Develop generative AI apps in Azure (AI-3016) Course

Course Code: M-AI3016

‍

Duration: 1 day

‍

Course Overview

Generative artificial intelligence is becoming more accessible through development platforms such as Azure AI Foundry. This course teaches you how to build generative AI applications, including custom copilots that use language models and prompt flow to provide value to users.

You will explore the complete development process, from planning an Azure AI solution and deploying a model to building applications with the Azure AI Foundry SDK, retrieval-augmented generation (RAG), fine-tuning, responsible AI and performance evaluation.

‍

Target Audience

This course is intended for AI engineers, data scientists, developers and other technical professionals who understand AI fundamentals and want to create generative AI applications or custom copilots using Azure AI Foundry.

‍

Course Objectives

By the end of the course, you will be able to:

• Plan and prepare to develop AI solutions on Azure
• Choose and deploy models from the model catalogue in Azure AI Foundry
• Develop an AI application with the Azure AI Foundry SDK
• Use prompt flow to develop language-model applications
• Develop a RAG-based solution using your own data
• Fine-tune a language model with Azure AI Foundry
• Implement a responsible generative AI solution
• Evaluate generative AI performance in Azure AI Foundry

‍

Course Content

Module 1: Plan and prepare to develop AI solutions on Azure

• What is AI?
• Azure AI services
• Azure AI Foundry
• Developer tools and SDKs
• Responsible AI
• Exercise: Prepare for an AI development project

Module 2: Choose and deploy models from the model catalogue in Azure AI Foundry

• Explore the model catalogue
• Deploy a model to an endpoint
• Optimise model performance
• Exercise: Explore, deploy and chat with language models

Module 3: Develop an AI application with the Azure AI Foundry SDK

• What is the Azure AI Foundry SDK?
• Work with project connections
• Create a chat client
• Exercise: Create a generative AI chat application

Module 4: Get started with prompt flow

• Understand the development lifecycle of a large language model application
• Understand core components and explore flow types
• Explore connections and runtimes
• Explore variants and monitoring options
• Exercise: Get started with prompt flow

Module 5: Develop a RAG-based solution with your own data

• Understand how to ground your language model
• Make your data searchable
• Create a RAG-based client application
• Implement RAG in a prompt flow
• Exercise: Create a generative AI application that uses your own data

Module 6: Fine-tune a language model with Azure AI Foundry

• Understand when to fine-tune a language model
• Prepare data to fine-tune a chat completion model
• Explore fine-tuning in the Azure AI Foundry portal
• Exercise: Fine-tune a language model

Module 7: Implement a responsible generative AI solution

• Plan a responsible generative AI solution
• Map and measure potential harms
• Mitigate potential harms
• Manage a responsible generative AI solution
• Exercise: Apply content filters to prevent harmful output

Module 8: Evaluate generative AI performance

• Assess model performance
• Manually evaluate model performance
• Use automated evaluations
• Exercise: Evaluate generative AI model performance

‍

Further Information

This course is delivered via our training partner Skillsoft Global Knowledge.

‍

‍