Coursera
Introduction to Retrieval Augmented Generation (RAG)
What this course answers
A three-hour beginner course on retrieval-augmented generation. It explains what large language models can automate, how language embeddings are stored in vector databases, and how to build RAG applications with the LangChain framework through real-world projects. More than 6,600 learners have enrolled, and Coursera issues a shareable certificate.
Last verified25 Sep 2026
What you will be able to do
- Demonstrate what large language models can automate with natural language
- Identify the range of problems RAG applications can solve
- Use vector databases to store language embeddings
- Develop RAG applications with LLM frameworks, models and vector databases
Curriculum
Prerequisites
- Basic Python programming
- Foundational knowledge of large language models