Artificial Intelligence
Generative AI & LLM Engineering
Build real products on top of large language models.
Generative AI — Advance
RAG, embeddings, vector databases, agents and tool use — the LLM application stack.
60 study hours
430 pages
11 modules
PDF ebook
What is inside
01
Embeddings and semantic search
02
Vector databases: pgvector, Qdrant, Pinecone
03
Retrieval-augmented generation end to end
04
Chunking, reranking and retrieval quality
05
Function calling and tool use
06
Building agents that take real actions
07
Structured output and JSON reliability
08
Streaming, latency and user experience
09
Multimodal: images, documents and audio
10
Speech to text and text to speech pipelines
11
Evaluating an LLM application
By the end you can
- Build a RAG system over your own documents
- Ship an AI assistant that uses tools safely
- Measure and improve LLM application quality