RAG : Construire des applications avec LangChain et LlamaIndex

Aperçu

Retrieval-Augmented Generation (RAG) is rapidly becoming a core skill for Data Scientists, AI Engineers, and Software Developers, with competitive salaries reflecting its demand. In this course, you’ll start by learning how RAG improves information retrieval, context accuracy, and user interactions.

You’ll build your first retrieval pipeline and experiment with document splitting, embedding, and retrieval workflows using Python. You’ll design user-facing GenAI applications with Gradio, creating clean, interactive interfaces that connect your retrieval pipeline to real-time user queries.

Through guided labs, you’ll transform project ideas into a working QA system capable of answering questions from loaded documents. You’ll explore LlamaIndex as an alternative RAG framework, examining its structure, strengths, and differences compared with LangChain.

By completing hands-on labs, you’ll build a full RAG application using both frameworks, gaining a practical understanding of when each tool is most effective. By the end of this course, you’ll have the experience needed to design, implement, evaluate, and deploy end-to-end RAG applications that power context-aware AI solutions.

Programme

---

Matières

Artificial Intelligence