Develop generative AI apps in Azure (AI-3016)

 

Course Overview

Learn how to develop generative AI apps in Microsoft Foundry

Prerequisites

Before starting this module, you should be familiar with fundamental AI concepts and services in Azure. Consider completing the Get started with artificial intelligence learning path first.

Course Content

Plan and prepare to develop AI solutions on Azure

  • Introduction
  • What is AI?
  • Microsoft Foundry
  • Foundry Tools
  • Developer tools and SDKs
  • Responsible AI
  • Exercise - Prepare for an AI development project
  • Module assessment
  • Summary

Select, deploy, and evaluate Microsoft Foundry models

  • Introduction
  • Explore the model catalog
  • Select models using benchmarks
  • Deploy models to endpoints
  • Evaluate model performance
  • Exercise - Select, deploy, and evaluate models
  • Knowledge check
  • Summary

Develop a generative AI chat app with Microsoft Foundry

  • Introduction
  • Explore with the model playground
  • Choose an endpoint and SDK
  • Generate responses with the Responses API
  • Generate responses with the ChatCompletions API
  • Exercise - Create a generative AI chat app
  • Knowledge check
  • Summary

Develop generative AI apps that use tools

  • Introduction
  • What are tools?
  • Use the code_interpreter tool
  • Use the web_search tool
  • Use the file_search tool
  • Use the function tool
  • Exercise - Create a generative AI chat app that uses tools
  • Module assessment
  • Summary

Optimize generative AI model performance with Microsoft Foundry

  • Introduction
  • Optimize model output with prompt engineering
  • Ground your model with Retrieval Augmented Generation
  • Fine-tune a model for consistent behavior
  • Compare and combine optimization strategies
  • Exercise - Optimize generative AI model performance
  • Module assessment
  • Summary

Implement a responsible generative AI solution in Microsoft Foundry

  • Introduction
  • Plan a responsible generative AI solution
  • Map potential harms
  • Measure potential harms
  • Mitigate potential harms
  • Manage a responsible generative AI solution
  • Exercise - Apply guardrails to prevent the output of harmful content
  • Module assessment
  • Summary

Click on town name or "Online Training" to book Agenda

Instructor-led Online Training:   This is an Instructor-Led Online (ILO) course. These sessions are conducted via Microsoft Teams in a VoIP environment and require an Internet Connection and headset with microphone connected to your computer or laptop.
This is a FLEX course, which is delivered both virtually and in the classroom.

North America

Estados Unidos

Treinamento online Fuso horário: Central Daylight Time (CDT) Língua do curso: Inglês
Treinamento online Fuso horário: Pacific Daylight Time (PDT) Língua do curso: Inglês
Treinamento online Fuso horário: Central Standard Time (CST) Língua do curso: Inglês
Treinamento online Fuso horário: Eastern Standard Time (EST) Língua do curso: Inglês

Canadá

Treinamento online Fuso horário: Central Daylight Time (CDT) Língua do curso: Inglês
Treinamento online Fuso horário: Pacific Daylight Time (PDT) Língua do curso: Inglês
Treinamento online Fuso horário: Central Standard Time (CST) Língua do curso: Inglês
Treinamento online Fuso horário: Eastern Standard Time (EST) Língua do curso: Inglês

Europa

Alemanha

Hamburgo
Berlim
Hamburgo
Berlim
Frankfurt
Hamburgo
Munich

França

Treinamento online Fuso horário: Central European Summer Time (CEST) Língua do curso: Français
Treinamento online Fuso horário: Central European Time (CET) Língua do curso: Français

Holanda

Utrecht

Polónia

Warszawa
Warszawa

Reino Unido

Treinamento online Fuso horário: British Summer Time (BST) Língua do curso: Inglês
Treinamento online Fuso horário: Greenwich Mean Time (GMT) Língua do curso: Inglês

Suíça

Treinamento online Fuso horário: Central European Time (CET) Língua do curso: German

itália

Treinamento online Fuso horário: Central European Summer Time (CEST) Língua do curso: Italiano

Oriente Médio

Emirados Árabes

Dubai
Dubai