AI-102 Implement generative AI solutions Practice Test 16 — 15 Questions

Question 1

You operate a RAG assistant on Azure OpenAI Service that answers questions over a product catalog. The index contains thousands of items, and users complain that answers mix details from unrelated products. You need retrieval to consider semantic meaning and handle paraphrased queries while returning only the most relevant items. What should you implement?

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

Accepted Answer

Vector search using embeddings generated by an Azure OpenAI embedding model. Embedding-based vector search maps both the query and the catalog items into a semantic space, so similarity reflects meaning rather than exact wording. Paraphrased questions then retrieve the right products, and ranking by vector distance keeps unrelated items out of the context. Keyword, facet, and scoring-profile approaches remain term- or attribute-driven and cannot perform semantic matching.

Answer

Faceted navigation that filters results by product category

Answer

Scoring profiles that boost documents containing a specific field value

Answer

Keyword search using the Azure AI Search simple query syntax

Question 2

You are deploying a generative AI feature that drafts marketing copy with an Azure OpenAI GPT-4o deployment. The application must stream partial responses to the browser so users see text as it is generated, rather than waiting for the full completion. What should you enable in your API call?

Accepted Answer

Set the stream parameter to true and consume the server-sent event chunks returned by the chat completions endpoint.. Streaming in Azure OpenAI is opt-in per request: setting the stream flag makes the chat completions endpoint return incremental deltas over server-sent events, which the browser can render progressively. Polling, batch processing, and quota changes all describe non-interactive or throughput-oriented behaviors that do not deliver partial tokens as they are generated.

Answer

Enable the asynchronous batch API and retrieve results from the output file once the job finishes.

Answer

Set a high max_tokens value and poll the operation status endpoint until the completion is marked complete.

Answer

Increase the deployment's tokens-per-minute quota so responses are generated faster.

Question 3

You are prototyping a chat experience on Azure OpenAI and want the model to produce structured JSON that matches a schema your application can deserialize reliably. Which feature should you configure?

Accepted Answer

Set response_format to json_schema with a strict schema definition on the chat completions call.. Schema-constrained generation is the only option that enforces structure at decode time. Configuring response_format with a strict JSON schema makes the model emit payloads that conform to the defined fields and types, so the application can deserialize without defensive parsing. Sampling parameters, prompt hints, and content filters do not enforce schema conformance.

Answer

Enable content filtering and set the severity threshold to high.

Answer

Increase top_p to 1 and rely on the model's instruction-following ability.

Answer

Set temperature to 0 and add the word JSON to the user prompt.

Question 4

You are preparing an Azure OpenAI deployment for a production generative AI application that must stream responses to a web front end and must limit the cost of overly long conversations. You need to configure parameters that control response length and streaming behavior. Which two parameters should you set? (Choose two.)

Accepted Answer

stream. Two distinct needs are stated: bounding the cost of long conversations and streaming responses to a web front end. The max_tokens parameter limits how many tokens each completion may contain, providing the cost ceiling. The stream parameter switches the API to incremental server-sent delivery, satisfying the front-end streaming requirement. Sampling parameters such as temperature, top_p, and frequency_penalty influence output content rather than length or delivery.

Answer

frequency_penalty

Answer

top_p

Answer

temperature

Question 5

Your team ships a generative assistant that calls a custom function to look up live order status. Users report that the assistant sometimes invents an order status instead of calling the function, and that when it does call the tool the arguments are occasionally malformed. You need to make tool invocation more reliable while keeping the existing model. What should you do?

Accepted Answer

Define the function with a clear name, description, and parameter schema, set tool_choice to require a tool call, and validate returned arguments before executing.. Reliable function calling comes from three things working together: descriptive tool metadata so the model understands when and how to call it, an explicit tool_choice that forces a call when the intent is known, and client-side validation of the returned arguments before execution. Penalties, larger models, and prompt-only pleading do not enforce tool invocation or argument correctness.

Answer

Switch the deployment to a larger model and keep the existing function definitions unchanged.

Answer

Add the phrase "always call the function" to the system message and leave tool_choice at its default value.

Answer

Raise the frequency_penalty so the model is discouraged from repeating previously invented order statuses.

Question 6

You are building an application that uses the Azure OpenAI Assistants API. The assistant must maintain conversational context across multiple user turns and use a code interpreter to analyze uploaded CSV files. Which two actions should you perform? (Choose two.)

Accepted Answer

Create a thread and add user messages to it, then create a run that references the assistant and the thread.. The Assistants API stores multi-turn context in threads, so messages are appended to a thread and runs execute against the assistant and thread. Code interpreter must be enabled as a tool, and CSV files must be uploaded and attached so the tool can read them during the run. Together these actions satisfy both the context and analysis requirements.

Answer

Create a new assistant for each user turn to avoid context conflicts.

Answer

Set the 'stream' parameter to true on every run to preserve conversation state between turns.

Answer

Use the completions endpoint with a manually maintained message array instead of the Assistants API.

Question 7

Your team is building a generative AI application on Azure OpenAI that must call an internal order-lookup REST API whenever a user asks about an order status. The model must decide when to call the API, and the application must execute the call and return the result to the model for the final answer. Which capability should you implement?

Accepted Answer

Function calling (tools) on the chat completions request, defining the order-lookup API as a tool.. The requirement is a model-driven decision to invoke a live REST API and then incorporate the returned data. Function calling provides exactly that contract: tools are declared, the model emits a structured call, the host application performs the HTTP request, and the result is fed back for final generation. The other options either constrain formatting, rely on training data, or only rank search results.

Answer

Semantic ranker enabled on an Azure AI Search index that stores order records.

Answer

A system message instructing the model to answer order questions only from its training data.

Answer

A JSON mode response format that forces the model to emit a schema-conforming order status object.

Question 8

A development team is building an Azure OpenAI chat application and wants the model to return structured JSON that matches a defined schema containing an 'intent' field and a 'confidence' field. The application will parse the response directly. Which deployment parameter should the team use to constrain the output format?

Accepted Answer

Configure a structured output format, such as a JSON schema response format, on the request.. Constraining a model to emit machine-parseable JSON with specific fields is accomplished with structured outputs, where a JSON schema is supplied in the request's response format. This guarantees schema conformance far more reliably than sampling parameters or length limits, which only influence variability or truncation.

Answer

Set the 'temperature' parameter to 0.

Answer

Set the 'top_p' parameter to 1.

Answer

Increase the 'max_tokens' value to allow the full JSON document to be generated.

Question 9

You are implementing a Retrieval Augmented Generation pattern with Azure AI Search and Azure OpenAI. Users complain that answers occasionally cite documents the user is not authorized to see, because the index contains all departments' content. You need to restrict retrieval so that each user only receives chunks from documents their identity permits. What should you do?

Accepted Answer

Add a security filter on a document access field in Azure AI Search, and pass the user's group or object IDs as an OData filter in the query.. Security trimming for RAG must occur at retrieval. Storing each document's allowed principals in a filterable field and passing the caller's group or object IDs as an OData filter ensures the search response never contains unauthorized chunks. Relevance ranking, prompt instructions, and manual index selection do not enforce authorization and can leak restricted content before the model or user sees it.

Answer

Create a separate index per department and have users manually select which index to search.

Answer

Add a system message instructing the model to ignore any content the user is not allowed to see.

Answer

Apply a semantic ranker to the query and rely on relevance scoring to push unauthorized content lower in the results.

Question 10

You are building a generative AI feature that drafts marketing copy in English and must also produce accurate French and German versions. The team wants a single deployment that handles all three languages without maintaining separate prompt templates per language, and the translations must preserve the marketing tone. Which Azure OpenAI capability should the solution rely on?

Accepted Answer

Use a single model deployment and instruct it in the system message to generate in the requested language while preserving tone.. Azure OpenAI chat models are trained on multilingual data and respond well to explicit language and style instructions. Specifying the target language and the marketing tone in the system message lets one deployment serve English, French, and German without maintaining separate templates. Separate deployments, an external translation pipeline, or fine-tuning all add complexity that the scenario does not require and do not better guarantee tone preservation.

Answer

Translate the English output using Azure AI Translator and then post-process with a grammar model.

Answer

Deploy a separate model instance per language and route requests based on the target locale.

Answer

Fine-tune the model on parallel marketing copy in all three languages before deploying it.

Question 11

You are building a generative AI assistant on Azure OpenAI that must call internal REST APIs to look up order status. You decide to use function calling. Which TWO actions are required to make the assistant reliably invoke the correct API and return a coherent answer? (Choose two.)

Accepted Answer

Execute the function in your application code and send the result back to the model as a tool message so it can generate the final response.. Function calling is a two-part contract. First, the application declares available functions with names, descriptions, and JSON schemas in the tools parameter so the model can choose one and emit structured arguments. Second, the application executes the chosen function and returns the result as a tool message, allowing the model to compose the final answer. Temperature, browsing, and token limits do not enable this loop.

Answer

Set the model temperature to zero so the function call arguments are always deterministic.

Answer

Enable the model's built-in web browsing tool so it can reach the internal APIs directly.

Answer

Increase the max_tokens value to ensure the function call arguments fit in the response.

Question 12

A team is prototyping an Azure OpenAI chat application and wants to iterate quickly on prompt wording without changing application code or redeploying. They also want to compare outputs from different prompt variants side by side. Which Azure AI Foundry feature should they use?

Accepted Answer

The prompt flow authoring experience in Azure AI Foundry. The requirement is to iterate on prompts and compare variants without code changes. Prompt flow in Azure AI Foundry is the authoring and orchestration surface designed for exactly that, letting prompts be edited, run, and evaluated visually. Quota pages, key and endpoint blades, and content filter settings are administrative or safety configuration surfaces and provide no prompt editing or comparison capability.

Answer

The Azure OpenAI resource's keys and endpoint blade

Answer

The model deployment quota page in the Azure portal

Answer

The content filter configuration page for the deployment

Question 13

You are deploying a generative AI solution that must produce structured JSON order confirmations from free-text customer emails. Downstream systems reject any response that is not valid JSON matching a fixed schema. Which approach best guarantees schema-conformant output from an Azure OpenAI chat completion?

Accepted Answer

Use a structured outputs configuration with a strict JSON schema that defines required fields and types.. Structured outputs constrain token generation to a supplied JSON schema, enforcing required fields and correct types so responses validate against the contract. JSON mode only guarantees syntactic validity, and few-shot examples or post-processing repairs do not provide a hard structural guarantee. For downstream systems that reject any schema deviation, constrained decoding is the most reliable approach.

Answer

Set the temperature to zero and include an example of the exact JSON output in the prompt.

Answer

Set response_format to json_object and describe the desired schema in the system message.

Answer

Request the output in JSON and run a regex-based validator that repairs any deviations before forwarding.

Question 14

You are developing a generative AI application using Azure OpenAI Service. The application must generate summaries of customer emails and then extract action items. You want to minimize the number of API calls and ensure the model outputs structured JSON. What should you do?

Accepted Answer

Use a single prompt that asks the model to summarize the email and extract action items, and specify the output format as JSON in the prompt.. The most efficient method is to use a single prompt that instructs the model to both summarize the email and extract action items, with the output specified as JSON. This reduces API calls to one, lowers latency, and provides structured data for easy parsing. It leverages the model's ability to handle multiple instructions and format outputs as requested.

Answer

Fine-tune the model to output JSON with both summary and action items.

Answer

Use the Azure OpenAI function calling feature to define a function that returns both summary and action items.

Answer

Use two separate prompts: one for summarization and one for action item extraction, and combine the results in code.

Question 15

You are building a generative AI feature where an Azure OpenAI model must call internal functions, such as looking up an order status and issuing a refund, based on the user's natural language request. You need the model to decide which function to invoke and to incorporate the function result into its answer. Which two actions should you take? (Choose two.)

Accepted Answer

Execute the returned function call in your application and send the result back in a subsequent message with the tool role.. Function calling requires two coordinated steps: declaring the callable functions with their parameter schemas in the request, and then executing the model's requested call and returning the result in a tool-role message. Together these let the model decide on the correct internal operation and produce a final answer grounded in real system data.

Answer

Attach the internal API documentation as an 'On Your Data' source so the model can retrieve and call the endpoints.

Answer

Fine-tune the model on historical order and refund conversations so it memorizes the internal APIs.

Answer

Raise the temperature so the model explores multiple possible functions before answering.