Intermediate SML-402 ⏱ 8 weeks 📚 11 topics

RAG From Scratch: Chunking, Embedding, Retrieval, and Evaluation Certification

Build a production-ready Retrieval-Augmented Generation (RAG) system from scratch. Learn chunking strategies, embedding models, vector search, re-ranking, and evaluation. Free intermediate course.

—

Questions

—

Pass Score

—

Time Limit

What You'll Demonstrate

  • Design and implement a complete RAG pipeline from document ingestion to answer generation
  • Choose the right chunking strategy for any document type
  • Set up and query vector databases including ChromaDB, Pinecone, and pgvector
  • Implement hybrid retrieval and cross-encoder re-ranking for better precision
  • Evaluate RAG systems rigorously using RAGAS and custom metrics

Topics Covered by This Exam

1

Why RAG? The Problem with Fine-Tuning for Knowledge

45 minutes

lesson
2

RAG Architecture Overview

60 minutes

lesson
3

Document Ingestion and Parsing

90 minutes

lesson
4

Chunking Strategies That Actually Work

120 minutes

lesson
5

Embedding Models: Choosing the Right One

90 minutes

lesson
6

Vector Databases in Practice

150 minutes

lesson
7

Retrieval: Dense, Sparse, and Hybrid Search

120 minutes

lesson
8

Re-Ranking: Improve Precision After Retrieval

90 minutes

lesson
9

RAG Evaluation: RAGAS and Beyond

120 minutes

lesson
10

Advanced RAG: HyDE, Query Expansion, and Self-RAG

120 minutes

lesson
11

Capstone: Document Q&A System

360 minutes

project

Adaptive Exam Format

🧠

Progressive Difficulty

Questions advance from Easy → Medium → Hard as you proceed through the exam

🎯

Single & Multi Select

Mix of single-answer and multi-answer questions to assess depth of knowledge

🔀

Randomised Bank

Questions are drawn randomly from a larger question bank — no two exams are the same

🏅

Badge & Certificate

Digital badge and printable certificate issued immediately upon passing