Microsoft - AI-900: Microsoft Certified: Azure AI Fundamentals

Sample Questions

Explanation:

Azure AI Language is built for:

• Sentiment analysis
• Key phrase extraction
• Named entity recognition
• PII detection
• Text translation & summarization
• Classification & Q&A extraction

Key phrase extraction is one of the features offered by Azure Language in Foundry Tools. This capability is part of a suite of cloud-based machine learning and AI tools designed for building intelligent applications that process written language. Use key phrase extraction to quickly identify the main concepts in text. For example, in the text "The food was delicious and the staff were wonderful.", key phrase extraction returns the main topics: "food" and "wonderful staff."

Azure AI Language doesn’t generate long-form content like press releases, blog posts, or marketing copy. You would use Azure OpenAI generative AI models instead.

Sentiment analysis and opinion mining are features offered by the Azure AI Language service. These features help you discover what people think about your brand or topic by analyzing text for signs of positive or negative sentiment. They can also link these sentiments to specific aspects of the text.

References:

What is Azure AI Language?

What is key phrase extraction in Azure Language in Foundry Tools?

What is sentiment analysis and opinion mining?

Explanation:

Custom question answering provides cloud-based Natural Language Processing (NLP) that allows you to create a natural conversational layer over your data. It's used to find appropriate answers from customer input or from a project.

Custom question answering is commonly used to build conversational client applications, which include social media applications, chat bots, and speech-enabled desktop applications. This offering includes features like enhanced relevance using a deep learning ranker, precise answers, and end-to-end region support.

Custom question answering imports your content into a project full of question and answer pairs. The import process extracts information about the relationship between the parts of your structured and semi-structured content to imply relationships between the question and answer pairs. You can edit these question and answer pairs or add new pairs.

The content of the question and answer pair includes:

• All the alternate forms of the question
• Metadata tags used to filter answer choices during the search
• Follow-up prompts to continue the search refinement

After you publish your project, a client application sends a user's question to your endpoint. Your custom question answering service processes the question and responds with the best answer.

Use custom question answering when you have static information in your project. This project is custom to your needs, which you built with documents such as PDFs and URLs.

Reference: What is custom question answering?

Explanation:

Microsoft Foundry is a unified Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development. This foundation combines production-grade infrastructure with friendly interfaces, enabling developers to focus on building applications rather than managing infrastructure.

Microsoft Foundry unifies agents, models, and tools under a single management grouping with built-in enterprise-readiness capabilities including tracing, monitoring, evaluations, and customizable enterprise setup configurations. The platform provides streamlined management through unified Role-based access control (RBAC), networking, and policies under one Azure resource provider namespace.

Note: Microsoft Foundry is the new name for Azure AI Foundry which was formerly named Azure AI Studio.

Reference: What is Microsoft Foundry?

Explanation:

Azure OpenAI in Microsoft Foundry models is powered by a diverse set of models with different capabilities and price points. Model availability varies by region and cloud.

Azure OpenAI is powered by a diverse set of models with different capabilities and price points. Model availability varies by region and cloud.

Azure OpenAI in Microsoft Foundry includes the following models:

References:

Explore Microsoft Foundry Models

Foundry Models sold directly by Azure

Foundry Models frequently asked questions

Explanation:

Foundry provides several deployment options depending on the type of models and resources you need to provision. The following deployment options are available:

• Standard deployment in Foundry resources
• Deployment to serverless API endpoints
• Deployment to managed computes

Foundry portal might automatically pick a deployment option based on your environment and configuration. Use Foundry resources for deployment whenever possible. Models that support multiple deployment options default to Foundry resources for deployment. To access other deployment options, use the Azure CLI or Azure Machine Learning SDK for deployment.

Standard deployment in Foundry resources

Foundry resources (formerly referred to as Azure AI Services resources), is the preferred deployment option in Foundry. It offers the widest range of capabilities, including regional, data zone, or global processing, and it offers standard and provisioned throughput (PTU) options. Flagship models in Foundry Models support this deployment option.

This deployment option is available in:

• Foundry resources
• Azure OpenAI resources
• Azure AI hub, when connected to a Foundry resource

Serverless API endpoint

This deployment option is available only in Azure AI hub resources. It allows you to create dedicated endpoints to host the model, accessible through an API. Foundry Models support serverless API endpoints with pay-as-you-go billing, and you can create only regional deployments for serverless API endpoints.

Managed compute

This deployment option is available only in Azure AI hub resources. It allows you to create a dedicated endpoint to host the model in a dedicated compute. You need to have compute quota in your subscription to host the model, and you're billed per compute uptime.

Managed compute deployment is required for model collections that include:

• Hugging Face
• NVIDIA inference microservices (NIMs)
• Industry models (Saifr, Rockwell, Bayer, Cerence, Sight Machine, Page AI, SDAIA)
• Databricks
• Custom models

References:

Deployment overview for Microsoft Foundry Models

Deploy models as serverless API deployments