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
Gen AI Dev - Design Retrieval Mechanisms for FM Augmentation · LearnSpace
Назад в каталог
courseraАнализ данных

Gen AI Dev - Design Retrieval Mechanisms for FM Augmentation

Курс от Amazon Web Services
Продвинутый≈ 2.9 чАмериканский английский
О курсеНавыкиПрограммаПреподаватели

О курсе

As organizations increasingly deploy retrieval-augmented generation (RAG) systems to unlock the value of their knowledge assets, the demand for skilled professionals who can architect, implement, and optimize these solutions continues to grow. This curriculum prepares you to meet that demand by providing hands-on experience with AWS services and production-ready implementation patterns.In this module, you will learn how to do the following:Design and implement effective retrieval mechanisms

Навыки, которые вы освоите

Amazon Web ServicesNatural Language ProcessingSoftware DevelopmentPrompt EngineeringRestful APIArtificial IntelligenceLarge Language ModelingDocument ManagementModel EvaluationAPI GatewayAPI DesignCloud ComputingScalabilityAI WorkflowsApplication Programming Interface (API)Artificial Intelligence and Machine Learning (AI/ML)Generative AIMachine LearningPerformance Tuning

Программа курса

6 модулей · 139 учебных материалов

01Introduction2 материалов

Module Introduction

IntroductionЧтениеKey topicsЧтение
02Document Segmentation for Foundation Model Context Augmentation16 материалов

Document Segmentation Fundamentals

Introduction to document segmentationЧтениеChunking fundamentals

Учитесь у экспертов

AWS Instructor

Преподаватель курса

Gen AI Dev - Design Retrieval Mechanisms for FM Augmentation
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

≈ 2.9 ч

6 модулей

Язык: Американский английский

Часть программы вашего университета
Чтение
Purpose of segmentation in foundation model pipelinesЧтение
Tradeoffs between relevance and context preservationЧтение
Evaluation metrics for segmentation qualityЧтение
Hierarchical chunking strategiesЧтение
Content-aware parsingЧтение
Recursive chunking implementationЧтение
Parent-child relationship maintenanceЧтение
Dynamic chunk sizing based on semantic boundariesЧтение

Custom and Managed Chunking Strategies

IntroductionЧтениеAmazon Bedrock native chunkingЧтениеConfiguration and integrationЧтениеCustom Lambda-based chunkingЧтениеLambda implementation patternsЧтениеSelection criteria and decision frameworkЧтение
03Vector Search on AWS44 материалов

Introduction to Vector Search

IntroductionЧтениеVector embeddings and semantic representationЧтениеFoundation model text transformation processЧтениеSemantic similarity and vector spaceЧтениеVector search versus keyword searchЧтениеWhen to use each approachЧтениеAWS Vector search servicesЧтениеService comparison guideЧтениеService selection guidelinesЧтениеDetailed service specificationsЧтение

Embedding Strategy and Optimization

IntroductionЧтениеEmbedding model evaluationЧтениеPerformance metrics and benchmarkingЧтениеModel comparison frameworkЧтениеBatch embedding generationЧтениеAWS batch processing architectureЧтениеCost optimization strategies

Amazon Bedrock Knowledge Bases

IntroductionЧтениеCreating and configuring knowledge basesЧтениеSupported vector stores and configurationЧтениеData source connectors and integrationЧтениеData ingestion pipeline design and optimizationЧтениеSemantic retrieval and RAG implementationЧтение

Advanced Relevance Engineering with Rerankers

IntroductionЧтениеReranking fundamentals and architectureЧтениеEvolution beyond basic retrieval systemsЧтениеReranker model types and characteristicsЧтениеAmazon Bedrock reranker models integrationЧтениеBedrock reranker capabilities and model optionsЧтение
04Query Handling with AWS Services29 материалов

Advanced Query Processing Techniques

IntroductionЧтениеQuery expansion with Amazon BedrockЧтениеImplementation with BedrockЧтениеQuery decomposition with AWS LambdaЧтениеLambda implementation patternsЧтениеQuery transformation workflowsЧтениеWorkflow orchestrationЧтениеPerformance optimizationЧтениеIntegration and deploymentЧтениеSystem integration patternsЧтениеPractical implementation exampleЧтениеE-commerce search scenarioЧтениеChallenges and limitationsЧтениеTechnical challengesЧтениеOperational limitationsЧтение

End-to-End Query Processing Systems

IntroductionЧтениеSystem integration architecture and designЧтениеConnecting expansion, decomposition, and transformationЧтениеLatency, throughput, and cost optimizationЧтениеPerformance evaluation and quality assessmentЧтениеRetrieval quality metrics implementationЧтение
05Vector Search API Design and Implementation43 материалов

Standardized Function Calling for Vector Search

IntroductionЧтениеFunction interface design principlesЧтениеParameter standardization and validationЧтениеError handling conventions and response formattingЧтениеVector search function patternsЧтениеQuery construction FunctionsЧтениеResult processing and formatting functionsЧтениеImplementation approaches and architectureЧтениеAWS Lambda function design and deploymentЧтениеAPI gateway integration and securityЧтениеCross-service authentication and integrationЧтениеHealthcare use case implementationЧтениеClinical search system developmentЧтениеClinical decision support integrationЧтение

API Patterns for Retrieval Augmentation

IntroductionЧтениеAPI Design for Retrieval ServicesЧтениеSynchronous vs. asynchronous processing patternsЧтениеRequest/response standardizationЧтениеQuery parameter normalization and result managementЧтениеQuery parameter normalization strategiesЧтение

Integration with Foundation Models

IntroductionЧтениеFoundation model integration requirementsЧтениеContext window considerations and managementЧтениеInput formatting standards and response parsingЧтениеRetrieval-augmented generation workflowsЧтениеPre-processing pipelines and content preparationЧтение
06Conclusion5 материалов

Course Summary

Graded AssessmentЗаданиеRecap and next stepsЧтениеResourcesЧтениеSurveyЧтение

Contact Us

We want to hear from youЧтение
Чтение
Embedding strategy selectionЧтение
Implementation best practicesЧтение
Query interface introductionЧтение
Hybrid search implementationЧтение
Advanced retrieval strategiesЧтение
Update and maintenance strategiesЧтение
Document freshness and lifecycle managementЧтение
API specifications and input/output formatsЧтение
Hybrid search architecture with rerankingЧтение
Multi-signal retrieval architecture designЧтение
OpenSearch implementation with rerankingЧтение
Result merging and fusion strategiesЧтение
Performance and quality optimizationЧтение
Evaluation frameworks and metricsЧтение
Latency management and optimizationЧтение
Real-world implementation case studyЧтение
Query context management with AgentCore Episodic MemoryЧтение
A/B testing and iterative refinementЧтение
Legal technology case study analysisЧтение
Implementation patterns and architecture decisionsЧтение
Performance outcomes and optimization resultsЧтение
Advanced integration techniques and future considerationsЧтение
Adaptive processing and machine learning integrationЧтение
Result pagination and formattingЧтение
Metadata inclusion standardsЧтение
Cross-service integration and interoperabilityЧтение
OpenAPI specification developmentЧтение
Version compatibility managementЧтение
Financial services use case implementationЧтение
Standardized function calling interface designЧтение
Fraud detection model integrationЧтение
Post-processing techniques and response enhancementЧтение
Caching strategies and performance optimizationЧтение
Error handling and fallback mechanismsЧтение
Graceful degradation approachesЧтение
Timeout management and alternative retrieval pathsЧтение
System resilience and reliability patternsЧтение
Government agency use case implementationЧтение
Unified retrieval augmentation API developmentЧтение
Document processing and citizen services integrationЧтение