Course Description
Short Course | 18 hours | 1.8 CEUs | $2,295
This course provides a hands-on introduction to Retrieval-Augmented Generation (RAG), a method for enhancing large language models (LLMs) by connecting them to real-time and domain-specific data. Students will learn how the RAG workflow moves from user question to response, including embeddings, vector databases, retrieval strategies, and prompt augmentation techniques. Through a structured, multi-session format with hands-on labs, participants will work with tools such as Python, APIs, and vector databases to build, test, and improve RAG pipelines. The course also covers evaluation, grounding with citations, and real-world applications to support accurate, context-aware AI outputs.
AI400 is the first course in the Agentic AI and Retrieval Augmented Generation (RAG) Certificate. To complete the certificate students will also enroll in AI410. Click on each course link for more details and to add to cart.
Course Outline
Module 1: Introduction to RAG
- LLM limitations and why RAG is needed
- RAG vs. fine-tuning vs. keyword search
- RAG pipeline and components
- Vector databases and semantic search
- Tools and use cases
Module 2: Data Pipeline – Ingestion, Chunking, and Metadata
- Data ingestion and parsing
- Cleaning and normalization
- Chunking strategies
- Metadata design and filtering
- End-to-end workflow
Module 3: Retrieval Strategies
- Dense, sparse, and hybrid retrieval
- Retrieval parameters and tuning
- Precision vs. recall
- Metadata design and filtering
- Troubleshooting retrieval issues
Module 4: Augmentation, Prompting, and Grounded Responses
- Prompt augmentation
- Context integration
- Grounding and citations
- Guardrails and testing
Module 5: Evaluating RAG Quality and Performance
- Evaluation metrics (groundedness, faithfulness, precision, recall)
- Evaluation workflows
- Interpreting results
- Performance improvements
Module 6: Real-World Applications and RAG Workflows
- Use cases across industries
- Deployment considerations
- Testing and optimization
- Final build demonstration
Learner Outcomes
- Describe how RAG extends LLM capabilities
- Explain the RAG workflow from query to response
- Prepare and structure data for RAG pipelines
- Apply chunking and metadata techniques to improve retrieval
- Compare dense, sparse, and hybrid retrieval approaches
- Use prompt augmentation to incorporate retrieved context
- Apply grounding and citation techniques in responses
- Evaluate RAG system performance using key metrics
- Test and improve RAG workflows
Prerequisites
- Basic familiarity with Python or completion of Python -Introduction (PYT100)
- General awareness of AI or large language model or completion of Artificial Intelligence and Large Language Models Foundations (AI390)
- No prior experience with RAG required
Duration
18 Hours | 3 Days or 6 NightsEnroll Now - Select a section to enroll in
*Academic Unit eligibility to be determined by college/university in which you are enrolled in a degree seeking program.