RAG in Action

Foundations, Architecture, and Agentic Implementation
1. Auflage 2027
ISBN: 978-1-041-28455-0
Verlag: Taylor & Francis

Buch, Englisch, 482 Seiten, Format (B × H): 156 mm x 234 mm

Retrieval-Augmented Generation (RAG) has become a fundamental architectural pattern in generative AI systems and addresses critical limitations of large language models (LLMs). While LLMs excel at language comprehension and content generation, they are constrained by static training data and parametric memory, raising concerns about factual accuracy, transparency, and controllability. RAG overcomes these challenges by integrating structured information retrieval into the generative process. Instead of relying solely on memorized representations, RAG systems dynamically access external knowledge sources during inference to enhance factual grounding, contextuality, and access to domain-specific or continuously updated information.

RAG in Action: Foundations, Architecture, and Agentic Implementation covers theoretical foundations and engineering practices. It begins with fundamental components including document ingestion, preprocessing, and chunking strategies that directly impact retrieval performance. Coverage then extends to various retrieval methodologies: dense vector retrieval, sparse retrieval, hybrid approaches, and graph-based retrieval. Subsequent sections discuss optimization techniques for ranking and relevance and emphasize reranking models and scoring systems crucial for response fidelity. Also examined are multimodal RAG systems integrating text, images, and structured documents, as well as enterprise considerations such as distributed architectures, cross-cloud deployment, scalability, observability, evaluation frameworks, cost management, and governance.

The book emphasizes how architectural decisions create cascading effects: retrieval quality influences generation quality; assessment policies affect reliability; infrastructure choices impact scalability and performance. Understanding these interdependencies is essential for building robust, production-ready AI systems. As generative AI advances, the integration of retrieval, reasoning, and system-level engineering will define trustworthy deployments, making RAG a crucial step toward sensible, transparent, and responsible AI.

Zielgruppe

Professional Practice & Development and Professional Reference

Autoren/Hrsg.

Thummarakoti, Sairohith

Pendyala, Jothsna Praveena

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Spracherkennung, Sprachverarbeitung
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik EDV | Informatik Daten / Datenbanken Data Mining

Inhaltsverzeichnis

1. Retrieval-Augmented Generation (RAG): Architecture, Core Flow, and Key Components 2. Chunking Strategies 3. Introduction to Retrieval in RAG 4. Ranking and Relevance: Reranking, Noise Filtering, and Scoring in Modern Retrieval Systems 5. Performance Evaluation 6. Retrieval-Augmented Generation for Text (PDFs): End-to-End Pipeline for Processing Documents 7. Multimodal RAG: Text and Vision Models for Images, Charts, and OCR 8. Optimization and Scalability: A System-Level Engineering Perspective on Caching, Batching, Large-Scale Tuning of Retrieval-Augmented Generation Systems 9. Cross-Cloud RAG Architectures: Building Enterprise-Grade Retrieval-Augmented Generation on AWS, GCP, and Pega Cloud 10. Cloud-Scale RAG Systems: Architectural Design and Performance Optimization for Enterprise AI Systems 11. Agentic RAG

Über Autor(innen)

Sairohith Thummarakoti is a seasoned enterprise technology professional with more than a decade of experience in cloud computing, low code platforms, and healthcare IT. He currently works at HCA Healthcare as a Consultant Application Engineer, where he leads critical modernization initiatives using Pega Cloud 3 and containerized architectures to improve application scalability, security, and operational efficiency.  Jothsna Praveena is a senior data scientist focused on agentic AI and production RAG. Her work spans ambient agents with LangGraph, evaluation-first pipelines, and cloud deployments, drawing on experience that includes a stint at Amazon and roles in enterprise ML and AIOps. She holds an MS in Data Analytics from Clark University and maintains active credentials in AWS and Databricks.