Skip to main content

Syllabus: RAG and Optimization

1. Header Information

FieldValue
Technical Group?
Topic NameRAG and Optimization
Topic Code?
Version1.0
Training AudienceFreshers

2. Course Objectives

[!NOTE] This topic introduces advanced techniques and optimizations for Retrieval-Augmented Generation (RAG) systems; adapting trainees with skills, lessons, and practices specific to AI applications, enterprise vector search, and GraphRAG knowledge bases.

Output Standards table

NameCodeDescription
Advanced Indexing?Understand Semantic Chunking vs Recursive Chunking and optimize Vector DBs using HNSW.
Hybrid Search?Combine traditional BM25 keyword search with Vector Search using Reciprocal Rank Fusion (RRF).
Query Transformation?Utilize LLM capabilities for HyDE and Query Decomposition to augment queries before retrieval.
Post-Retrieval Processing?Filter and re-rank search results using Cross-Encoder models and Maximal Marginal Relevance (MMR).
GraphRAG Implementation?Build sophisticated hybrid RAG architectures leveraging Knowledge Graphs and Neo4j.

Detailed Learning Outcomes (LOs)

  • ? LO1 - Able to comprehend and apply Semantic Chunking vs Recursive Chunking.
  • ? LO2 - Able to optimize vector databases using the HNSW Index (M, ef_construction, ef_search).
  • ? LO3 - Able to leverage the BM25 algorithm alongside Vector Search.
  • ? LO4 - Able to merge multi-search results using Reciprocal Rank Fusion (RRF).
  • ? LO5 - Able to implement Hypothetical Document Embeddings (HyDE).
  • ? LO6 - Able to perform Query Decomposition for complex multi-intent queries.
  • ? LO7 - Able to utilize Cross-Encoder for enhanced Re-ranking vs Bi-Encoder approaches.
  • ? LO8 - Able to apply Maximal Marginal Relevance (MMR) for diverse retrieval.
  • ? LO9 - Able to design Neo4j graph schemas, extract entities, and maintain a knowledge graph.
  • ? LO10 - Able to execute Graph Cypher QA Chains with Neo4j.

3. Topic Outline

  • Unit 01: Advanced Indexing
  • Unit 02: Hybrid Search
  • Unit 03: Query Transformation
  • Unit 04: Post-Retrieval Processing
  • Unit 05: GraphRAG Implementation

4. Time Allocation

Activity TypePercentageDescription
Concept/Lecture40%Concepts, theory (4 Sessions)
Assignment/Lab40%Assignment, Lab
Guides/Review10%Self review/Cross review
Exam10%Pre-Test, Final Topic Test

5. Training Materials & Environments

Textbooks

References

Technical Requirements

  • Python 3.10+
  • LangChain, LangGraph
  • Neo4j Database
  • IDE (VSCode / PyCharm)

6. Assessment Scheme

ComponentQuantityWeight (%)Note
Quiz520%In-class labs
Assignments230%In-class labs
Final Practice Test150%Comprehensive project

Pass Criteria

  • Total topic GPA >= 7.0/10
  • Completed 100% Online video, Quiz, Assignments, Labs, Final Test
  • Succesful demo of the Final Project (RAG system with advance function)

7. Training Delivery Principles

RoleResponsibility/Criteria
TraineesMust be familiar with basic RAG.
TrainerCertified AI Engineer or higher.
TrainingDaily offline training and labs.
Re-TestAllowed 1 time for Failed status.
MarkingDirect grading of Practice tests.
Waiver CriteriaEquivalent industry certificates.
OthersNeed personal laptop for labs.