Beginner’s Guide to RAG Micro-Credential

Beginner’s Guide to RAG Micro-Credential

Duration: 3-4 Hours

Description

Large language models are frozen at their training cutoff and know nothing about your internal documents — RAG is the fix, and this session builds one end to end so the concept stops being abstract. Participants generate embeddings from real text, load them into a vector store, and wire the retrieval and generation steps together into a working pipeline, including a look at connecting a retrieval source through the Model Context Protocol (MCP), the emerging standard for linking AI systems to external data. The labs also cover the part most tutorials skip: what a RAG system looks like when it’s quietly failing — retrieving the wrong context, or the right context in the wrong order — and the basic checks that catch it.

Audience

This session assumes basic programming knowledge but no prior RAG or vector database experience — it’s built as a true starting point. It’s aimed at developers and data scientists who need to connect a language model to their own data (internal docs, a knowledge base, a product catalog) and want the fundamentals before reaching for a higher-level framework that hides how the pieces fit together.

Objectives

  • Understand the core components and a simple workflow of a RAG system
  • Build a complete, functional RAG pipeline from a knowledge base
  • Identify and address basic issues in a RAG system
  • Use a RAG system to answer questions based on custom data

Prerequisites

Developers with basic Python proficiency who are new to the concept of Retrieval-Augmented Generation (RAG) are perfect for this micro-credential. This course assumes some familiarity with Large Language Models (LLMs), but no prior experience with information retrieval or vector databases is required.

Related AI Courses

See the full AI training roadmap and course directory for how this fits into a broader learning path.

Ready to go beyond the basics? See Advanced RAG Micro-Credential, or the full RAG Deep Dive course. For the vector search foundation underneath RAG, see Introduction to Vector Databases for Developers Micro-Credential or Vector Databases and Semantic Search.

Course Outline

Module 1: The RAG Fundamentals

  • Introduction to RAG
  • RAG vs. Fine-Tuning
  • The Core Components (Loader/Chunker, Retriever, and Generator)
  • Lab – Loading and Chunking a Simple Text Document

Module 2: Building Your First RAG Pipeline

  • Create Embeddings
  • Setting Up the Vector Store
  • Connecting External Data Sources with MCP
  • Lab – Building a Functional RAG Application

Module 3: Troubleshooting and Best Practices

  • Basic Evaluation
  • Common Pitfalls
  • Improving the System
  • Exploring Frameworks