Advent of 2024, Day 18 – Microsoft Azure AI – Azure AI Hub and Azure AI Project

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

In this Microsoft Azure AI series:

1. Dec 01: Microsoft Azure AI – What is Foundry?
2. Dec 02: Microsoft Azure AI – Working with Azure AI Foundry
3. Dec 03: Microsoft Azure AI – Creating project in Azure AI Foundry
4. Dec 04: Microsoft Azure AI – Deployment in Azure AI Foundry
5. Dec 05: Microsoft Azure AI – Deployment parameters in Azure AI Foundry
6. Dec 06: Microsoft Azure AI – AI Services in Azure AI Foundry
7. Dec 07: Microsoft Azure AI – Speech service in AI Services
8. Dec 08: Microsoft Azure AI – Speech Studio in Azure with AI Services
9. Dec 09: Microsoft Azure AI – Speech SDK with Python
10. Dec 10: Microsoft Azure AI – Language and Translation in Azure AI Foundry
11. Dec 11: Microsoft Azure AI – Language and Translation Python SDK
12. Dec 12: Microsoft Azure AI – Vision and Document AI Service
13. Dec 13: Microsoft Azure AI – Vision and Document Python SDK
14. Dec 14: Microsoft Azure AI – Content safety AI service
15. Dec 15: Microsoft Azure AI – Content safety Python SDK
16. Dec 16: Microsoft Azure AI – Fine-tuning a model
17. Dec 17: Microsoft Azure AI – Azure OpenAI service

Azure AI Hub

In AI Foundry portal, hubs provide the environment for a team to collaborate and organize work, and help you as a team lead or IT admin centrally set up security settings and govern usage and spend. You can create and manage a hub from the Azure portal or from the AI Foundry portal, and then your developers can create projects from the hub.

In essence, Hubs are the primary top-level Azure resource for AI Foundry. Their purpose is to to govern security, connectivity, and computing resources across playgrounds and projects.

Once a hub is created, developers can create multiple projects from it and access any other shared shared resources.

Many of the resource can be created in hub and shared:

• Security configuration including public network access, V-net, VPN, customer-managed key encryption, and privileged access to whom can create projects for customization. Security settings configured on the hub automatically pass down to each project. A managed virtual network is shared between all projects that share the same hub.
• Connections are named and authenticated references to Azure and non-Azure resources like data storage providers. Use a connection as a means for making an external resource available to a group of developers without having to expose its stored credential to an individual.
• Compute and quota allocation is managed as shared capacity for all projects in AI Foundry portal that share the same hub. This quota includes compute instance as managed cloud-based workstation for an individual. The same user can use a compute instance across projects.
• AI services access keys to endpoints for prebuilt AI models are managed on the hub scope. Use these endpoints to access foundation models from Azure OpenAI, Speech, Vision, and Content Safety with one API Key.
• Policy enforced in Azure on the hub scope applies to all projects managed under it.
• Dependent Azure resources are set up once per hub and associated projects and used to store artifacts you generate while working in AI Foundry portal such as logs or when uploading data.

A hub will also provides the hosting environment for projects.

Azure AI Projects

Project workspaces that are created using a hub inherit the same security settings and shared resource access. Teams can create project workspaces as needed to organize their work, isolate data, and/or restrict access.

A project is also an organisational container that has tools for AI customisation and orchestration. It lets you organise your work, save state across different tools like prompt flow, and collaborate with others. For example, you can share uploaded files and connections to data sources.

Multiple projects can use a hub, and multiple users can use a project. A project also helps you keep track of billing, and manage access and provides data isolation. Every project uses dedicated storage containers to let you upload files and share it with only other project members when using the ‘data’ experiences.

Projects let you create and group reusable components that can be used across tools in AI Foundry portal:

• Data – all datasets that can be used to create indexes, fine-tune models, and evaluate models.
• Flows – are an executable instruction set that can implement the AI logic.
• Evaluations – of a model or flow. You can run manual or metrics-based evaluations.
• Indexes – Vector search indexes generated from your data.

You will find in your Azure resources type of resources: Hub and Project.

or within the Azure AI Foundry:

Tomorrow we will look into the the management center in 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.