Gen AI Dev - Design Retrieval Mechanisms for FM Augmentation

Labor Day starts with $70+ in savings on Coursera Plus. Save 40% for 3 months.

Gen AI Dev - Design Retrieval Mechanisms for FM Augmentation

Instructor: AWS Instructor

Included with Learn more

6 modules

Gain insight into a topic and learn the fundamentals.

Advanced level

Recommended experience

3 hours to complete

Flexible schedule

Learn at your own pace

6 modules

Gain insight into a topic and learn the fundamentals.

Advanced level

Recommended experience

3 hours to complete

Flexible schedule

Learn at your own pace

What you'll learn

Design and implement effective retrieval mechanisms
Manage Knowledge Base updates through incremental ingestion and synchronization
Construct end-to-end RAG systems by applying standardized interfaces that enforce security controls

Details to know

Shareable certificate

Add to your LinkedIn profile

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

There are 6 modules in this course

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

What's included

2 readings

What's included

16 readings

16 readingsTotal 16 minutes

Introduction to document segmentation1 minute
Chunking fundamentals1 minute
Purpose of segmentation in foundation model pipelines1 minute
Tradeoffs between relevance and context preservation1 minute
Evaluation metrics for segmentation quality1 minute
Hierarchical chunking strategies1 minute
Content-aware parsing1 minute
Recursive chunking implementation1 minute
Parent-child relationship maintenance1 minute
Dynamic chunk sizing based on semantic boundaries1 minute
Introduction1 minute
Amazon Bedrock native chunking1 minute
Configuration and integration1 minute
Custom Lambda-based chunking1 minute
Lambda implementation patterns1 minute
Selection criteria and decision framework1 minute

What's included

44 readings

44 readingsTotal 46 minutes

Introduction1 minute
Vector embeddings and semantic representation1 minute
Foundation model text transformation process1 minute
Semantic similarity and vector space1 minute
Vector search versus keyword search1 minute
When to use each approach1 minute
AWS Vector search services1 minute
Service comparison guide1 minute
Service selection guidelines1 minute
Detailed service specifications3 minutes
Introduction1 minute
Embedding model evaluation1 minute
Performance metrics and benchmarking1 minute
Model comparison framework1 minute
Batch embedding generation1 minute
AWS batch processing architecture1 minute
Cost optimization strategies1 minute
Embedding strategy selection1 minute
Implementation best practices1 minute
Introduction1 minute
Creating and configuring knowledge bases1 minute
Supported vector stores and configuration1 minute
Data source connectors and integration1 minute
Data ingestion pipeline design and optimization1 minute
Semantic retrieval and RAG implementation1 minute
Query interface introduction1 minute
Hybrid search implementation1 minute
Advanced retrieval strategies1 minute
Update and maintenance strategies1 minute
Document freshness and lifecycle management1 minute
Introduction1 minute
Reranking fundamentals and architecture1 minute
Evolution beyond basic retrieval systems1 minute
Reranker model types and characteristics1 minute
Amazon Bedrock reranker models integration1 minute
Bedrock reranker capabilities and model options1 minute
API specifications and input/output formats1 minute
Hybrid search architecture with reranking1 minute
Multi-signal retrieval architecture design1 minute
OpenSearch implementation with reranking1 minute
Result merging and fusion strategies1 minute
Performance and quality optimization1 minute
Evaluation frameworks and metrics1 minute
Latency management and optimization1 minute

What's included

29 readings

29 readingsTotal 31 minutes

Introduction1 minute
Query expansion with Amazon Bedrock1 minute
Implementation with Bedrock1 minute
Query decomposition with AWS Lambda1 minute
Lambda implementation patterns1 minute
Query transformation workflows1 minute
Workflow orchestration1 minute
Performance optimization1 minute
Integration and deployment1 minute
System integration patterns1 minute
Practical implementation example1 minute
E-commerce search scenario1 minute
Challenges and limitations1 minute
Technical challenges1 minute
Operational limitations1 minute
Introduction1 minute
System integration architecture and design1 minute
Connecting expansion, decomposition, and transformation1 minute
Latency, throughput, and cost optimization1 minute
Performance evaluation and quality assessment1 minute
Retrieval quality metrics implementation1 minute
Real-world implementation case study1 minute
Query context management with AgentCore Episodic Memory3 minutes
A/B testing and iterative refinement1 minute
Legal technology case study analysis1 minute
Implementation patterns and architecture decisions1 minute
Performance outcomes and optimization results1 minute
Advanced integration techniques and future considerations1 minute
Adaptive processing and machine learning integration1 minute

What's included

43 readings

43 readingsTotal 49 minutes

Introduction1 minute
Function interface design principles1 minute
Parameter standardization and validation1 minute
Error handling conventions and response formatting1 minute
Vector search function patterns1 minute
Query construction Functions2 minutes
Result processing and formatting functions1 minute
Implementation approaches and architecture1 minute
AWS Lambda function design and deployment1 minute
API gateway integration and security2 minutes
Cross-service authentication and integration1 minute
Healthcare use case implementation1 minute
Clinical search system development1 minute
Clinical decision support integration1 minute
Introduction1 minute
API Design for Retrieval Services1 minute
Synchronous vs. asynchronous processing patterns2 minutes
Request/response standardization1 minute
Query parameter normalization and result management1 minute
Query parameter normalization strategies1 minute
Result pagination and formatting1 minute
Metadata inclusion standards1 minute
Cross-service integration and interoperability1 minute
OpenAPI specification development2 minutes
Version compatibility management1 minute
Financial services use case implementation1 minute
Standardized function calling interface design1 minute
Fraud detection model integration1 minute
Introduction1 minute
Foundation model integration requirements1 minute
Context window considerations and management2 minutes
Input formatting standards and response parsing1 minute
Retrieval-augmented generation workflows1 minute
Pre-processing pipelines and content preparation1 minute
Post-processing techniques and response enhancement1 minute
Caching strategies and performance optimization2 minutes
Error handling and fallback mechanisms1 minute
Graceful degradation approaches1 minute
Timeout management and alternative retrieval paths1 minute
System resilience and reliability patterns1 minute
Government agency use case implementation1 minute
Unified retrieval augmentation API development1 minute
Document processing and citizen services integration1 minute

What's included

4 readings1 assignment

Instructor

AWS Instructor

Amazon Web Services

168 Courses365,088 learners

Offered by

Amazon Web Services

Why people choose Coursera for their career

Felipe M.

Learner since 2018

"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."

Jennifer J.

Learner since 2020

"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."

Larry W.

Learner since 2021

"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Break down barriers to learning with big savings
Get Coursera Plus
Start with easy savings for hard-working teams
Save 30% today

Frequently asked questions

To access course materials, assignments, and earn a Certificate, you'll need to purchase the Certificate experience when you enroll in a course. Eligible learners may also have the option to start with a Free Trial. Some courses may also offer a Full Course, No Certificate option. This lets you access course materials, submit required assessments, and receive a final grade, but you won't be able to earn or purchase a Certificate.

When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.