Coursify

Retrieval-Augmented Generation (RAG) — From Fundamentals to Production-Ready Agentic RAG Systems

Retrieval-Augmented Generation (RAG) — From Fundamentals to Production-Ready Agentic RAG Systems
advanced40+ hours54 sectionsUpdated Jun 15, 2026

A comprehensive, end-to-end course through Retrieval-Augmented Generation — beginning with core concepts and document processing, advancing through embeddings, vector stores, and retrieval techniques, and culminating in agentic RAG systems built with LangGraph and a deployable capstone project.

What you'll learn

  • Understand the RAG architecture and when to use it vs fine-tuning vs prompt engineering
  • Master document processing, chunking strategies, and metadata management
  • Select and implement appropriate embedding models for different use cases
  • Deploy and operate vector stores including Chroma, FAISS, Qdrant, and Pinecone
  • Implement basic and advanced retrieval techniques including hybrid search, MMR, and re-ranking
  • Build advanced RAG patterns: RAG Fusion, HyDE, Corrective RAG, Self-RAG, and Graph RAG
  • Design and implement agentic RAG systems using LangGraph with multi-step reasoning
  • Evaluate RAG pipelines using RAGAS with comprehensive metrics
  • Deploy a production-ready RAG system with monitoring, caching, and optimization

Prerequisites

  • Python fundamentals (functions, classes, async/await)
  • GenAI fundamentals (LLM basics, tokens, prompting)
  • LangChain basics (Chains, LCEL, tool usage)
  • LangGraph basics (StateGraph, nodes, edges, conditional routing)

Course outline

1

RAG Fundamentals and Architecture

0/4
What is RAG?
The Problem RAG Solves
RAG vs. Fine-Tuning vs. Prompt Engineering
RAG Architecture Deep Dive
2

Document Processing and Chunking

0/7
Introduction to Document Processing
LangChain Document Loaders
Text Splitting Strategies
Product Quantization: Compressing Vectors
Chunking Best Practices
Metadata Management
Hands-on Document Processing Pipeline
3

Embeddings and Vector Representations

0/5
How Embeddings Work — Vector Representation of Text
Embedding Models Compared
Using the MTEB Leaderboard
Implementing Embeddings with LangChain
Dimensionality and Storage Trade-offs
4

Vector Stores

0/6
Introduction to Vector Stores
Chroma — Getting Started
FAISS — Facebook AI Similarity Search
Qdrant and Pinecone for Production
Vector Store CRUD Operations
Hands-On: Building a Vector Store Application
5

Basic Retrieval Techniques

0/5
Similarity Search Fundamentals
Similarity Score Thresholds
Maximum Marginal Relevance (MMR)
Hybrid Search with BM25 and EnsembleRetriever
Hands-On: Building a Basic RAG Pipeline
6

Advanced Retrieval Techniques

0/5
Contextual Compression
Parent Document Retriever
Self-Query Retriever
Multi-Query Retriever
Cross-Encoder Re-Ranking
7

Advanced RAG Patterns

0/6
RAG Fusion — Multi-Query Fusion
HyDE — Hypothetical Document Embeddings
Corrective RAG (CRAG)
Self-RAG — Self-Reflective Retrieval
Graph RAG with Neo4j
Hands-On: Choosing the Right RAG Pattern
8

Agentic RAG with LangGraph

0/5
From RAG to Agentic RAG
Creating Retriever Tools with LangGraph
ReAct Agent with Retrieval
Plan-and-Execute RAG Agents
Hands-On: Building a Self-Correcting RAG Agent
9

Evaluating RAG with RAGAS

0/5
Introduction to RAG Evaluation
RAGAS Framework and Metrics
Creating Evaluation Datasets
Running and Interpreting RAGAS Metrics
Iterative Improvement with Evaluation Feedback
10

Capstone Project with Deployment

0/6
Capstone Overview and Architecture Design
Building the Multi-Document Ingestion Layer
Implementing Hybrid Retrieval with Re-Ranking
Building the Agentic RAG Workflow with LangGraph
Evaluation, Monitoring, and Optimization
Deployment and Security Best Practices
Start learning
Retrieval-Augmented Generation (RAG) — From Fundamentals to Production-Ready Agentic RAG Systems | Coursify