{"product_id":"138796","title":"Real-World! Developing RAG-Based Generative AI ","description":"\u003ccenter\u003e\u003cdiv style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/tmgdisk01.cafe24.com\/images\/vs\/4172\/sv\/3jXPB8jWFwC3mtAyyr8oDvo0DK1PxH.png?v=1765068520\" 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 Real-World! Developing RAG-Based Generative AI \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\/143311442\/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 \u003cb\u003eMinimize AI illusions using RAG and integrate embedding vector databases and human feedback.\u003cbr\u003e Build accurate, customized generative AI pipelines!\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003e\"Practical! RAG-Based Generative AI Development\" presents a roadmap for building effective LLM, computer vision, and generative AI systems that balance performance and cost.\u003cbr\u003e This book details how to design, manage, and control RAG and multimodal AI pipelines. RAG is a technology that enhances the accuracy and contextual relevance of output by linking it to traceable source documents, enabling a dynamic approach to managing large amounts of information.\u003cbr\u003e The book also provides practical knowledge about vector storage, chunking, indexing, and ranking, and shows how to build the RAG framework from start to finish. \u003cbr\u003eYou'll learn techniques to optimize project performance and better understand your data, including improving search accuracy with adaptive RAGs and human feedback, balancing RAGs with fine-tuning, implementing dynamic RAGs to enhance real-time decision-making, and visualizing complex data with knowledge graphs.\u003cbr\u003e\u003cbr\u003e It contains abundant practical examples using frameworks such as RamaIndex, Pinecone, and DeepLake, as well as generative AI platforms such as OpenAI and HuggingFace.\u003cbr\u003e By learning the skills to implement intelligent solutions through this book, you'll gain a competitive edge in any project, from production to customer service.\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 \",\"\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eindex\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e \u003cb\u003e▣ Chapter 1: Why RAG (Research Augmentation Generation) is Needed\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 1.1 What is RAG?\u003cbr\u003e 1.2 Simple, advanced, and modular RAG configurations\u003cbr\u003e 1.3 RAG vs. Fine Tuning\u003cbr\u003e 1.4 RAG Ecosystem  \u003cbr\u003e__1.4.1 Search Engine (D)\u003cbr\u003e __1.4.2 Generator (G)\u003cbr\u003e __1.4.3 Evaluator (E)\u003cbr\u003e __1.4.4 Training (T)\u003cbr\u003e 1.5 Simple, Advanced, and Modular Python Implementations of RAG\u003cbr\u003e __1.5.1 Part 1: Basics and Basic Implementation\u003cbr\u003e __1.5.2 Part 2: Advanced Techniques and Evaluation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 2: RAG Embedding Vector Repository Using Deep Lake and OpenAI\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 2.1 From raw data to embedding in vector storage\u003cbr\u003e 2.2 Configuring the RAG system as a single pipeline\u003cbr\u003e 2.3 RAG-based generative AI pipeline\u003cbr\u003e 2.4 Building the RAG Pipeline\u003cbr\u003e __2.4.1 Preferences\u003cbr\u003e __2.4.2 Component 1: Data Collection and Preparation\u003cbr\u003e __2.4.3 Component 2: Data Embedding and Storage\u003cbr\u003e __2.4.4 Vector storage information\u003cbr\u003e __2.4.5 Component 3: Input Augmentation and Response Generation\u003cbr\u003e 2.5 Output Evaluation Using Cosine Similarity\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 3: Building an Index-Based RAG Using RamaIndex, Deep Lake, and OpenAI\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 3.1 Why Use Index-Based RAG?\u003cbr\u003e __3.1.1 Architecture  \u003cbr\u003e3.2 Building a Semantic Search Engine and Generative Agent for Drone Technology Information\u003cbr\u003e __3.2.1 Environment Installation\u003cbr\u003e __3.2.2 Pipeline 1: Document Collection and Preparation\u003cbr\u003e __3.2.3 Pipeline 2: Preparing the Vector Store\u003cbr\u003e __3.2.4 Pipeline 3: Index-based RAG\u003cbr\u003e 3.3 Vector Storage Index and Query Engine\u003cbr\u003e __3.3.1 Query Response and Source Verification\u003cbr\u003e __3.3.2 Optimized chunking\u003cbr\u003e __3.3.3 Performance Metrics\u003cbr\u003e 3.4 Tree Index Query Engine\u003cbr\u003e __3.4.1 Performance Metrics\u003cbr\u003e 3.5 List Index Query Engine\u003cbr\u003e __3.5.1 Performance Metrics\u003cbr\u003e 3.6 Keyword Index Query Engine\u003cbr\u003e __3.6.1 Performance Metrics\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 4: Multimodal Modular RAG for Drone Technology\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 4.1 What is a multi-modal modular RAG?\u003cbr\u003e 4.2 Building a Multimodal Modular RAG Program for Drone Technology\u003cbr\u003e __4.2.1 Loading the LLM dataset\u003cbr\u003e __4.2.2 Loading and Visualizing Multimodal Datasets\u003cbr\u003e __4.2.3 Multimodal Dataset Structure\u003cbr\u003e __4.2.4 Building a Multi-Modal Query Engine\u003cbr\u003e __4.2.5 Multi-modal modular query result summary\u003cbr\u003e __4.2.6 Performance Metrics\u003cbr\u003e \u003cbr\u003e\u003cb\u003e▣ Chapter 5: Improving RAG Performance Using Expert Feedback\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 5.1 Adaptive RAG\u003cbr\u003e 5.2 Building a Hybrid Adaptive RAG System Using Python\u003cbr\u003e __5.2.1 Finder (Section 1)\u003cbr\u003e __5.2.2 Generator (Section 2)\u003cbr\u003e __5.2.3 Evaluator (Section 3)\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 6: Expanding RAG Bank Customer Data Using Finecon\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 6.1 Extension using Pinecone\u003cbr\u003e __6.1.1 Architecture\u003cbr\u003e 6.2 Pipeline 1: Dataset Collection and Preparation\u003cbr\u003e __6.2.1 Dataset Collection and Processing (Section 1)\u003cbr\u003e __6.2.2 Exploratory Data Analysis (Section 2)\u003cbr\u003e __6.2.3 ML Model Training (Section 3)\u003cbr\u003e 6.3 Pipeline 2: Expanding the Pinecone Index (Vector Storage)\u003cbr\u003e __6.3.1 Challenges of Vector Storage Management\u003cbr\u003e __6.3.2 Environment Installation\u003cbr\u003e __6.3.3 Dataset Processing\u003cbr\u003e __6.3.4 Dataset Chunking and Embedding\u003cbr\u003e __6.3.5 Creating a Pinecone Index\u003cbr\u003e __6.3.6 Upsert\u003cbr\u003e __6.3.7 Pinecone Index Query\u003cbr\u003e 6.4 Pipeline 3: RAG Generative AI\u003cbr\u003e __6.4.1 RAG using GPT-4o\u003cbr\u003e __6.4.2 Extracting Related Text\u003cbr\u003e __6.4.3 Input Augmentation and Prompt Engineering  \u003cbr\u003e__6.4.4 Augmented Generation\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 7: Building a Scalable Knowledge Graph-Based RAG Using the Wikipedia API and RamaIndex\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 7.1 RAG Architecture for Knowledge Graph-Based Semantic Retrieval\u003cbr\u003e __7.1.1 Creating a tree graph with nodes\u003cbr\u003e 7.2 Pipeline 1: Document Collection and Preparation\u003cbr\u003e __7.2.1 Searching Wikipedia data and metadata\u003cbr\u003e __7.2.2 Preparing Data for Upsert\u003cbr\u003e 7.3 Pipeline 2: Creating and Populating the Deep Lake Vector Store\u003cbr\u003e 7.4 Pipeline 3: Knowledge Graph Index-Based RAG\u003cbr\u003e __7.4.1 Creating a Knowledge Graph Index\u003cbr\u003e __7.4.2 Graph display\u003cbr\u003e __7.4.3 Interacting with the Knowledge Graph Index\u003cbr\u003e __7.4.4 Installing the similarity score package and defining functions\u003cbr\u003e __7.4.5 Re-ranking\u003cbr\u003e __7.4.6 Example indicators\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 8: Dynamic RAG using chroma and hugging face llamas\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 8.1 Architecture of Dynamic RAG\u003cbr\u003e 8.2 Environment Installation\u003cbr\u003e __8.2.1 Installing Hugging Face\u003cbr\u003e __8.2.2 Installing Chroma\u003cbr\u003e 8.3 Enabling Session Time\u003cbr\u003e 8.4 Downloading and Preparing the Dataset  \u003cbr\u003e8.5 Data Embedding and Upsert in Chroma Collections\u003cbr\u003e __8.5.1 Model Selection\u003cbr\u003e __8.5.2 Document Embedding and Saving\u003cbr\u003e __8.5.3 Embedding display\u003cbr\u003e 8.6 Executing queries on collections\u003cbr\u003e 8.7 Prompts and Searches\u003cbr\u003e 8.8 RAG using Rama\u003cbr\u003e __8.8.1 Deleting a Collection\u003cbr\u003e 8.9 Total Session Time\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 9: Enhancing AI Model Capabilities - Fine-tuning RAG Data and Human Feedback\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 9.1 Architecture of static RAG data fine-tuning\u003cbr\u003e __9.1.1 RAG Ecosystem\u003cbr\u003e 9.2 Environment Installation\u003cbr\u003e 9.3 Preparing the Dataset for Fine-Tuning (Section 1)\u003cbr\u003e __9.3 1 Downloading and Visualizing the Dataset (Section 1.1)\u003cbr\u003e __9.3 2 Preparing the Dataset for Fine-Tuning (Section 1.2)\u003cbr\u003e 9.4 Model Fine-Tuning (Section 2)\u003cbr\u003e __9.4.1 Fine-tuning monitoring\u003cbr\u003e 9.5 Running the Fine-Tuned OpenAI Model (Section 3)\u003cbr\u003e 9.6 Indicator\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 10: RAG System for Video Stock Production Using Pinecone and OpenAI\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 10.1 RAG Architecture for Video Production\u003cbr\u003e 10.2 Environment of the video production ecosystem\u003cbr\u003e __10.2.1 Importing modules and libraries  \u003cbr\u003e__10.2.2 GitHub\u003cbr\u003e __10.2.3 OpenAI\u003cbr\u003e __10.2.4 Pinecone\u003cbr\u003e 10.3 Pipeline 1: Generator and Commentary Writer\u003cbr\u003e __10.3.1 AI-generated video dataset\u003cbr\u003e __10.3.2 Generator and Commentary Writer\u003cbr\u003e 10.4 Pipeline 2: Vector Storage Manager\u003cbr\u003e __10.4.1 Pinecone Index Query\u003cbr\u003e 10.5 Pipeline 3: Video Expert\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Appendix A: Practice Problem Answers\u003c\/b\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\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\/TopCate5178\/MidCate4\/517736988.jpg\" border=\"0\" alt=\"Detailed Image 1\"\u003e\u003c\/div\u003e\u003c\/div\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 \u003cb\u003e★ What this book covers ★\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e ◎ Extend the RAG pipeline to efficiently process large datasets.\u003cbr\u003e ◎ Apply techniques to minimize hallucinations and ensure accurate responses.\u003cbr\u003e ◎ Implement an indexing technique that improves AI accuracy with traceable and transparent output.\u003cbr\u003e ◎ Customize and expand RAG-driven generative AI systems across various domains.\u003cbr\u003e ◎ Search data faster and more efficiently using Deep Lake and Pinecone. \u003cbr\u003e◎ Build and control a robust generative AI system based on actual data.\u003cbr\u003e ◎ Combine text and image data for richer and more informative AI responses.\u003cbr\u003e\n\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e \"]\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 March 18, 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 412 pages | 175*235*17mm\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 9791158395919 \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":43893314060330,"sku":"138796","price":41.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0683\/2750\/5962\/files\/2ee09dcd336e1831a495df085f779802.jpg?v=1765395747","url":"https:\/\/librairie.coreenne.fr\/en\/products\/138796","provider":"LIBRAIRIE COREENNE","version":"1.0","type":"link"}