Free Lesson
Dense Vector Retrieval
30 min
May 12, 2026 7:00 PM
Virtual (Zoom)
In this video
What you'll learn
Introduction to classic RAG
Meet context engineering through the lense of retrieval, RAG, and the LLM application stack
Overview of embeddings and similarity search
Understand the role that different types of LLMs play in a RAG process
Build a RAG application from scratch in Python
Without using any off-the-shelf tools, build a truly Pythonic RAG application
Why this topic matters
To understand context engineering, you must first understand in-context learning. The easiest way to approach this concept for software engineers who are new to data science is through the lens of RAG.
Once you understand the process of RAG, then understanding the historical context of LLMs (including chat and embedding models) is a much simpler task.
You'll learn from
Raul Salles de Padua
Principal AI & ML Engineer @ Rumble
Can Temizyurek
Maintainer, Evalite (>200k downloads/wk)