Azure AI Studio tool empowers you to unlock the full potential of machine learning and automate tasks effectively.
By leveraging the powerful tools and features provided by Azure AI Studio, you can streamline your workflows, improve accuracy, and drive innovation in your domain.
Overview:
Azure AI Studio is designed for developers to:
- Build generative AI applications on an enterprise-grade platform.
- Directly from the studio you can interact with a project code-first via the Azure AI SDK and Azure AI CLI.
- Azure AI Studio is a trusted and inclusive platform that empowers developers of all abilities and preferences to innovate with AI and shape the future.
- Seamlessly explore, build, test, and deploy using cutting-edge AI tools and ML models, grounded in responsible AI practices.
- Build together as one team. Your Azure AI hub resource provides enterprise-grade security, and a collaborative environment with shared files and connections to pretrained models, data and compute.
- Organize your way. Your Azure AI project helps you save state, allowing you iterate from first idea, to first prototype, and then first production deployment. Also easily invite others to collaborate along this journey.
With Azure AI Studio, you can evaluate large language model (LLM) responses and orchestrate prompt application components with prompt flow for better performance.
AI Studio Architecture:
AI Studio provides a unified experience for AI developers and data scientists to build, evaluate, and deploy AI models through a web portal, SDK, or CLI. It’s built on capabilities and services provided by other Azure services.
The top-level AI Studio resources (AI hub and AI projects) are based on Azure Machine Learning. Other resources, such as Azure OpenAI, Azure AI Services, and Azure AI Search, are used by the AI hub and AI project.
An AI hub can have multiple child AI projects. Each AI project can have its own set of project-scoped connections.
Demo: Create an Azure AI project in Azure AI Studio
Let’s explore AI Studio and check what are the features it has and how to get started with AI studio.
Prerequisites:
Azure Subscription
Login to url: https://ai.azure.com/
Click on “All Azure AI” to view list of Services available for the AI Studio.
Create an AI Project
To create an Azure AI project in Azure AI Studio, follow these steps:
- Select the Build tab at the top of the page.
- Select + New AI project.
Follow steps as per tutorial: Create an Azure AI project in Azure AI Studio – Azure AI Studio | Microsoft Learn
Click next and you will see below page.
AI Studio Home Page: Overview
You have created an AI project in AI studio and can build and manage your AI solutions here.
Home Page:
Click on Home and you can view below the structure of your AI project.
Explore:
You will find various Model catalog here.
Popular Chat-GPT models are available here
| GPT-4 | A set of models that improve on GPT-3.5 and can understand and generate natural language and code. |
| GPT-3.5 | A set of models that improve on GPT-3 and can understand and generate natural language and code. |
| Embeddings | A set of models that can convert text into numerical vector form to facilitate text similarity. |
| DALL-E | A series of models that can generate original images from natural language. |
| Whisper | A series of models in preview that can transcribe and translate speech to text. |
| Text to speech (Preview) | A series of models in preview that can synthesize text to speech. |
Build:
Under this section, you configure the Playground settings, do the manual evaluation, and Customize the prompt flow.
Conclusion:
In this blog, we walked through an introduction to the Azure AI Studio tool and explored its features.
In the upcoming blog, we will delve into the process of creating your own Copilot using Azure AI Studio.
Creating your own Copilot using the Azure AI Studio tool empowers you to unlock the full potential of machine learning and automate tasks effectively. By leveraging the powerful tools and features provided by Azure AI Studio, you can streamline your workflows, improve accuracy, and drive innovation in your domain.
Stay tuned for the next blog post where we will explore the process of creating your own Copilot in more detail.
References:
https://learn.microsoft.com/en-us/azure/ai-studio/concepts/architecture
https://learn.microsoft.com/en-us/azure/ai-studio/how-to/create-projects
https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models