COURSE 09Intermediate9 IN-DEPTH LESSONS

RAG, Search and Knowledge Systems

Building reliable knowledge-grounded systems: document chunking, dense embeddings, hybrid BM25 search, rerankers, citations, and graph RAG.

Start Lesson 1: RAG (retrieval-augmented generation) →← All 29 Courses

Course Syllabus & Units

Unit 1

Rag

1 lessons
1.1L1

RAG (retrieval-augmented generation)

**RAG** means: before (or while) generating an answer, the system **retrieves** relevant documents and feeds them into the prompt so the model can ground replies in those sources.

Read lesson →
Unit 2

Chunking

1 lessons
2.1L1

Chunking and embeddings for RAG

**Chunking** splits documents into pieces a retriever can fetch. **Embeddings** turn those pieces into vectors so “similar meaning” search can work.

Read lesson →
Unit 3

Grounding

1 lessons
3.1L1

Citations and groundedness

**Groundedness** means the answer sticks to retrieved sources. **Citations** show which chunks support which claims so a human can verify.

Read lesson →
Unit 4

Retrieval

2 lessons
4.1L1

Hybrid search

**Hybrid search** mixes keyword search (exact terms, IDs, jargon) with vector/semantic search (paraphrases, meaning). A merger or re-ranker blends the lists.

Read lesson →
4.2L1

Rerankers

A **reranker** takes a first-pass retrieval list and reorders it with a stronger (often slower) model so the generator sees better chunks.

Read lesson →
Unit 5

Eval

1 lessons
5.1L1

Evaluating RAG systems

How to measure RAG: retrieval quality, answer faithfulness, citation correctness, latency, and cost—not vibes.

Read lesson →
Unit 6

Graphs

1 lessons
6.1L1

Knowledge graphs and RAG

Combining **knowledge graphs** (entities + relations) with RAG so retrieval can follow structured links—not only vector similarity.

Read lesson →
Unit 7

Security

1 lessons
7.1L1

Access control in retrieval

Ensuring RAG only retrieves documents the **current user is allowed to see**.

Read lesson →
Unit 8

Ops

1 lessons
8.1L1

RAG freshness and reindexing

Keeping retrieval indexes up to date when docs change—schedules, incremental updates, and tombstones for deletes.

Read lesson →