Manasseh Komla
Getting Started with Retrieval-Augmented Generation (RAG) in Python
Large Language Models are powerful, but concerns about data privacy and security can limit their use, and they can also generate inaccurate or fabricated information. Retrieval-Augmented Generation (RAG) addresses these challenges by enabling models to retrieve relevant information from external knowledge sources before generating responses.
In this hands-on session, participants will learn how to build a complete RAG application using Python. Starting from the fundamentals, we will explore document loading, text chunking, embeddings, vector databases, semantic search, retrieval, and response generation with modern LLMs. Participants will also learn how these components work together to create intelligent AI assistants capable of answering questions from custom documents.
By the end of the session, participants will understand the architecture of RAG systems, know when to use them, and have the skills to build their own document-aware AI applications using Python.