AI
AI Foundations: LLMs & RAG
Understand how large language models actually behave, then build a retrieval-augmented assistant over your own documents.
- Level
- Intermediate
- Format
- Online (live)
- Duration
- 6 sessions · 2 per week
- Category
- AI
Description
A grounded introduction to applied AI. We cover what LLMs can and cannot do, how prompting and retrieval work together, and how to build something useful without pretending the model is infallible.
What you will be able to do
- Explain how an LLM turns input into output
- Build a retrieval pipeline over your own documents
- Reduce hallucinations with grounding and citations
- Plan cost, latency and fallback behaviour
Technologies
PythonLLM APIsRAGVector searchOllama
Modules
How LLMs work
- Tokens and context
- Prompting patterns
- Limits and failure modes
Retrieval
- Chunking documents
- Embeddings and search
- Grounding answers
Applications
- Assistants over documents
- Evaluation
- Cost and latency
Best for
- Developers adding AI features
- Students exploring applied AI
Prerequisites
- Comfortable writing code in Python or JavaScript
- Basic API experience
Interested in this course?
Cohorts, schedules and pricing are agreed per group. Send us a short note with your background and what you want to build.
Enquire about this course