RAG Systems in Practice

This course is part of LLM Engineering: Prompting, Fine-Tuning, Optimization & RAG Specialization

Instructor: Edureka

Access provided by NMIMS Indore

4 modules

Gain insight into a topic and learn the fundamentals.

Beginner level

Recommended experience

1 week to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

4 modules

Gain insight into a topic and learn the fundamentals.

Beginner level

Recommended experience

1 week to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

What you'll learn

How to build and optimize Retrieval-Augmented Generation (RAG) systems using LangChain and FAISS.
Techniques for enhancing retrieval accuracy through hybrid search, re-ranking, and grounding methods.
How to deploy RAG systems into production environments and integrate them with APIs and platforms like Streamlit.
Best practices for monitoring, evaluating, and scaling RAG systems for optimal performance.

Skills you'll gain

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

14 assignments

Taught in English

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

Build your subject-matter expertise

This course is part of the LLM Engineering: Prompting, Fine-Tuning, Optimization & RAG Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 4 modules in this course

This course introduces the core concepts and techniques behind Retrieval-Augmented Generation (RAG) systems, guiding you through building, optimizing, and deploying powerful AI systems that combine language models with external knowledge sources. Whether you are new to RAG or looking to deepen your understanding, this course provides a hands-on approach to mastering RAG workflows and improving model accuracy.

Through detailed lessons, demonstrations, and real-world applications, you’ll learn how to preprocess and index documents, generate embeddings, construct RAG pipelines, and deploy production-ready systems. You’ll also explore advanced optimization techniques to enhance retrieval quality, scalability, and context relevance. By the end of this course, you will be able to: • Understand the fundamentals of Retrieval-Augmented Generation and its applications in AI. • Apply text preprocessing and embedding techniques to improve document retrieval. • Build and optimize RAG pipelines using LangChain and FAISS. • Utilize hybrid retrieval, re-ranking, and grounding methods to enhance context accuracy. • Deploy and evaluate RAG systems in production environments for optimal performance. This course is ideal for AI enthusiasts, machine learning practitioners, and developers looking to specialize in building advanced AI systems that integrate external knowledge with language models. No prior experience with RAG systems is required, but a basic understanding of Python and machine learning concepts will be beneficial. Join us to begin your journey into the world of Retrieval-Augmented Generation and learn how to build efficient, scalable, and accurate AI systems!

In this module, learners will explore the fundamentals of Retrieval-Augmented Generation (RAG), including how it combines language models with external knowledge sources for improved accuracy. Key concepts such as text embeddings, vector stores, and document preprocessing will be introduced, with hands-on demonstrations to build simple RAG workflows and visualize context retrieval.

What's included

13 videos5 readings4 assignments1 discussion prompt

13 videos Total 72 minutes

Specialization Introduction 7 minutes
Course Introduction 4 minutes
Introduction to RAG 7 minutes
Demonstration: Building Simple Rag Workflow 6 minutes
Demonstration: Visualizing Context Retrieval Flow-I 5 minutes
Demonstration: Visualizing Context Retrieval Flow II 5 minutes
Importance of Embeddings in Retrieval System Design 5 minutes
Understanding Text Embeddings and Similarity Search 5 minutes
Demonstration: Generating Embeddings Using OpenAI API 6 minutes
Demonstration: Building a FAISS Vector Store 5 minutes
Splitting and Cleaning Documents for Indexing 5 minutes
Demonstration: Using LangChain Loaders for PDFs and Text Files 6 minutes
Demonstration: Chunking and Normalizing Text Data 6 minutes

5 readings Total 85 minutes

Welcome to RAG Systems in Practice 10 minutes
Overview of Retrieval-Augmented Generation Systems 20 minutes
Text Embeddings and Semantic Search Fundamentals 20 minutes
Document Preprocessing Techniques for RAG Systems 20 minutes
Module Summary: Introduction to Retrieval Systems 15 minutes

4 assignments Total 48 minutes

Knowledge Check: Introduction to Retrieval Systems 30 minutes
Practice Knowledge Check: Understanding Retrieval-Augmented Generation (RAG) 6 minutes
Practice Knowledge Check: Embeddings and Vector Stores 6 minutes
Practice Knowledge Check: Preprocessing for Effective Retrieval 6 minutes

1 discussion prompt Total 10 minutes

Introduce Yourself 10 minutes

Learners will focus on building and optimizing RAG pipelines using LangChain. They will explore techniques like hybrid retrieval, re-ranking, and grounding to improve context accuracy. The module includes practical applications for creating, testing, and evaluating high-performance RAG workflows.

What's included

16 videos5 readings5 assignments

16 videos Total 96 minutes

Retrieval Pipelines in RAG Systems 6 minutes
Connecting Vector Stores to LLMs 6 minutes
Demonstration: Creating a Retriever Chain with LangChain 4 minutes
Demonstration: Query Testing and Context Ranking 7 minutes
Hybrid Retrieval and Re-Ranking in RAG 6 minutes
Re-Ranking with Cross-Encoder and BM25 7 minutes
Demonstration: Combining Dense and Sparse Retrieval 6 minutes
Demonstration: Evaluating Retrieval Precision 6 minutes
Hallucinations as a Retrieval Problem 6 minutes
Context Window Management 5 minutes
Demonstration: Reducing Hallucinations via Grounded Context 7 minutes
Demonstration: Adding Citation References in RAG Output 6 minutes
Introduction to LangGraph 5 minutes
Demonstration: Building a Stateful RAG Graph with LangGraph 7 minutes
Demonstration: Decision-Driven RAG Orchestration with LangGraph - I 6 minutes
Demonstration: Decision-Driven RAG Orchestration with LangGraph - II 6 minutes

5 readings Total 120 minutes

Building Retrieval Pipelines with LangChain and FAISS 45 minutes
Hybrid Search Techniques for Context Accuracy 20 minutes
Improving Context Relevance and Grounding in RAG 20 minutes
Designing Graph-Based LLM Workflows with LangGraph 20 minutes
Module Summary : Building and Optimizing RAG Pipelines 15 minutes

5 assignments Total 54 minutes

Knowledge Check: Building and Optimizing RAG Pipelines 30 minutes
Practice Knowledge Check: Retrieval Pipelines in LangChain 6 minutes
Practice Knowledge Check: Hybrid and Re-Ranking Techniques 6 minutes
Practice Knowledge Check: Enhancing Context Quality 6 minutes
Practice Knowledge Check: Orchestrating RAG Workflows with LangGraph 6 minutes

This module covers the deployment and evaluation of RAG systems in real-world applications. Learners will explore deployment strategies, API integration, and performance monitoring. They will also learn how to optimize RAG systems for scalability and efficiency in production environments.

What's included

19 videos5 readings4 assignments

19 videos Total 100 minutes

RAG System Deployment in Production 5 minutes
Optimized End-to-End RAG Pipeline and System Design 6 minutes
Demonstration: Deploying RAG App with Streamlit : RAG Core - Retrieval Setup 7 minutes
Demonstration: Deploying RAG App with Streamlit : RAG Core - Question Answering 3 minutes
Demonstration: Deploying RAG App with Streamlit : Data and Authentication 6 minutes
Demonstration: Deploying RAG App with Streamlit : Ingestion and Prompt Design 5 minutes
Demonstration: Deploying RAG App with Streamlit : Context Retrieval and Utils 4 minutes
Demonstration: Deploying RAG App with Streamlit : Deployment 5 minutes
Demonstration: Integrating API Endpoints for Retrieval-I 7 minutes
Demonstration: Integrating API Endpoints for Retrieval-II 6 minutes
Evaluating RAG System Performance 5 minutes
Benchmarking RAG Performance 3 minutes
Demonstration: Using LangSmith or LlamaIndex for Local Evaluation 6 minutes
Demonstration: Analyzing Cost and Latency Metrics 6 minutes
Accuracy vs Scalability in RAG 4 minutes
Enhancing Query Understanding and Ranking 4 minutes
Demonstration: Implementing Hybrid Retrieval at Scale 6 minutes
Demonstration: Optimizing Latency and Throughput for RAG Systems 6 minutes
Production-Ready RAG System Architecture 5 minutes

5 readings Total 105 minutes

Deploying Retrieval-Augmented Generation Applications 20 minutes
Evaluating RAG Pipelines: Metrics and Observability Tools 20 minutes
Scaling RAG Systems for High-Performance Applications 20 minutes
Module Summary : Deploying and Evaluating RAG Systems 15 minutes
A Practical Guide to Building Scalable LLM Applications 30 minutes

4 assignments Total 48 minutes

Knowledge Check: Deploying and Evaluating RAG Systems 30 minutes
Practice Knowledge Check: RAG Deployment Fundamentals 6 minutes
Practice Knowledge Check: Monitoring and Evaluation 6 minutes
Practice Knowledge Check: Retrieval Accuracy and Scalability 6 minutes

In the final module, learners will apply their knowledge by completing a practice project and final assessment. They will review key concepts and build a production-ready RAG system, preparing them to implement RAG in real-world projects.