basic RAG (Pattern 6) to Deep Search (Pattern 12). Chapter 5 is about enhancing your model’s reasoning capabilities with patterns like Chain of Thought (Pattern 13), Tree of Thoughts (Pattern 14), and Adapter Tuning (Pattern 15). Chapter 6 emphasizes building reliable systems with LLM-as-Judge (Pattern 17), Reflection (Pattern 18), and Prompt Optimization (Pattern 20) patterns. Chapter 7 is about creating agentic systems, including Tool Calling (Pattern 21) and Multiagent Collaboration (Pattern 23). Chapter 8 covers optimizing deployment (including Small Language Model [Pattern 24] and Inference Distribution Testing [Pattern 27]), and Chapter 9 discusses implementing safety guardrails, including Self-Check (Pattern 31) and comprehensive Guardrails (Pattern 32).