Generative Artificial Intelligence (AI) is becoming more accessible through easy-to-use platforms like Azure AI Foundry. Learn how to build generative AI applications that use language models with prompt flow to provide value to your users.

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.

Modules in this learning path

Plan and prepare to develop AI solutions on Azure

Microsoft Azure offers multiple services that enable developers to build amazing AI-powered solutions. Proper planning and preparation involves identifying the services you'll use and creating an optimal working environment for your development team.

• Introduction
• What is AI?
• Azure AI services
• Azure AI Foundry
• Developer tools and SDKs
• Responsible AI
• Exercise - Explore the Azure AI Foundry portal
• Knowledge check
• Summary

Explore and deploy models from the model catalog in Azure AI Foundry portal

Explore the various language models that are available through the Azure AI Foundry's model catalog. Understand how to select, deploy, and test a model, and to improve its performance.

• Introduction
• Explore the language models in the model catalog
• Deploy a model to an endpoint
• Improve the performance of a language model
• Exercise - Explore, deploy, and chat with language models
• Knowledge check
• Summary

Develop an AI app with the Azure AI Foundry SDK

Use the Azure AI Foundry SDK to develop AI applications with Azure AI Foundry projects.

• Introduction
• What is the Azure AI Foundry SDK?
• Work with project connections
• Create a chat client
• Exercise - Create a generative AI chat app
• Knowledge check
• Summary

Get started with prompt flow to develop language model apps in the Azure AI Foundry

Learn about how to use prompt flow to develop applications that leverage language models in the Azure AI Foundry.

• Introduction
• Understand the development lifecycle of a large language model (LLM) app
• Understand core components and explore flow types
• Explore connections and runtimes
• Explore variants and monitoring options
• Exercise - Get started with prompt flow
• Knowledge check
• Summary

Build a RAG-based agent with your own data using Azure AI Foundry

Agents can work alongside you to provide suggestions, generate content, or help you make decisions. Agents use language models as a form of generative artificial intelligence (AI) and will answer your questions using the data they were trained on. To ensure an agent retrieves information from a specific source, you can add your own data when building an agent with the Azure AI Foundry.

• Introduction
• Understand how to ground your language model
• Make your data searchable
• Build an agent with prompt flow
• Exercise - Create a custom agent that uses your own data
• Knowledge check
• Summary

Fine-tune a language model with Azure AI Foundry

Train a base language model on a chat-completion task. The model catalog in Azure AI Foundry offers many open-source models that can be fine-tuned for your specific model behavior needs.

• Introduction
• Understand when to fine-tune a language model
• Prepare your data to fine-tune a chat completion model
• Explore fine-tuning language models in Azure AI Studio
• Exercise - Fine-tune a foundation model
• Knowledge check
• Summary

Evaluate the performance of generative AI apps with Azure AI Foundry

Evaluating copilots is essential to ensure your generative AI applications meet user needs, provide accurate responses, and continuously improve over time. Discover how to assess and optimize the performance of your generative AI applications using the tools and features available in the Azure AI Studio.

• Introduction
• Assess the model performance
• Manually evaluate the performance of a model
• Assess the performance of your generative AI apps
• Exercise - Evaluate the performance of your generative AI app
• Knowledge check
• Summary

Responsible generative AI

Generative AI enables amazing creative solutions, but must be implemented responsibly to minimize the risk of harmful content generation.

• Introduction
• Plan a responsible generative AI solution
• Identify potential harms
• Measure potential harms
• Mitigate potential harms
• Operate a responsible generative AI solution
• Exercise - Explore content filters in Azure AI Studio
• Knowledge check
• Summary