Ready to build production-grade AI? This program equips developers to deploy reliable generative AI solutions. We'll move past theory and focus on the proven implementation patterns you need. You'll master production essentials like model selection, cost estimation, and reliable prompt engineering to build efficient apps. You'll also implement lightweight model adaptation using PEFT. Then, you'll build end-to-end RAG systems, using vector databases to connect LLMs to your data and evaluate quality with frameworks like RAGAs. Finally, you'll dive into advanced multimodal applications that process text, images, and audio. You'll enforce structured outputs with Pydantic and implement system observability to build, trace, and debug modern AI apps.
Overview
Syllabus
- Generative AI Fundamentals
- Employ the abilities of Generative AI with a deep dive into fundamentals. This course examines how various models are developed, how they work, and how to use them to their full potential.
- Large Language Models (LLMs) and Retrieval Augmented Generation (RAG)
- Master Large Language Models (LLMs) and build sophisticated text generation applications in this hands-on course. You’ll master prompt engineering techniques, optimize model selection and costs, and dive deep into Retrieval-Augmented Generation (RAG), using vector databases to ground AI responses in external data and eliminate hallucinations. Finally, you’ll evaluate system performance with RAGAS and showcase your skills by building an end-to-end RAG application.
- Multimodal AI Applications
- Learn how computers process and understand image data, then harness the power of the latest Generative AI models to create new images.
Taught by
Brian Cruz, Eduardo Mota and Giacomo Vianello