Generative AI & LLM Engineering
-
Week 1: How LLMs work
-
Tokens, embeddings, context windows
-
Using OpenAI API
-
Week 2: Building chatbots with memory
-
Vector databases and retrieval
-
RAG (Retrieval Augmented Generation)
-
Week 3: Fine-tuning concepts
-
Guardrails and safety
-
Multi-modal AI apps
-
Week 4: Deploying AI apps
-
Cost optimization
-
Capstone: build a domain chatbot
