Advent of 2024, Day 1 – Microsoft Azure AI – What is Foundry?

This article is originally published at https://tomaztsql.wordpress.com

Microsoft Azure offers multiple services that enable developers to build amazing AI-powered solutions. Azure AI Foundry brings these services together in a single unified experience for AI development on the Azure cloud platform.

Until now, developers needed to work with multiple tools and web portals in a single project. With Azure AI Foundry, these tasks are now simplified and offers same environment for better collaboration.

What can I do with Azure AI Foundry?

Azure AI Foundry enables teams to collaborate efficiently and effectively on AI projects, such as developing generative AI apps that use language models. Tasks you can accomplish with the Azure AI Foundry portal include:

• Deploying models from the model catalog to real-time inferencing endpoints for client applications to consume.
• Deploying and testing generative AI models in an Azure OpenAI service.
• Integrating data from custom data sources to support a retrieval augmented generation (RAG) approach to prompt engineering for generative AI models.
• Using prompt flow to define workflows that integrate models, prompts, and custom processing.
• Integrating content safety filters into a generative AI solution to mitigate potential harms.
• Extending a generative AI solution with multiple AI capabilities using Azure AI services.

You can also develop code-first by using the Azure AI Foundry SDK.

How does Azure AI Foundry work?

An AI hub provides a collaborative workspace for AI solution development and management. You need at least one Azure AI hub to use the solution development features and capabilities of AI Foundry. A hub is the collaboration environment for your team to share your project work, model endpoints, compute, connections, and security settings.

For example, you can easily create a project to enable data scientists and developers to collaborate on building a custom copilot for a business application or process.

What can I do with an Azure AI hub?

An Azure AI hub is the foundation for AI development projects on Azure, and enables you to define shared assets that can be used across multiple projects. You can use the AI Foundry portal and Azure portal to perform the following tasks in an Azure AI hub on the Manage page:

• Create members and assign them to specific roles.
• Create and manage compute instances on which to run experiments, prompt flows, and custom code.
• Create and manage connections to resources, such as data stores, GitHub, Azure AI Search indexes, and others.
• Define policies to manage behavior, such as automatic compute shutdown.

What can I do with a project?

All AI development in the Azure AI Foundry portal is performed within a project. You use a project to:

• Deploy language models to support a chatbot or copilot.
• Test models in the chat playground.
• Evaluate model responses to prompts.
• Manage indexes and datasets for custom data.
• Define content filters to mitigate potentially harmful responses.
• Use Visual Studio Code in your browser to create custom code.
• Add your own data to augment prompts.
• Use prompt flow to define flows that combine models, prompts, and custom code.
• Deploy solutions as web apps or as container service.

You can use Azure AI Foundry to create an Azure AI hub in the Management center. When this is done, an AI hub resource is created and assigned within your Azure subscription in the resource group you specify. 

Several additional services are available to core AI hub. Especially those that support AI Services, like:

• Storage with storage account in which data for AI projects are stored
• Container registry to store images for your deployed projects
• Azure OpenAI Service resources that provides generative AI models
• Key Vault, Application insights, …

Tomorrow we will further explore the Azure AI Foundry.

All of the code samples will be available on my Github.

Thanks for visiting r-craft.org
This article is originally published at https://tomaztsql.wordpress.com
Please visit source website for post related comments.