DRAG DROP (Drag and Drop is not supported)You have a Microsoft Foundry project that contains an agent. The agent uses threads and file uploads and calls an Azure OpenAI model deployment.During load testing, calls intermittently fall and return an HTTP 429 rate limit exceeded error. Some user uploads fail and generate an HTTP 400 file size exceeded error.You need to mitigate the errors and reduce call failures. The solution must remain within the service and model limits.What should you do to resolve each error? To answer, drag the appropriate actions to the correct errors. Each action may be used once, more than once or not at all. You may need to drag the split bar between panes or scroll to view content.Note: Each comet selection is worth one point.Select and Place:
Answer(s): A
Box 1: Implement exponential backoff and jitter in the retry logicTo remedy intermittent HTTP 429 rate limit errors while staying within service limits, you must implement a retry policy that uses exponential backoff and jitter.Because the agent uses threads and file uploads, load testing triggers short-window concurrency spikes(bursting). Azure OpenAI evaluates rate limits in small slices (like 1- to 10-second windows), meaning overlapping file processing or concurrent thread steps will trigger a 429 even if your total Tokens-Per-Minute(TPM) or Requests-Per-Minute (RPM) look safe overall.Box 2: Split content into smaller files before uploading the files.Instead of uploading a large document in a single standard files.create request, utilize the Chunked UploadsREST API path. This splits the file payload on your client application layer before streaming it to Azure.Note: To resolve the HTTP 400 file size exceeded error in your Microsoft Foundry agent, you need to bypass the strict payload constraints of standard single-request uploads. In Azure OpenAI and Microsoft FoundryAgent architectures, a multipart standard upload has a rigid request body limit (typically 30 MB or 50 MB.
https://learn.microsoft.com/en-us/answers/questions/2265002/getting-error-after-deployed-a-model-in-azure-ai-f https://learn.microsoft.com/en-us/answers/questions/5521436/getting-400-error(request-body-too-large)-for-bat c
You have a Microsoft Foundry project.You need to deploy a model from the model catalog to support a search solution for internal policy documents.The model must generate vector representations of the text in the documents and of user queries.Which type of model should you use?
To fulfill this requirement, you need an embeddings model from the Microsoft Foundry AI Model Catalog that captures semantic meaning and outputs numerical vectors for text chunks.
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/understand-embeddings
You have a Microsoft Foundry project.You need to deploy a model from the model catalog to support real-time inference. The solution must meet the following requirements:▪ Use key-based authentication.▪ Support real-time REST API access.▪ NOT consume the vCPU quota of the virtual machines in the Azure subscription.Which type of deployment should you use?
Answer(s): D
The most appropriate type of deployment is a serverless API deployment (also referred to as a standard deployment or Models-as-a-Service / MaaS).Key-Based Authentication: Serverless API deployments natively provision an endpoint URL alongside primary and secondary API keys to secure your client applications.Real-Time REST API Access: When the model is successfully deployed, it exposes a scalable, real-timeHTTP/REST endpoint matching the standardized Azure AI Model Inference API.No Virtual Machine vCPU Quota Consumption: Unlike managed compute deployments—which provision dedicated virtual machines in your subscription and require VM vCPU quota—serverless API deployments are completely hosted and managed by Microsoft. They operate on a pay-as-you-go, token-based billing structure and do not consume any VM vCPU quota from your Azure subscription.
https://learn.microsoft.com/en-us/azure/foundry/concepts/deployments-overview
HOTSPOT (Drag and Drop is not supported)You plan to create a Microsoft Foundry project named Project1 that will contain an agent and use an Azure key vault named KV1.You need to configure a connection from Project1 to KV1.How should you complete the Bicep code? To answer, select the appropriate options in the answer area?Note: Each correct selection is worth one point.Hot Area:
Box 1: AzureKeyVaultTo configure a connection from a Microsoft Foundry project to an Azure Key Vault, you must use theAzureKeyVault connection category.Box 2: AccountManagedIdentityTo connect a Microsoft Foundry project to an Azure Key Vault, you must use AccountManagedIdentity as the authType.Microsoft Foundry secures its outbound connections to core Azure storage and security infrastructure usingMicrosoft Entra ID role-based access control (RBAC). Using AccountManagedIdentity completely eliminates the need to handle or rotate explicit credentials or api keys within your configuration.
https://learn.microsoft.com/en-us/azure/foundry/how-to/set-up-key-vault-connection
HOTSPOT (Drag and Drop is not supported)You have a Microsoft Foundry project.You need to create a customer support agent that meets the following requirements:▪ Grounds responses only in company policy documents stored in curated repositories▪ Retains customer preferences across separate chat sessionsHow should you configure the agent? To answer, select the appropriate options in the answer area.Note: Each correct selection is worth one point.Hot Area:
Box 1: Configure retrieval from approved data sourcesYou should configure retrieval from approved data sources to meet this requirement.In Microsoft Foundry (and broader Azure AI Foundry / Azure OpenAI architectures), grounding an agent exclusively in company policy documents requires implementing a Retrieval-Augmented Generation (RAG)pattern. This ensures the AI model only answers using the provided context and does not hallucinate or rely on its public training data.Box 2: Enable agent memory that uses persistent storageTo retain user preferences across completely separate chat sessions or conversations, you must use persistent agent memory. Traditional chat history only tracks messages within a single active thread or session.By contrast, the Memory Store feature provides a managed, long-term memory system that structurally indexes user preferences and facts across different devices and separate sessions.
https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/announcing-new-capabilities-for-azure-openai-on-your-data/4144636
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.