You have a Microsoft Foundry project that contains an agent. The agent generates summaries from retrieved policy documents.You need to improve response completeness. The solution must be implemented in the logic of the application code before responses are returned.What should you do?
Answer(s): A
Correct:* Add a reflection pass before the responses are returned.A reflection pass acts as an internal verification step within your application's logic. It directs the agent to evaluate its own draft response against the retrieved policy documents to ensure no mandatory regulatory clauses were left out. If it detects that critical text is missing, it regenerates or amends the answer before sending it to the user. This directly fulfills the core requirement of improving response completeness.* Add a retry evaluation before the responses are returned.You should implement an evaluation and retry loop in your application code.You must wrap the agent call inside a conditional code loop that evaluates the output against required criteria(such as a checklist of regulatory clauses), and programmatically forces a retry if information is omitted.Incorrect:* Decrease the value of the max_tokens parameter.* Decrease the value of the temperature paramerer.* Enable response streaming.* Increase the value of the presence_penalty parameter* Replace the model with a smaller deployment.* Switch to Retrieval Augmented Generation (RAG).
https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/ai-search
HOTSPOT (Drag and Drop is not supported)You develop a test method to verify the results retrieved from a call to the Azure Vision in Foundry Tools API.The call is used to analyze the existence of company logos in images. The call returns a collection of brands named brands.You have the following code segment:For each of the following statements, select Yes if the statement is true. Otherwise, select No.Note: Each correct selection is worth one point.Hot Area:
Box 1: YesThe code segment correctly filters for and displays the name (and coordinates) of each detected brand only if the model's confidence score is 75 percent or higher.The expression if brand.confidence >= 0.75 guarantees that only brands meeting or exceeding this threshold are printed.Box 2: YesThe code segment will display the coordinates. Specifically, it prints the x and y values of the rectangle's top-left corner alongside its width (w) and height (h) for any detected brand with a confidence score equal to or greater than 0.75 (75%).The provided code uses the properties directly to extract the bounding box:brand.rectangle.x and brand.rectangle.y: The coordinates of the top-left corner of the bounding box.brand.rectangle.w and brand.rectangle.h: The width and height of the bounding box.Box 3: NoSee Box 2 above.
https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-brand-detection
You have an Azure subscription.You plan to build an app that will use the Azure AI DALL-E model.You need to deploy the model.What should you use?
Answer(s): C
To deploy the DALL-E model, you need Microsoft Foundry and the Azure Command Line Interface (CLI).Deployment vs. Application Logic: The Azure CLI along with Microsoft Foundry handles the administrative infrastructure layer required to provision, configure, and manage model deployments within your subscription.Incorrect:[Not B]The Role of the SDK: The Azure SDK for JavaScript is a client-side development library. It is used within your code to consume or call the model's API after it has already been deployed. It cannot deploy the DALL-E model asset itself.Studio Clarification: While Azure Machine Learning Studio manages custom ML pipelines, foundational generative AI models like DALL-E are provisioned and hosted through the Microsoft Foundry portal and its associated ecosystem.
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/create-resource
HOTSPOT (Drag and Drop is not supported)You have an Azure subscription.You need to create a new resource that will generate fictional stores in response to user prompts. The solution must ensure that the resource uses a customer-managed key to protect data.How should you complete the script? To answer, select the appropriate options in the answer area.Note: Each correct selection is worth one point.Hot Area:
Box 1: OpenAITo generate fictional stores in response to user prompts, you need a generative AI model (such as GPT-3.5 orGPT-4). The Azure OpenAI service natively supports this generative capability and allows you to secure your deployed models and data using customer-managed keys (CMK).Box 2: --assign-identityWhen defining the Azure Key Vault resource script to enable customer-managed keys (CMK), you must use--assign-identity (or assign-identity).
https://learn.microsoft.com/en-us/azure/search/search-how-to-managed-identities
HOTSPOT (Drag and Drop is not supported)You have a Python application collects customer comments before posting them to a public forum.You need to send a text comment to Azure AI Content Safety and return the self-harm severity from the response.How should you complete the code? To answer, select the appropriate options in the answer area.Note: Each correct selection is worth one point.Hot Area:
Box 1: AnalyzeTextOptions(text=comment)To set up the request in your Python script, you must use AnalyzeTextOptions(text=comment), passing the text as a single string rather than a list.Example:Build the request options focusing on Text analysis# You can optionally restrict analysis to specific categories request_options = AnalyzeTextOptions(text=user_comment,categories=[TextCategory.SELF_HARM]Box 2: client.analyze_text(request)You must use client.analyze_text(request)1. Send the request: Call client.analyze_text(request) to retrieve the multi-severity results.2. Extract the self-harm result: Locate the self-harm categories from the response list.3. Return the severity: Access the .severity attribute
https://learn.microsoft.com/en-us/python/api/overview/azure/ai-contentsafety-readme
Post your Comments and Discuss Microsoft AI-103 exam prep with other Community members:
Our website is free, but we have to fight against AI bots and content theft. We're sorry for the inconvenience caused by these security measures. You can access the rest of the AI-103 content, but please register or login to continue.