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

What is RAG?The Problem RAG SolvesRAG vs. Fine-Tuning vs. Prompt EngineeringRAG Architecture Deep Dive

2. Document Processing and Chunking

Introduction to Document ProcessingLangChain Document LoadersText Splitting StrategiesProduct Quantization: Compressing VectorsChunking Best PracticesMetadata ManagementHands-on Document Processing Pipeline

3. Embeddings and Vector Representations

How Embeddings Work — Vector Representation of TextEmbedding Models ComparedUsing the MTEB LeaderboardImplementing Embeddings with LangChainDimensionality and Storage Trade-offs

4. Vector Stores

Introduction to Vector StoresChroma — Getting StartedFAISS — Facebook AI Similarity SearchQdrant and Pinecone for ProductionVector Store CRUD OperationsHands-On: Building a Vector Store Application

5. Basic Retrieval Techniques

Similarity Search FundamentalsSimilarity Score ThresholdsMaximum Marginal Relevance (MMR)Hybrid Search with BM25 and EnsembleRetrieverHands-On: Building a Basic RAG Pipeline

6. Advanced Retrieval Techniques

Contextual CompressionParent Document RetrieverSelf-Query RetrieverMulti-Query RetrieverCross-Encoder Re-Ranking

7. Advanced RAG Patterns

RAG Fusion — Multi-Query FusionHyDE — Hypothetical Document EmbeddingsCorrective RAG (CRAG)Self-RAG — Self-Reflective RetrievalGraph RAG with Neo4jHands-On: Choosing the Right RAG Pattern

8. Agentic RAG with LangGraph

From RAG to Agentic RAGCreating Retriever Tools with LangGraphReAct Agent with RetrievalPlan-and-Execute RAG AgentsHands-On: Building a Self-Correcting RAG Agent

9. Evaluating RAG with RAGAS

Introduction to RAG EvaluationRAGAS Framework and MetricsCreating Evaluation DatasetsRunning and Interpreting RAGAS MetricsIterative Improvement with Evaluation Feedback

10. Capstone Project with Deployment

Capstone Overview and Architecture DesignBuilding the Multi-Document Ingestion LayerImplementing Hybrid Retrieval with Re-RankingBuilding the Agentic RAG Workflow with LangGraphEvaluation, Monitoring, and OptimizationDeployment and Security Best Practices
Start learning