AI-102 Implement generative AI solutions Practice Test 6 — 15 Questions

Question 1

You are building a generative AI solution using Azure OpenAI Service. The application must retrieve information from a large private knowledge base. You need to ensure the model uses only relevant documents from the knowledge base to generate answers. Which feature should you configure?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Use Azure OpenAI On Your Data with vector search. B is correct because Azure OpenAI On Your Data with vector search enables the model to retrieve only the most semantically relevant documents from a private knowledge base by converting both the user query and the documents into high-dimensional vectors and performing similarity search. This ensures the model's responses are grounded in the specific, relevant information without exposing the entire knowledge base to the model.

Answer

Implement a custom prompt flow

Answer

Configure a content filter

Answer

Fine-tune the model with the knowledge base

Question 2

You are using Azure OpenAI Service to generate product descriptions. The output is often too verbose. You need to reduce the length of generated text without changing the model. Which parameter should you adjust?

Accepted Answer

Max tokens. Max tokens controls the total length of the generated response by capping the number of tokens (words/subwords) the model can output. Reducing this value directly truncates the output, making descriptions shorter without altering the model or its behavior. Other parameters influence randomness or repetition but do not enforce a strict length limit.

Answer

Frequency penalty

Answer

Temperature

Answer

Top-p (nucleus sampling)

Question 3

You are deploying a generative AI model using Azure Machine Learning. The model is a large language model that requires GPU compute. You need to minimize costs while ensuring the model is always available for inference. Which compute option should you choose?

Accepted Answer

Managed online endpoint with a GPU VM. A managed online endpoint with a GPU VM is the correct choice because it provisions a dedicated GPU instance that remains always active, ensuring the model is available for real-time inference at any time. This option balances cost and availability by allowing you to choose a lower-cost GPU SKU (e.g., NCas_v4) while avoiding the cold-start latency of serverless or batch options. The managed endpoint also handles auto-scaling and load balancing, but for constant availability, a fixed minimum instance count is required.

Answer

Batch endpoint with GPU

Answer

Serverless GPU compute

Answer

CPU-based inference

Question 4

You are building a generative AI application that uses Azure OpenAI Service. The application must access data from an Azure SQL database to answer user questions. You need to implement a solution that retrieves the most relevant data without exposing the database schema to the model. Which approach should you use?

Accepted Answer

Use a middle-tier service to query the database, then pass results to the model via Azure OpenAI On Your Data. It uses a middle-tier service to query the Azure SQL database and then passes only the relevant results to the Azure OpenAI model via the 'On Your Data' feature. This approach ensures the model never sees the database schema, protecting sensitive structural details while still providing the necessary context for answering user questions. It also allows the middle-tier to handle authentication, query optimization, and data filtering securely.

Answer

Configure the model to generate SQL queries and execute them against the database

Answer

Embed the entire database schema in the system prompt

Answer

Fine-tune the model with historical query results from the database

Question 5

You are using Azure OpenAI Service to summarize customer emails. The summaries must be concise and contain only key information. Which prompt engineering technique should you apply?

Accepted Answer

Use few-shot prompting with examples of desired summaries. Few-shot prompting is the correct technique because it provides the model with explicit examples of desired input-output pairs (e.g., a verbose email and its concise summary). This guides the model to learn the exact format, tone, and level of detail required for the summaries, which is critical for consistency in a production summarization pipeline. Without examples, the model may default to its training distribution and produce overly verbose or irrelevant output.

Answer

Use chain-of-thought prompting

Answer

Use zero-shot prompting with a one-sentence instruction

Answer

Use negative prompting to avoid verbose output

Question 6

You are deploying a generative AI solution that uses DALL-E to generate images. The application must ensure that generated images do not contain violent content. Which feature should you enable?

Accepted Answer

Configure Azure AI Content Safety to moderate images. Azure AI Content Safety is a dedicated service for detecting and moderating harmful content, including violence, in images and text. By integrating this service into your DALL-E image generation pipeline, you can scan generated images for violent content before they are delivered to users, ensuring compliance with safety policies. This is the correct approach because Azure AI Content Safety provides pre-built, customizable content moderation models specifically designed for this purpose.

Answer

Use grounding with Azure AI Search

Answer

Fine-tune the DALL-E model

Answer

Enable content filtering in DALL-E

Question 7

You are building a generative AI application using Azure OpenAI Service. The application must provide citations for answers retrieved from a set of documents. You need to ensure that each answer includes a reference to the source document. Which configuration should you use?

Accepted Answer

Use Azure OpenAI On Your Data with the 'include citations' option. Azure OpenAI On Your Data provides a built-in 'include citations' feature that automatically retrieves and appends source document references to the generated answer. This configuration leverages the underlying search index to map each response segment back to the original document, ensuring compliance with citation requirements without custom development.

Answer

Add a system message requesting citations

Answer

Implement a custom prompt flow with citation logic

Answer

Fine-tune the model to include citations

Question 8

You are designing a generative AI solution using Azure OpenAI Service. The solution must meet compliance requirements by preventing the model from generating sensitive personal data. Which TWO configurations should you implement? (Select TWO.)

Accepted Answer

Implement data loss prevention (DLP) policies using Microsoft Purview. Microsoft Purview DLP policies can scan and block sensitive data (e.g., PII, credit card numbers) in prompts and responses when integrated with Azure OpenAI Service, ensuring compliance by preventing data exfiltration. Azure AI Content Safety content filters allow you to configure severity thresholds to block harmful or sensitive content categories, directly preventing the model from generating personal data at the inference layer.

Answer

Add a system message instructing the model not to generate personal data

Answer

Deploy the model in a specific region

Answer

Fine-tune the model with a dataset that excludes personal data

Question 9

Your organization is deploying a generative AI chatbot using Azure OpenAI Service. The chatbot must answer questions based on internal documents stored in Azure Blob Storage. You need to implement a retrieval-augmented generation (RAG) solution. Which THREE components are required? (Select THREE.)

Accepted Answer

Azure AI Search index. Azure AI Search is the core indexing and retrieval engine in a RAG solution. It ingests documents from Azure Blob Storage, creates a searchable index, and enables vector or hybrid search to retrieve relevant chunks. The chatbot then uses these retrieved chunks as context for the Azure OpenAI model to generate grounded answers.

Answer

Azure Functions for preprocessing

Answer

Azure SQL Database for metadata

Question 10

You are using Azure OpenAI Service to generate code snippets. The output must be safe and free of security vulnerabilities. Which TWO practices should you follow? (Select TWO.)

Accepted Answer

Use Azure AI Content Safety to filter outputs. Azure AI Content Safety is a dedicated service that provides an additional layer of filtering for harmful or inappropriate content, including security vulnerabilities, beyond what the model itself offers. It allows you to define custom severity thresholds and blocklists, ensuring that generated code snippets are safe before they reach the user. This is a recommended practice for production deployments to mitigate risks like injection attacks or exposure of sensitive patterns.

Answer

Increase the temperature parameter to encourage diversity

Answer

Rely on the model's built-in safety features

Answer

Fine-tune the model with a dataset of secure code examples

Question 11

You are using Azure OpenAI Service with the system message shown in the exhibit. The model sometimes answers questions using general knowledge even when the context does not contain the answer. Which modification should you make to enforce the behavior?

Accepted Answer

Set the 'strict' parameter to true in Azure OpenAI On Your Data configuration. The 'strict' parameter in Azure OpenAI On Your Data configuration forces the model to rely exclusively on the provided data sources and refuse to answer when the context lacks the information. This directly enforces the desired behavior of not falling back on general knowledge.

Answer

Add a user message repeating the instruction

Answer

Reduce the temperature to 0

Answer

Fine-tune the model with examples of refusing to answer

Question 12

You run the Azure CLI command shown in the exhibit to create an online endpoint for a generative AI model. The deployment fails because the selected VM instance type is not available in the East US region. Which action should you take to resolve the issue?

Accepted Answer

Specify a different VM type or region that supports Standard_NC6s_v3. The deployment failed because the Standard_NC6s_v3 VM instance type is not available in the East US region. The correct action is to either choose a different VM type that is available in East US or deploy to a different region that supports Standard_NC6s_v3. This directly addresses the root cause of the failure, as Azure Machine Learning online endpoints require the selected VM SKU to be available in the target region.

Answer

Increase the instance count to 2

Answer

Use a batch endpoint instead of online endpoint

Answer

Change --compute-type to CPU

Question 13

You are testing an Azure OpenAI model with the parameters shown in the exhibit. The model generates very short responses. Which parameter should you modify to allow longer responses?

Accepted Answer

Increase max_tokens. The max_tokens parameter controls the maximum number of tokens (words or subwords) the model can generate in a single response. When responses are very short, increasing max_tokens allows the model to produce longer completions up to the specified limit. The other parameters affect randomness, diversity, or probability distribution, not the length cap.

Answer

Increase frequency_penalty

Answer

Increase top_p

Answer

Increase temperature

Question 14

You are developing a customer support chatbot using Azure OpenAI Service. The chatbot must only answer questions related to the company's product catalog and policies. You want to minimize the risk of the chatbot generating harmful or off-topic responses. Which approach should you use?

Accepted Answer

Use a system message that instructs the model to only answer product-related questions.. A system message sets the foundational behavior of the model by providing high-level instructions that guide all subsequent responses. By explicitly instructing the model to only answer product-related questions, you establish a clear boundary that minimizes off-topic or harmful outputs. This approach leverages the model's instruction-following capability, which is more effective than parameter tuning alone for content restriction.

Answer

Set the max_tokens parameter to 100.

Answer

Set the temperature parameter to 0.

Answer

Set the top_p parameter to 0.1.

Question 15

Your team is building an application that uses Azure OpenAI Service to summarize legal documents. You need to ensure that the summaries do not include any personally identifiable information (PII) that might appear in the source documents. Which feature should you configure in the Azure OpenAI Service?

Accepted Answer

Enable content filtering with PII detection.. Azure OpenAI Service's content filtering system includes built-in PII detection capabilities that can automatically identify and redact personally identifiable information from model inputs and outputs. This feature operates at the platform level, ensuring PII is filtered regardless of how the model is prompted, providing a reliable safeguard for sensitive legal documents.

Answer

Configure rate limiting to reduce processing volume.

Answer

Set the system message to instruct the model to exclude PII.

Answer

Use the 'Add your data' feature to ground the model.