{"product_id":"154434","title":"LLM Design Patterns ","description":"\u003ccenter\u003e\u003cdiv style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/tmgdisk01.cafe24.com\/images\/vs\/4172\/sv\/3jYDPLS5SlhHkPKfj1lJ1hZNsHWJ9S.png?v=1765080100\" style=\"max-width:100%;max-height:10px\"\u003e\u003c\/div\u003e\u003c\/center\u003e\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\u003ccenter\u003e\n\n\u003cdiv style=\"width:95%\"\u003e\n\n\u003cdiv style=\"text-align:center;font-size:30px;font-weight:bolder;line-height:1.6em\"\u003e LLM Design Patterns \u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"border-bottom:1px;border-bottom-style:dotted;border-color:;padding-bottom:20px\"\u003e\u003ccenter\u003e\u003ctable align=\"center\" width=\"100%\"\u003e\u003ctbody style=\"border:0px\"\u003e\n\n\u003ctr\u003e\u003ctd align=\"center\" style=\"line-height:1.2em;text-align:center;font-size:18px;color:black;font-weight:bold;padding-bottom:20px;\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\n\n\u003ctr\u003e\u003ctd style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/image.yes24.com\/goods\/166382462\/XL\" style=\"max-width:100%;height:auto\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\n\n\n\u003c\/tbody\u003e\u003c\/table\u003e\u003c\/center\u003e\u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"width:95%;{split_style6}padding-top:20px;padding-bottom:20px\"\u003e\n\n\u003cdiv style=\"text-align:left;font-size:16px;font-weight:bold;padding-bottom:20px\"\u003e Description \u003c\/div\u003e\n\n\u003cdiv style=\"text-align:left;word-break:break-all;font-size:14px;line-height:1.6em;\"\u003e\n\n\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eBook Introduction\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e\u003cdiv\u003e LLM Design Patterns is a practical guide for AI professionals, helping them leverage the power of design patterns to develop robust, scalable, and efficient large-scale language models (LLMs).\u003cbr\u003e Written by a world-renowned AI expert and bestselling author who leads standards and innovation in generative AI, security, and strategy, this book covers the entire LLM development lifecycle, presenting reusable architectures and engineering solutions for challenges encountered during data processing, model training, evaluation, and deployment.\u003cbr\u003e \u003cbr\u003eIt covers everything from cleaning, augmenting, and annotating large-scale datasets to designing modular training pipelines, hyperparameter tuning, pruning, and model optimization through quantization.\u003cbr\u003e Each chapter also explores advanced prompting techniques such as regularization, checkpointing, fine-tuning, and ReAct (reason and execution), and introduces how to implement reflection-based reasoning, multi-step reasoning, and tool utilization.\u003cbr\u003e In addition, it focuses on search augmented generation (RAG), graph-based search, interpretability, fairness, and human feedback reinforcement learning (RLHF), ultimately leading to the construction of an agentic LLM system.\u003cbr\u003e\u003cbr\u003e By the end of this book, readers will have the knowledge and tools to design and build next-generation LLMs that are adaptable, effective, secure, and aligned with human values.\u003cbr\u003e\n\u003c\/div\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cul\u003e\u003cli\u003e You can preview some of the book's contents.\u003cbr\u003e \u003cspan\u003ePreview\u003c\/span\u003e\n\n\u003c\/li\u003e\u003c\/ul\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eindex\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e  \u003cdiv\u003e[Part 1] Introduction and Data Preparation\u003cbr\u003e\u003cbr\u003e ▣ Chapter 1: Introduction to LLM Design Patterns\u003cbr\u003e 1.1 Understanding LLM\u003cbr\u003e __1.1.1 Evolution of Language Models\u003cbr\u003e __1.1.2 Core Features of LLM\u003cbr\u003e 1.2 Understanding Design Patterns\u003cbr\u003e __1.2.1 Origin and Evolution\u003cbr\u003e __1.2.2 Core principles of design patterns\u003cbr\u003e 1.3 Design Patterns for LLM Development\u003cbr\u003e __1.3.1 Benefits of the LLM Design Pattern\u003cbr\u003e __1.3.2 Challenges in Applying Design Patterns to LLM\u003cbr\u003e 1.4 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 2: LLM Training Data Cleaning\u003cbr\u003e 2.1 The Importance of Data Cleaning\u003cbr\u003e 2.2 Data quality issues commonly encountered in language datasets\u003cbr\u003e 2.3 Text preprocessing techniques for LLM\u003cbr\u003e 2.4 Multilingual and mixed-sign data processing\u003cbr\u003e 2.5 Deduplication strategies for large-scale text corpora\u003cbr\u003e __2.5.1 Exact Match Duplicate Removal\u003cbr\u003e __2.5.2 Approximate Duplicate Detection\u003cbr\u003e __2.5.3 Single Ring\u003cbr\u003e __2.5.4 Locality-Sensitive Hashing (LSH)\u003cbr\u003e 2.6 Automating the Data Cleansing Pipeline\u003cbr\u003e 2.7 Data Verification and Quality Assurance\u003cbr\u003e 2.8 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 3: Data Augmentation\u003cbr\u003e 3.1 Text data augmentation techniques  \u003cbr\u003e__3.1.1 Synonym Replacement\u003cbr\u003e __3.1.2 Back translation\u003cbr\u003e __3.1.3 Text generation using T5\u003cbr\u003e 3.2 Data generation using existing LLM\u003cbr\u003e 3.3 Multilingual Data Augmentation Strategy\u003cbr\u003e __3.3.1 Back-translation between languages\u003cbr\u003e __3.3.2 Multilingual T5 Augmentation\u003cbr\u003e 3.4 Preserving meaning when augmenting text\u003cbr\u003e __3.4.1 Using sentence embeddings\u003cbr\u003e __3.4.2 Contextual word embeddings for synonym replacement\u003cbr\u003e 3.5 Balancing Augmentation and Data Quality\u003cbr\u003e __3.5.1 Quality Filtering\u003cbr\u003e __3.5.2 Human-in-the-Loop (HITL) Verification\u003cbr\u003e 3.6 Assessing the Impact of Data Augmentation\u003cbr\u003e __3.6.1 Embarrassment\u003cbr\u003e __3.6.2 Task-specific metrics\u003cbr\u003e __3.6.3 Diversity Indicators\u003cbr\u003e 3.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 4: Processing Large-Scale Datasets for LLM Training\u003cbr\u003e 4.1 Challenges of Large Datasets\u003cbr\u003e 4.2 Data Sampling Techniques\u003cbr\u003e 4.3 Distributed Data Processing\u003cbr\u003e 4.4 Data Sharding and Parallelization Strategies\u003cbr\u003e 4.5 Efficient data storage format\u003cbr\u003e 4.6 Streaming Data Processing for Continuous LLM Training\u003cbr\u003e 4.7 Memory-Efficient Data Loading Techniques\u003cbr\u003e 4.8 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 5: Data Version Management  \u003cbr\u003e5.1 Understanding the Need for Data Versioning\u003cbr\u003e 5.2 Data Versioning Strategies for Large-Scale Language Datasets\u003cbr\u003e 5.3 Tools for Data Version Management\u003cbr\u003e 5.4 Integrating Data Versioning into Your Training Workflow\u003cbr\u003e 5.5 Versioning Text Corpora\u003cbr\u003e 5.6 Dataset Transformation and Experiment Management\u003cbr\u003e 5.7 Best Practices for Data Versioning\u003cbr\u003e 5.8 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 6: Dataset Annotation and Labeling\u003cbr\u003e 6.1 The Importance of High-Quality Annotations\u003cbr\u003e 6.2 Various task-specific annotation strategies\u003cbr\u003e 6.3 Tools and Platforms for Large-Scale Text Annotation\u003cbr\u003e 6.4 Annotation Quality Control\u003cbr\u003e 6.5 Pros and Cons of Crowdsourcing Annotations\u003cbr\u003e 6.6 Semi-automatic annotation techniques\u003cbr\u003e 6.7 Annotation Techniques for Large-Scale Language Datasets\u003cbr\u003e 6.8 Annotation Bias and Mitigation Strategies\u003cbr\u003e 6.9 Summary\u003cbr\u003e\u003cbr\u003e [Part 2] Training and Optimizing Large-Scale Language Models\u003cbr\u003e\u003cbr\u003e ▣ Chapter 7: Training Pipeline\u003cbr\u003e 7.1 Components of the Training Pipeline\u003cbr\u003e 7.2 Data Entry and Preprocessing\u003cbr\u003e 7.3 LLM Architecture Design Considerations\u003cbr\u003e 7.4 Loss Functions and Optimization Strategies\u003cbr\u003e 7.5 Logging  \u003cbr\u003e7.6 Pipeline Modularity and Reusability\u003cbr\u003e 7.7 Extending the Training Pipeline for Larger Models\u003cbr\u003e 7.8 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 8: Hyperparameter Tuning\u003cbr\u003e 8.1 Understanding Hyperparameters\u003cbr\u003e 8.2 Manual and automatic tuning\u003cbr\u003e __8.2.1 Manual Tuning\u003cbr\u003e __8.2.2 Automatic tuning\u003cbr\u003e 8.3 Grid search and random search\u003cbr\u003e 8.4 Bayesian Optimization\u003cbr\u003e 8.5 Population-based methods\u003cbr\u003e 8.6 Multi-objective hyperparameter optimization\u003cbr\u003e 8.7 Challenges and Solutions for Large-Scale Hyperparameter Tuning\u003cbr\u003e 8.8 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 9: Normalization\u003cbr\u003e 9.1 L2 regularization (ridge regression)\u003cbr\u003e 9.2 Dropout\u003cbr\u003e 9.3 Layer-wise adaptive normalization\u003cbr\u003e 9.4 Gradient Clipping and Noise Injection\u003cbr\u003e 9.5 Regularization in Transfer Learning and Fine-Tuning Scenarios\u003cbr\u003e 9.6 New normalization techniques\u003cbr\u003e __9.6.1 Stochastic Weighted Averaging (SWA)\u003cbr\u003e __9.6.2 Sharpness-Aware Minimization (SAM)\u003cbr\u003e __9.6.3 Differential Privacy-Based Normalization\u003cbr\u003e __9.6.4 Fast Gradient Sign Method (FGSM)\u003cbr\u003e __9.6.5 Look-Ahead Optimizer\u003cbr\u003e 9.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 10: Checkpointing and Recovery  \u003cbr\u003e10.1 Why is checkpointing important?\u003cbr\u003e 10.2 Checkpoint Frequency and Storage Strategy\u003cbr\u003e 10.3 Efficient checkpoint storage method\u003cbr\u003e 10.4 Recovering from Failure\u003cbr\u003e 10.5 Checkpointing in Distributed LLM Training\u003cbr\u003e 10.6 Versioning of LLM Checkpoints\u003cbr\u003e 10.7 Automated Checkpointing and Recovery System\u003cbr\u003e 10.8 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 11: Fine Tuning\u003cbr\u003e 11.1 Implementing Transfer Learning and Fine-Tuning\u003cbr\u003e 11.2 Freezing and thawing strategies for layers\u003cbr\u003e 11.3 Learning rate scheduling\u003cbr\u003e 11.4 Domain-Specific Fine-Tuning Techniques\u003cbr\u003e 11.5 Few-Shot\/Zero-Shot Fine Tuning\u003cbr\u003e 11.6 Continuous Fine Tuning and Catastrophic Forgetting\u003cbr\u003e 11.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 12: Model Pruning\u003cbr\u003e 12.1 Size-based pruning\u003cbr\u003e 12.2 Structural and Unstructured Pruning\u003cbr\u003e 12.3 Iterative pruning technique\u003cbr\u003e 12.4 Pruning During and After Training\u003cbr\u003e 12.5 Balancing Pruning and Model Performance\u003cbr\u003e 12.6 Combining Pruning with Other Compression Techniques\u003cbr\u003e __12.6.1 Pruning and Quantization\u003cbr\u003e __12.6.2 Pruning and Knowledge Distillation\u003cbr\u003e 12.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 13: Quantization\u003cbr\u003e 13.1 Understanding Basic Concepts  \u003cbr\u003e__13.1.1 Post-Training Quantization (PTQ)\u003cbr\u003e 13.2 Mixed-precision quantization\u003cbr\u003e 13.3 Hardware Considerations\u003cbr\u003e 13.4 Comparison of Quantization Strategies\u003cbr\u003e 13.5 Combining Quantization with Other Optimization Techniques\u003cbr\u003e __13.5.1 Pruning and Quantization\u003cbr\u003e __13.5.2 Knowledge Distillation and Quantization\u003cbr\u003e 13.6 Summary\u003cbr\u003e\u003cbr\u003e [Part 3] Evaluation and Interpretation of Large-Scale Language Models\u003cbr\u003e\u003cbr\u003e ▣ Chapter 14: Evaluation Indicators\u003cbr\u003e 14.1 NLU Benchmark\u003cbr\u003e __14.1.1 MMLU\u003cbr\u003e __14.1.2 SuperGLUE\u003cbr\u003e __14.1.3 TruthfulQA\u003cbr\u003e 14.2 Reasoning and Problem Solving Indicators\u003cbr\u003e __14.2.1 AI2 Reasoning Challenge\u003cbr\u003e __14.2.2 GSM8K\u003cbr\u003e 14.3 Coding and Programming Assessment\u003cbr\u003e 14.4 Conversational Skills Assessment\u003cbr\u003e 14.5 Common Sense and General Knowledge Benchmark\u003cbr\u003e 14.6 Other Key Benchmarks\u003cbr\u003e 14.7 Developing Custom Metrics and Benchmarks\u003cbr\u003e 14.8 Interpretation and comparison of LLM evaluation results\u003cbr\u003e 14.9 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 15: Cross-Validation\u003cbr\u003e 15.1 Pretraining and Fine-Tuning Data Splitting\u003cbr\u003e __15.1.1 Stratified Sampling for Pretraining Data\u003cbr\u003e __15.1.2 Time-based segmentation for fine-tuning data\u003cbr\u003e __15.1.3 Oversampling and Weighting Techniques for Data Balance  \u003cbr\u003e15.2 Few-shot and Zero-shot Evaluation Strategies\u003cbr\u003e __15.2.1 Fewshot Evaluation\u003cbr\u003e __15.2.2 Zero Shot Evaluation\u003cbr\u003e 15.3 Domain and Task Generalization\u003cbr\u003e __15.3.1 Domain Adaptation Evaluation\u003cbr\u003e __15.3.2 Task Generalization Assessment\u003cbr\u003e 15.4 Continuous Learning Assessment\u003cbr\u003e 15.5 Challenges and Best Practices of Cross-Validation\u003cbr\u003e 15.6 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 16: Interpretability\u003cbr\u003e 16.1 Attention Visualization Techniques\u003cbr\u003e 16.2 Probe method\u003cbr\u003e 16.3 Explaining LLM predictions using contribution analysis techniques\u003cbr\u003e 16.4 Interpretability of Transformer-Based LLM\u003cbr\u003e 16.5 Possibility of a mechanistic interpretation\u003cbr\u003e 16.6 Balance between interpretability and performance\u003cbr\u003e 16.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 17: Fairness and Bias Detection\u003cbr\u003e 17.1 Types of Bias\u003cbr\u003e 17.2 Fairness Indicators for LLM Text Generation and Comprehension\u003cbr\u003e 17.3 Bias Detection\u003cbr\u003e 17.4 Debiasing Strategies\u003cbr\u003e 17.5 Training with Fairness in Mind\u003cbr\u003e 17.6 Ethical Considerations\u003cbr\u003e 17.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 18: Adversarial Robustness\u003cbr\u003e 18.1 Types of Text Adversarial Attacks\u003cbr\u003e 18.2 Adversarial Training Techniques\u003cbr\u003e 18.3 Robustness Evaluation\u003cbr\u003e 18.4 Trade-offs in LLM's Adversarial Training\u003cbr\u003e 18.5 Real-World Implications\u003cbr\u003e 18.6 Summary\u003cbr\u003e \u003cbr\u003e▣ Chapter 19: Reinforcement Learning with Human Feedback\u003cbr\u003e 19.1 Components of the RLHF System\u003cbr\u003e __19.1.1 Compensation Model\u003cbr\u003e __19.1.2 Policy Optimization\u003cbr\u003e 19.2 Extending RLHF\u003cbr\u003e 19.3 Limitations of RLHF in Language Modeling\u003cbr\u003e 19.4 RLHF Applications\u003cbr\u003e 19.5 Summary\u003cbr\u003e\u003cbr\u003e [Part 4] Advanced Prompt Engineering Techniques\u003cbr\u003e\u003cbr\u003e ▣ Chapter 20: Chain of Thinking (CoT) Prompting\u003cbr\u003e 20.1 Designing Effective CoT Prompts\u003cbr\u003e 20.2 Using CoT Prompting for Troubleshooting\u003cbr\u003e 20.3 Combining CoT prompting with other techniques\u003cbr\u003e 20.4 Evaluating CoT Prompting Output\u003cbr\u003e 20.5 Limitations of CoT Prompting\u003cbr\u003e 20.6 Future Direction\u003cbr\u003e 20.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 21: Thinking Tree (ToT) Prompting\u003cbr\u003e 21.1 Designing ToT Prompts\u003cbr\u003e 21.2 Exploration Strategy\u003cbr\u003e 21.3 Pruning and Evaluation\u003cbr\u003e 21.4 Applying ToT to Solve Multi-Step Problems\u003cbr\u003e 21.5 Implementation Challenges\u003cbr\u003e 21.6 Future Direction\u003cbr\u003e 21.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 22: Reasoning and Execution (ReAct)\u003cbr\u003e 22.1 Implementing ReAct with LangChain\u003cbr\u003e __22.1.1 ReAct Document Repository\u003cbr\u003e 22.2 Building a ReAct Agent with LCEL\u003cbr\u003e __22.2.1 ReActSingleInputOutputParser Description  \u003cbr\u003e__22.2.2 Running an agent with AgentExecutor\u003cbr\u003e 22.3 Complete tasks and solve problems\u003cbr\u003e 22.4 Performance Evaluation of ReAct\u003cbr\u003e 22.5 Safety, Control, and Ethical Considerations\u003cbr\u003e 22.6 Limitations and Future Directions\u003cbr\u003e 22.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 23: ReWOO (Remote Observation Outcome)\u003cbr\u003e 23.1 Implementing ReWOO with LangGraph\u003cbr\u003e 23.2 Advantages of ReWOO\u003cbr\u003e 23.3 Quality Assessment and Ethical Considerations\u003cbr\u003e 23.4 Future Direction\u003cbr\u003e 23.5 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 24: Reflection Techniques\u003cbr\u003e 24.1 Designing Prompts for Self-Reflection\u003cbr\u003e 24.2 Implementing Iterative Improvements\u003cbr\u003e 24.3 Bug Fixes\u003cbr\u003e 24.4 Assessing the Impact of Reflection\u003cbr\u003e 24.5 Challenges of Implementing Effective Reflection\u003cbr\u003e 24.6 Future Direction\u003cbr\u003e 24.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 25: Automated Multi-Step Reasoning and Tool Use\u003cbr\u003e 25.1 Prompting Design for Complex Task Decomposition\u003cbr\u003e 25.2 Integrating External Tools\u003cbr\u003e 25.3 Implementing automatic tool selection and use\u003cbr\u003e 25.4 Complex Problem Solving\u003cbr\u003e 25.5 Multi-level reasoning and tool use assessment\u003cbr\u003e 25.6 Challenges and Future Directions\u003cbr\u003e 25.7 Summary\u003cbr\u003e\u003cbr\u003e [Part 5] Search and Knowledge Integration in Large-Scale Language Models\u003cbr\u003e\u003cbr\u003e ▣ Chapter 26: Augmented Search Creation  \u003cbr\u003e26.1 Building a Simple RAG System\u003cbr\u003e 26.2 Embedding and Indexing Techniques for Search\u003cbr\u003e __26.2.1 Embedding\u003cbr\u003e __26.2.2 Index\u003cbr\u003e __26.2.3 Example code demonstrating embedding, indexing, and searching\u003cbr\u003e 26.3 Search Query Writing Strategies\u003cbr\u003e 26.4 Integrating the retrieved information into LLM creation\u003cbr\u003e 26.5 RAG's Challenges and Development Direction\u003cbr\u003e 26.6 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 27: Graph-based RAG\u003cbr\u003e 27.1 Overview of Graph-Based Knowledge Representation\u003cbr\u003e 27.2 Graph-Based RAG Architecture Design\u003cbr\u003e 27.3 Improving Search Performance Using Graph Embeddings\u003cbr\u003e 27.4 Integrating query expansion and generation using graph structures\u003cbr\u003e 27.5 Graph RAG Use Cases\u003cbr\u003e 27.6 Challenges and Solutions of Graph-Based RAG\u003cbr\u003e 27.7 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 28: Advanced RAG\u003cbr\u003e 28.1 Multi-stage and iterative search techniques\u003cbr\u003e 28.2 Adaptive Search Based on Context and Task\u003cbr\u003e 28.3 Improving Search through Meta-Learning\u003cbr\u003e 28.4 Combining RAG with Other Prompting Techniques\u003cbr\u003e 28.5 Handling Ambiguity and Uncertainty in RAG\u003cbr\u003e 28.6 Large-scale expansion of RAG's knowledge base\u003cbr\u003e 28.7 Future Directions of RAG Research\u003cbr\u003e 28.8 Summary\u003cbr\u003e \u003cbr\u003e▣ Chapter 29: RAG System Evaluation\u003cbr\u003e 29.1 Challenges in RAG System Evaluation\u003cbr\u003e __29.1.1 Interaction between Search and Creation\u003cbr\u003e __29.1.2 Context-Sensitive Evaluation\u003cbr\u003e __29.1.3 Beyond factual accuracy\u003cbr\u003e __29.1.4 Limitations of Automated Metrics\u003cbr\u003e __29.1.5 Difficulties in Error Analysis\u003cbr\u003e __29.1.6 The Need for Various Evaluation Scenarios\u003cbr\u003e __29.1.7 Dynamic Knowledge and Evolving Information\u003cbr\u003e __29.1.8 Computational Cost\u003cbr\u003e 29.2 Search Quality Evaluation Indicators\u003cbr\u003e __29.2.1 Recall@k\u003cbr\u003e __29.2.2 Precision@k\u003cbr\u003e __29.2.3 Mean Reverse Rank (MRR)\u003cbr\u003e __29.2.4 Normalized Discounted Cumulative Gain (NDCG@k)\u003cbr\u003e 29.3 Considerations Regarding Search Metrics\u003cbr\u003e 29.4 Assessing the relevance of retrieved information\u003cbr\u003e __29.4.1 How to evaluate the relevance of retrieved information\u003cbr\u003e __29.4.2 Challenges of RAG Relevance Assessment\u003cbr\u003e 29.5 Measuring the Impact of Search on Generation Performance\u003cbr\u003e __29.5.1 Key Indicators for Search Impact Assessment\u003cbr\u003e __29.5.2 Challenges in Measuring the Impact of Search\u003cbr\u003e 29.6 End-to-end evaluation of the RAG system\u003cbr\u003e __29.6.1 Evaluation Strategy\u003cbr\u003e __29.6.2 Challenges of End-to-End Evaluation  \u003cbr\u003e29.7 Human Evaluation Techniques for RAG\u003cbr\u003e __29.7.1 Best Practices for Human Evaluation\u003cbr\u003e __29.7.2 Challenges of Human Evaluation\u003cbr\u003e 29.8 Benchmarks and Datasets for RAG Evaluation\u003cbr\u003e 29.9 Summary\u003cbr\u003e\u003cbr\u003e ▣ Chapter 30: Agentic Patterns\u003cbr\u003e 30.1 Introduction to LLM-Based Agentic AI Systems\u003cbr\u003e 30.2 Goal Setting and Planning in LLM-Based Agents\u003cbr\u003e 30.3 Memory Implementation and State Management for LLM Agents\u003cbr\u003e 30.4 Decision-making and action selection in LLM-based agents\u003cbr\u003e 30.5 Learning and Adaptation in the Agentic LLM System\u003cbr\u003e 30.6 Ethical Considerations and Safety of LLM-Based Agentic AI\u003cbr\u003e 30.7 The Future of Agentic AI Using LLM\u003cbr\u003e 30.8 Summary\u003cbr\u003e 30.9 Future Directions and Development of the LLM Pattern\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eDetailed image\u003c\/b\u003e \u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cdiv\u003e\u003cimg src=\"https:\/\/image.yes24.com\/momo\/TopCate6140\/MidCate6\/613952182.jpg\" border=\"0\" alt=\"Detailed Image 1\"\u003e\u003c\/div\u003e\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003ePublisher's Review\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e ★ What this book covers ★\u003cbr\u003e\u003cbr\u003e ◎ Improving the efficiency of data preparation stages such as data purification and augmentation\u003cbr\u003e ◎ Design a scalable training pipeline using tuning, normalization, and checkpointing. \u003cbr\u003e◎ LLM optimization through pruning, quantization, and fine-tuning\u003cbr\u003e ◎ Model evaluation through metrics, cross-validation, and interpretability\u003cbr\u003e ◎ Understand fairness and find bias in output\u003cbr\u003e ◎ Development of an RLHF strategy for building a safe agentic AI system.\u003cbr\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"width:95%;padding-top:20px;padding-bottom:20px\"\u003e\n\n\u003cdiv style=\"text-align:left;font-size:16px;font-weight:bold;padding-bottom:20px\"\u003e GOODS SPECIFICS \u003c\/div\u003e\n\n\u003cdiv style=\"text-align:left;font-size:14px;line-height:1.6em;\"\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eDate of issue:\u003c\/strong\u003e November 25, 2025\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003ePage count, weight, size:\u003c\/strong\u003e 520 pages | 188*240*21mm\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eISBN13:\u003c\/strong\u003e 9791158396503 \u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\u003ccenter\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cspan\u003e\u003c\/span\u003e\n\n\u003c\/center\u003e\n\n\n\u003c\/center\u003e","brand":"LIBRAIRIE COREENNE","offers":[{"title":"Default Title","offer_id":43893426946090,"sku":"154434","price":44.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0683\/2750\/5962\/files\/6d570185b79a3083279ef2589bed9a7e.jpg?v=1765401526","url":"https:\/\/librairie.coreenne.fr\/en\/products\/154434","provider":"LIBRAIRIE COREENNE","version":"1.0","type":"link"}