RAG (Retrieval-Augmented Generation) is an emerging paradigm in AI that combines the strengths of retrieval systems and generative models to deliver context-aware, highly relevant responses.

By leveraging FastAPI and Langchain, a modular tools for interacting with language models and knowledge sources, you’ll learn how to create an AI assistant application for a shop. We will see how to use hexagonal architecture to reduce costs and uncertainty during development.

Whether you’re a developer aiming to expand your AI toolkit or a data enthusiast exploring RAG, the aims to provide you with the knowledge and skills to design and deploy intelligent, context-driven applications.