← Back to Academy

This course is free. Create a free account to learn, save your progress, and earn a certificate when you complete it.

RAG Systems for Developers

Free

Learn how to build retrieval-augmented generation systems that work reliably in production. This course covers every component of a RAG pipeline: document ingestion and chunking, embedding models and vector stores, retrieval design with hybrid search and reranking, context assembly and generation prompting, retrieval evaluation and quality measurement, and production observability and cost optimization. This course assumes familiarity with Python and calling LLM APIs. No ML background or prior RAG experience required.

No payment or subscription required. Sign in to track your learning and claim your certificate when you finish.

Bookmark
Loading…

Complete lessons in order to unlock the next — structured progression.

What RAG Is and How It Works

Understand the problem RAG solves, when to use it versus fine-tuning or long context, and how the five core components of a RAG system fit together.

  1. 1What Is Rag And Why Does It MatterTutorial
  2. 2Rag System Architecture: The Five ComponentsTutorial
  3. 3Rag Foundations CheckQuiz

Document Ingestion and Chunking

Build a production-quality ingestion pipeline. Learn how to load different document types, clean and normalize text, preserve metadata, and apply the right chunking strategy for your content.

  1. 4Document Ingestion And PreprocessingTutorial
  2. 5Chunking Strategies For Effective RetrievalTutorial
  3. 6Embedding Models, Vector Stores, And IndexingTutorial
  4. 7Document Ingestion And Chunking CheckQuiz

Retrieval Design

Design a retrieval layer that finds the right chunks reliably. Learn vector search mechanics, hybrid search with BM25, reranking, retrieval evaluation metrics, and how to measure whether your retrieval is working.

  1. 8Vector Search FundamentalsTutorial
  2. 9Hybrid Search And RerankingTutorial
  3. 10Evaluating Retrieval QualityTutorial
  4. 11Retrieval Design CheckQuiz

Context Assembly and Generation

Assemble retrieved chunks into effective prompts. Learn context structure, chunk ordering, deduplication, handling missing or conflicting context, and the advanced RAG patterns that address hard retrieval cases.

  1. 12Context Assembly And Rag Prompt DesignTutorial
  2. 13Handling Rag Failures And Hard CasesTutorial
  3. 14Advanced Rag PatternsTutorial
  4. 15Context Assembly And Generation CheckQuiz

Production RAG: Observability, Cost, and Capstone

Operate a RAG system in production. Learn what to log and trace for every query, how to measure end-to-end quality with RAGAS, how to optimize token cost and latency, and complete the capstone project.

  1. 16Observability And End To End Evaluation For RagTutorial
  2. 17Optimizing Rag For Cost And LatencyTutorial
  3. 18Rag Systems For Developers: Capstone ProjectTutorial
  4. 19Production Rag CheckQuiz

Discussion

  • Loading…

← Back to Academy