Microsoft AI-102 Based on Real Exam Environment

Scenario Recap:

Application: Flower species classification using Custom Vision .

New images are received.

Solution: Add the new images, and then use the Smart Labeler tool.

Analysis:

The Smart Labeler tool in Custom Vision can help automatically generate suggested labels for newly uploaded images.

This is a valid way to extend a classifier with new images.

It doesn’t complete the entire pipeline (you’d still retrain afterward), but using Smart Labeler does meet the goal of adding new species efficiently.

Correct Answer: A. Yes

Key Knowledge:

To analyze images with Azure OpenAI, you must use a GPT-4 model with vision support (model version vision-preview ).

This requires deploying a GPT-4 model for vision.

Then you use the Chat playground (not completions, not DALL-E) since you want analysis, not generation.

You need to give the assistant instructions in the system message field (e.g., “You are an AI assistant that describes images”).

Finally, you upload an image and prompt the model to describe it.

Correct Sequence:

Create a new deployment, select a GPT-4 model, and set Model version to vision-preview.

Because GPT-4 with vision is required.

Open Chat playground and select the deployed model.

Vision capabilities are accessed through the Chat playground.

In the System message field, enter: “You are an AI assistant that describes images.”

This sets the assistant’s role.

In the Chat session pane, enter a text prompt of “Describe this image,” and upload an image by using the attachment button.

This triggers the model to analyze and describe the image.

Verified Answer (Correct Order):

Create a new deployment, select a GPT-4 model, and set Model version to vision-preview.

Open Chat playground and select the deployed model.

In the System message field, enter: You are an AI assistant that describes images.

In the Chat session pane, enter: Describe this image , and upload an image by using the attachment button.

Microsoft References:

Azure OpenAI vision capabilities

Azure OpenAI Studio overview

Provision the Language service resource in Azure.

Deploy a Docker container to an on-premises server.

Run the container and query the prediction endpoint.

According to the Microsoft documentation, the Language service is a cloud-based service that provides various natural language processing features, such as sentiment analysis, key phrase extraction, named entity recognition, etc. You can provision the Language service resource in Azure by following the steps in Create a Language resource. You will need to provide a name, a subscription, a resource group, a region, and a pricing tier for your resource. You will also get a key and an endpoint for your resource, which you will use to authenticate your requests to the Language service API.

According to the Microsoft documentation, you can also use the Language service as a container on your own premises or in another cloud. This option gives you more control over your data and network, and allows you to use the Language service without an internet connection. You can deploy a Docker container to an on-premises server by following the steps in Deploy Language containers. You will need to have Docker installed on your server, pull the container image from the Microsoft Container Registry, and run the container with the appropriate parameters. You will also need to activate your container with your key and endpoint from your Azure resource.

According to the Microsoft documentation, once you have deployed and activated your container, you can run it and query the prediction endpoint to get sentiment analysis results. The prediction endpoint is a local URL that follows this < container IP address > : < port > /text/analytics/v3.1-preview.4/sentiment. You can send HTTP POST requests to this endpoint with your text input in JSON format, and receive JSON responses with sentiment labels and scores for each document and sentence in your input.

The agent will reason over the uploaded file.●○

The code will create a run and check the output.○●

The code will create an agent and enable a file search.○●

 The agent will reason over the uploaded file.

Yes : The code includes file = project_client.agents.upload_file_and_poll(file_path= " ./data/file1.zip " , purpose=FilePurpose.AGENTS). The upload_file_and_poll method with FilePurpose.AGENTS suggests that the file (file1.zip) is uploaded for the agent to process, and agents in the Azure AI Foundry Agent Service are typically designed to reason over uploaded data. This indicates the agent will reason over the uploaded file.

 The code will create a run and check the output.

No : The provided code snippet does not include any explicit call to create a run (e.g., a method like create_run or start_run) or check the output (e.g., a method to retrieve or poll run results). The code only uploads a file and creates a vector store, but it does not initiate or monitor a run.

 The code will create an agent and enable a file search.

No : The code does not contain a method to create an agent (e.g., create_agent) or explicitly enable a file search. The create_vector_store_and_poll method creates a vector store, which is typically used for indexing data for search, but there is no indication of enabling a file search or creating an agent in this snippet.