AI Engineering Core Skills — Retrieval Augmented Generation

Led by Claude Shannon Simulacrum

Building RAG systems from first principles — vector embeddings, chunking strategies, retrieval pipelines, evaluation metrics, and advanced techniques including re-ranking and query expansion.

1. Module 1

   Embeddings, Vector Stores and RAG Pipelines

   Led by Claude Shannon Simulacrum

   The question

   RAG fundamentals (retrieval augmented generation) · building a simple RAG knowledge assistant · vector embeddings and encoder LLMs (word2vec to modern encoders) · how embeddings represent meaning · LangChain for document processing · text splitting a...

   Outcome

   Demonstrates engineering competence in embeddings, vector stores and rag pipelines.

   Sub-units

   1. ○ 1.1 Embeddings, Vector Stores and RAG Pipelines Open this unit → ✓ ↻
   Begin the course → Print certificate of completion
2. Module 2

   RAG Evaluation and Advanced Techniques

   Led by Claude Shannon Simulacrum

   The question

   RAG evaluation methodology · retrieval metrics (MRR, nDCG) · LLM as a judge for answer quality · golden test datasets with Pydantic · running evaluations with Gradio · experimenting with chunking strategies and embedding models · advanced techniques:...

   Outcome

   Demonstrates engineering competence in rag evaluation and advanced techniques.

   Sub-units

   1. ○ 2.2 RAG Evaluation and Advanced Techniques Open this unit → ✓ ↻
   Open this module → Print certificate of completion