← Back to curriculum

Module 7 — GenAI & LLMs

Welcome to Module 7

Enter modern GenAI: how LLM apps work, what you will build, and prerequisites from Module 6.

~25 min read + exercises

Welcome to Module 7 — GenAI & LLMs

Before we begin

Module 6 taught how transformers work. Module 7 teaches how people use them in products — lifecycle, fine-tuning, RAG engineering, automated workflows, and trust.

You are entering modern AI engineering — not just training models, but shipping assistants that answer from your data.

Figure

Module 7 at a glance

Module 7 — GenAI & LLMs1WelcomeModule 72LLMGPT3Lifecycletrain4Promptssteer5TuneLoRA6Workflowagent7RAGretrieve8Trustsafe9Quizcheck10Projectchat
LLM lifecycle through RAG engineering, quiz, then a hands-on RAG chatbot project.

What Module 7 covers

TopicWhat you will understand
LLM basics & lifecyclePre-training, post-training, inference
Prompt engineeringSystem prompts, examples, structured outputs
Fine-tuning & quantizationLoRA, INT8/GPTQ for business workloads
AI-automated workflowsCoding agents, skills, subagents
RAG engineeringChunking, ingestion, reranking, vector DBs
Trust & safetyHallucinations, guardrails, citations

Key terms (read once)

TermPlain English
SFTSupervised fine-tuning — training on (prompt, ideal answer) pairs
RLHFReinforcement learning from human feedback — tuning model to prefer better answers
LoRALow-rank adaptation — cheap fine-tune that adds small adapter weights
QuantizationStoring weights in fewer bits (e.g. INT8 = 8-bit integers) for faster/cheaper inference
GPTQ / AWQPopular 4-bit quantization methods for running large models on one GPU
RAGRetrieval-augmented generation — fetch relevant docs, then generate an answer
BM25Classic keyword search score — good for exact product codes and names
Hybrid searchCombine keyword (BM25) + meaning (embeddings)
RerankingRe-score top search hits with a slower, more accurate model
HallucinationModel states a confident “fact” that is not true or not in your sources

Before you start

Required: Module 6 or solid transformer/token intuition.

For the project:

  • OpenAI-compatible API key or local model (Ollama)
  • pip install faiss-cpu openai pypdf (adjust to your stack)
  • Next.js already powers this site for the chat UI

Lessons 1–10 are reading. Lesson 11 is the RAG chatbot project.


Ready?

Lesson 1 — LLM basics