AI-3016 Develop generative AI apps in Azure

In this lecture, you’ll learn how to effectively plan and set up the foundation for building generative AI solutions on Microsoft Azure. We’ll walk through the essential Azure AI services, the role of Azure AI Foundry, and how to align your project goals with the right tools and resources. By the end, you’ll understand the prerequisites, workspace setup, and best practices needed to start developing AI applications confidently. This step ensures you are well-prepared for hands-on development in the upcoming labs.

In this lecture, you’ll explore the Azure AI Foundry model catalog, which provides access to a wide range of pre-trained foundation models. We’ll cover how to compare different models, evaluate their strengths, and select the one best suited for your specific use case. You’ll also learn the step-by-step process of deploying models into your Azure environment, preparing them for integration into real-world applications. By the end, you’ll be able to confidently navigate the catalog and deploy models tailored to your project needs

In this hands-on lab, you’ll practice selecting different language models from the Azure AI Foundry model catalog and deploying them to your workspace. You’ll compare their capabilities, performance, and suitability for specific AI tasks. This guided exercise helps you understand not just how to deploy, but also how to evaluate models side by side in a real Azure environment. By completing this lab, you’ll gain practical skills in model selection and deployment that directly apply to real-world AI development.

In this lecture, you’ll learn how to build a real-world AI-powered application using the Azure AI Foundry SDK. We’ll walk through the process of integrating large language models into your app, managing prompts, and handling inputs and outputs efficiently. You’ll also explore how the SDK simplifies development by providing pre-built tools and workflows for generative AI use cases. By the end of this lecture, you’ll be able to create and run your own AI application on Azure with ease

In this hands-on lab, you will apply what you learned about the Azure AI Foundry SDK to build a functional AI application. Step by step, you’ll set up the development environment, connect to Azure resources, and integrate a generative AI model into your app. You’ll also practice testing prompts, handling responses, and validating that the application works as intended. By the end of this lab, you’ll have a working AI app prototype built entirely with the Azure AI Foundry SDK.

In this lecture, you will learn how to build a Retrieval-Augmented Generation (RAG) solution in Azure AI Foundry using your own data. We’ll explore how to connect external data sources, preprocess and index them, and then integrate this data with generative AI models for more context-aware and accurate responses. You’ll understand how RAG enhances traditional large language model (LLM) outputs by grounding them in your enterprise data. By the end, you’ll be able to design AI solutions that are more reliable, customized, and practical for real-world business scenarios.

In this lab, you’ll get hands-on experience with setting up the foundation for a Retrieval-Augmented Generation (RAG) solution in Azure AI Foundry. We’ll focus on preparing your data, uploading it to the platform, and creating a vector index to make your documents searchable. By the end of Part 1, you’ll have the building blocks ready for connecting your custom data to a generative AI model.

In this continuation lab, you’ll integrate the indexed data with a language model to enable context-aware responses. You’ll test and refine queries, evaluate how effectively the model uses your data, and learn best practices for optimizing retrieval performance. By completing Part 2, you’ll have a fully functioning RAG-based application that combines your own data with Azure’s generative AI models for accurate and relevant results.