Building your AI Workflow | How to combine LLM and embeddings for GenAI
Apr 15, 2026 | 10:40 AM - 12:20 PM
Apr 15, 2026 | 10:40 AM - 12:20 PM
Description
In this hands-on training, you will learn the basics of how to build production GenAI systems by combining Large Language Models with retrieval technologies. You'll learn what LLMs are and how they function, then explore the technologies required for robust AI applications: embeddings for semantic representation, distance metrics, and vector databases for efficient search. In the second part of this training, you’ll learn how to design and build a Retrieval-Augmented Generation (RAG) pipeline for more accurate AI responses grounded in your own data. We’ll also explore different chunking strategies that determine RAG system performance.
Level: Beginner-friendly, no prior AI or machine learning experience required. Basic knowledge of Python is helpful.
