К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Unlocking Data with Generative AI and RAG · LearnSpace
Назад в каталог
courseraАнализ данных

Unlocking Data with Generative AI and RAG

Курс от Packt
Средний≈ 13.9 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

Master Retrieval-Augmented Generation (RAG), the most popular generative AI tool, to unlock the full potential of your data. This course enables you to develop highly sought-after skills as corporate investment in generative AI soars. This resource equips learners with the knowledge and skills to harness RAG (Retrieval-Augmented Generation) for more intelligent AI applications. It bridges theoretical concepts with practical implementation, focusing on real-world use cases and advanced techniques. Designed for professionals seeking to enhance AI systems, it provides actionable insights and hands-on experience. This resource is ideal for AI researchers, data scientists, software developers, and business analysts with a foundational understanding of AI. It provides practical, hands-on learning through real-world coding examples, making it accessible to both technical and non-technical audiences. A basic knowledge of Python and Jupyter Notebooks is required. For non-technical readers trying to understand how RAG can be utilized, much of the text explains the importance of RAG and how it can be best utilized. For technical readers, we provide a full RAG pipeline coding use case. For each new topic, we show how that topic impacts the code, giving you an in-depth understanding of how coding choices can impact the capabilities of RAG-based applications.

Навыки, которые вы освоите

EmbeddingsPrompt EngineeringRetrieval-Augmented GenerationAI SecurityUI ComponentsGenerative AILLM ApplicationMultimodal PromptsArtificial Intelligence and Machine Learning (AI/ML)Agentic WorkflowsArtificial IntelligenceLangGraphVector DatabasesApplication SecurityLarge Language ModelingLangChainUser Interface (UI) DesignGenerative AI AgentsPython Programming

Программа курса

14 модулей · 124 учебных материалов

01What Is Retrieval-Augmented Generation (RAG)9 материалов

Unlocking the Power of Retrieval-Augmented Generation in AI

OverviewВидеоIntroductionЧтениеChallenges of RAGЧтениеRAG vocabularyЧтение

Учитесь у экспертов

Packt - Course Instructors

Преподаватель курса

Unlocking Data with Generative AI and RAG
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 13.9 ч

14 модулей

Язык: Английский

Часть программы вашего университета
Fine-tuning – full-model fine-tuning (FMFT) and parameter-efficient fine-tuning (PEFT)Чтение
Implementing RAG in AI applicationsЧтение
Comparing RAG with model fine-tuningЧтение
The architecture of RAG systemsЧтение
Exploring Retrieval-Augmented GenerationЗадание
02Code Lab – An Entire RAG Pipeline10 материалов

Building Your First End-to-End RAG Pipeline

OverviewВидеоIntroductionЧтениеNo interface!ЧтениеImportsЧтениеIndexingЧтениеEmbedding and indexing the chunksЧтениеRetrieval and generationЧтениеSetting up a LangChain chain using LCELЧтениеSubmitting a question for RAGЧтениеRAG Pipeline FundamentalsЗадание
03Practical Applications of RAG8 материалов

Transforming Business Workflows with Retrieval-Augmented Generation

OverviewВидеоIntroductionЧтениеRAG for automated reportingЧтениеE-commerce supportЧтениеUtilizing knowledge bases with RAGЧтениеInnovation scouting and trend analysisЧтениеCode lab 3.1 – Adding sources to your RAGЧтениеPractical Applications of RAGЗадание
04Components of a RAG System7 материалов

Building Blocks of Retrieval-Augmented Generation: From Indexing to User Experience

OverviewВидеоIntroductionЧтениеRetrieval and generationЧтениеPromptingЧтениеDefining your LLMЧтениеUIЧтениеExploring RAG System ArchitectureЗадание
05Managing Security in RAG Applications9 материалов

Defending RAG Systems: From Threats to Countermeasures

OverviewВидеоIntroductionЧтениеRAG security challengesЧтениеHallucinationsЧтениеCommon areas to target with red teamingЧтениеCode lab 5.1 – Securing your keysЧтениеCode lab 5.2 – Red team attack!ЧтениеCode lab 5.3 – Blue team defend!ЧтениеSecuring RAG ApplicationsЗадание
06Interfacing with RAG and Gradio4 материалов

Building Interactive RAG Apps with Gradio

OverviewВидеоIntroductionЧтениеBenefits of using GradioЧтениеRAG and Gradio FundamentalsЗадание
07The Key Role Vectors and Vector Stores Play in RAG14 материалов

Demystifying Vectors and Embeddings in RAG Systems

OverviewВидеоIntroductionЧтениеVector dimensions and sizeЧтениеWhere vectors lurk in your codeЧтениеThe amount of text you vectorize matters!ЧтениеNot all semantics are created equal!ЧтениеWord2Vec, Sentence2Vec, and Doc2VecЧтениеBidirectional encoder representations from transformersЧтениеOpenAI and other similar large-scale embedding servicesЧтениеSpeedЧтениеData sources (other than vector)ЧтениеCommon vector store optionsЧтениеChoosing a vector storeЧтениеVectors and Vector Stores in Retrieval-Augmented GenerationЗадание
08Similarity Searching with Vectors12 материалов

Mastering Semantic Search: From Distance Metrics to Hybrid Retrieval

OverviewВидеоIntroductionЧтениеSemantic versus keyword searchЧтениеEuclidean distance (L2)ЧтениеDifferent search paradigms – sparse, dense, and hybridЧтениеCode lab 8.2 – Hybrid search with a custom functionЧтениеCode lab 8.3 – Hybrid search with LangChain's EnsembleRetriever to replace our custom functionЧтениеSemantic search algorithmsЧтениеEnhancing search with indexing techniquesЧтениеVector search optionsЧтениеPineconeЧтениеVector Search FundamentalsЗадание
09Evaluating RAG Quantitatively and with Visualizations12 материалов

Mastering RAG Evaluation: Metrics, Visualizations, and Practical Tools

OverviewВидеоIntroductionЧтениеEvaluation helps you get betterЧтениеFinal thoughts on standardized evaluation frameworksЧтениеCode lab 9.1 – ragasЧтениеSetting up LLMs/embedding modelsЧтениеGenerating the synthetic ground truthЧтениеAnalyzing the ragas resultsЧтениеRetrieval evaluationЧтениеEnd-to-end evaluationЧтениеAdditional evaluation techniquesЧтениеQuantitative Evaluation and Visualization in RAGЗадание
10Key RAG Components in LangChain5 материалов

Building Effective RAG Pipelines with LangChain Components

OverviewВидеоIntroductionЧтениеCode lab 10.2 – LangChain RetrieversЧтениеCode lab 10.3 – LangChain LLMsЧтениеLangChain RAG Components and Vector SearchЗадание
11Using LangChain to Get More from RAG6 материалов

Mastering Document Chunking and Output Parsing with LangChain

OverviewВидеоIntroductionЧтениеCode lab 11.2 – Text splittersЧтениеRecursive character text splitterЧтениеCode lab 11.3 – Output parsersЧтениеLangChain and RAG TechniquesЗадание
12Combining RAG with the Power of AI Agents and LangGraph8 материалов

Building Intelligent RAG Pipelines with LangGraph Agents

OverviewВидеоIntroductionЧтениеGraphs, AI agents, and LangGraphЧтениеCode lab 12.1 – adding a LangGraph agent to RAGЧтениеAgent stateЧтениеNodes and edges in our agentЧтениеCyclical graph setupЧтениеAI Agents and LangGraph FundamentalsЗадание
13Using Prompt Engineering to Improve RAG Efforts12 материалов

Mastering Prompt Strategies for Enhanced RAG Performance

OverviewВидеоIntroductionЧтениеTop-pЧтениеTake your shotЧтениеFundamentals of prompt designЧтениеAdapting prompts for different LLMsЧтениеCode lab 13.2 – Prompting optionsЧтениеSummarizingЧтениеExtracting key dataЧтениеTransformationЧтениеExpansionЧтениеEnhancing RAG Performance Through Prompt DesignЗадание
14Advanced RAG-Related Techniques for Improving Results8 материалов

Mastering Advanced RAG: From Re-ranking to Multi-Modal Integration

OverviewВидеоIntroductionЧтениеRe-ranking in hybrid RAGЧтениеCode lab 14.2 – Query decompositionЧтениеCode lab 14.3 – MM-RAGЧтениеIntroducing MM-RAG in codeЧтениеOther advanced RAG techniques to exploreЧтениеEnhancing Retrieval with Advanced TechniquesЗадание