Free Microsoft AI-102 Practice Test & Real Exam Questions
You are building a chatbot.
You need to configure the chatbot to query a knowledge base.
Which dialog class should you use?
You need to configure the chatbot to query a knowledge base.
Which dialog class should you use?
Correct Answer: B
Vote an answer
Explanation: Only visible for Pass4Leader members. You can sign-up / login (it's free).
You have a video recording of a company meeting that includes presentations by multiple presenters.
You plan to use Azure AI Video Indexer to process the video and generate a separate text file for each presenter ' s presentation.
You need to identify each presenter in the video and attribute each text file to a presenter.
Which insight should you extract?
You plan to use Azure AI Video Indexer to process the video and generate a separate text file for each presenter ' s presentation.
You need to identify each presenter in the video and attribute each text file to a presenter.
Which insight should you extract?
Correct Answer: A
Vote an answer
You develop a custom question answering project in Azure Cognitive Service for Language. The project will be used by a chatbot. You need to configure the project to engage in multi-turn conversations. What should you do?
Correct Answer: B
Vote an answer
Explanation: Only visible for Pass4Leader members. You can sign-up / login (it's free).
You are building an agent by using the Semantic Kernel. The agent will use a custom plugin. You need to ensure that the agent meets the following requirements:
* The agent must use function calling.
* All functions that match the instructions must be triggered.
* All required parameters in the function must be requested by the agent if the user fails to provide them.
How should you complete the code? To answer, select the appropriate options in the answer area. NOTE:
Each correct selection is worth one point.
* The agent must use function calling.
* All functions that match the instructions must be triggered.
* All required parameters in the function must be requested by the agent if the user fails to provide them.
How should you complete the code? To answer, select the appropriate options in the answer area. NOTE:
Each correct selection is worth one point.
Correct Answer:
Explanation:
You are adding a custom plugin to a Semantic Kernel-based agent and you want function calling to be enforced and self-completing:
To register a plugin that exposes one or more callable functions to the agent, use CreatePluginFromFunctions . This builds a plugin from Kernel functions (prompt- or code-based) and makes them available for tool/function calling by the model.
To ensure the model must call functions (and request any required parameters it doesn't have), set the prompt execution settings to FunctionChoiceBehaviour.Required . In Semantic Kernel, this corresponds to the OpenAI tool/function-calling control that forces the assistant to invoke appropriate functions. When required parameters are marked in the function's schema, the assistant will ask follow-up questions to collect them before (or while) invoking the function.
References (Microsoft Azure AI Solution)
Semantic Kernel: Plugins and Functions, ChatCompletionAgent, OpenAIPromptExecutionSettings, and FunctionChoiceBehavior for enforced tool/function calling.
Your company has a repotting solution that has paginated reports. The reports query a dimensional model in a data warehouse. Which type of processing does the reporting solution use?
Correct Answer: C
Vote an answer
You have an Azure subscription that contains an Azure OpenA1 resource. You configure a model that has the following settings:
* Temperature: 1
* Top probabilities: 0.5
* Max response tokens: 100
You ask the model a question and receive the following response.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth point.
* Temperature: 1
* Top probabilities: 0.5
* Max response tokens: 100
You ask the model a question and receive the following response.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth point.
Correct Answer:
Explanation:
The subscription will be charged 86 tokens for the execution of the session. No The text completion was truncated because the Max response tokens value was exceeded. No The prompt_tokens value will be included in the calculation of the Max response tokens value. No From the response payload:
usage.prompt_tokens = 37
usage.completion_tokens = 86
usage.total_tokens = 123
finish_reason = " stop "
Billing is for total tokens (input + output), not just completion tokens.
Azure OpenAI bills on both prompt (input) and completion (output) tokens. Here, the total is 123 tokens, so it is not just 86. Hence No.
Not truncated by max response tokens.
If a response hits the maximum allowed output tokens, finish_reason would be " length " . Here it is " stop " and the model produced only 86 completion tokens while Max response tokens was set to 100, so the limit was not reached. Hence No.
max response tokens applies only to the generated output, not the prompt.
max_tokens (Max response tokens) limits the number of tokens the model may generate in the completion; it does not include prompt_tokens . Hence No.
Microsoft References
Azure OpenAI Service - Chat Completions API (parameters, max_tokens , response usage , finish_reason ).
https://learn.microsoft.com/azure/ai-services/openai/reference#chat-completions Azure OpenAI pricing and token usage model (charges for input and output tokens).
https://learn.microsoft.com/azure/ai-services/openai/overview#pricing
Token counting and limits (context vs. max output tokens).
https://learn.microsoft.com/azure/ai-services/openai/concepts/tokenizers#token-limits
For each of the following statements, select Yes if the statement is tine. Otherwise, select No. NOTE: Each correct selection is worth one point.
Correct Answer:
Explanation:
Stream processing has access to the most recent data received or data within a rolling time window. # Yes
Batch processing must occur immediately and have latency in the order of seconds or milliseconds. # No Stream processing is used for simple response functions, aggregates, or calculations such as rolling averages. # Yes
Comprehensive Detailed Explanation
Stream processing has access to the most recent data received or data within a rolling time window.
Correct.
Stream processing handles real-time or near real-time data.
It operates on a continuous data stream and often uses a rolling time window for analytics.
The answer: Yes
Batch processing must occur immediately and have latency in the order of seconds or milliseconds.
Incorrect.
Batch processing is designed for large volumes of data collected over time.
It typically has high latency (minutes, hours, or even days), not immediate execution.
The answer: No
Stream processing is used for simple response functions, aggregates, or calculations such as rolling averages.
Correct.
Common stream analytics tasks include event-driven responses, real-time aggregations, anomaly detection, and rolling averages.
The answer: Yes
Correct Answers:
Yes
No
Yes
Microsoft References
Batch vs. Stream processing in Azure
Azure Stream Analytics overview
You are building a Language Understanding solution.
You discover that many intents have similar utterances containing airport names or airport codes.
You need to minimize the number of utterances used to fram the model.
Which type of custom entity should you use?
You discover that many intents have similar utterances containing airport names or airport codes.
You need to minimize the number of utterances used to fram the model.
Which type of custom entity should you use?
Correct Answer: D
Vote an answer
Explanation: Only visible for Pass4Leader members. You can sign-up / login (it's free).
You have a chatbot that uses a QnA Maker application.
You enable active learning for the knowledge base used by the QnA Maker application.
You need to integrate user input into the model.
Which four actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
You enable active learning for the knowledge base used by the QnA Maker application.
You need to integrate user input into the model.
Which four actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Correct Answer:
Explanation:
Step 1: For the knowledge base, select Show active learning suggestions.
In order to see the suggested questions, on the Edit knowledge base page, select View Options, then select Show active learning suggestions.
Step 2: Approve and reject suggestions.
Each QnA pair suggests the new question alternatives with a check mark, # , to accept the question or an x to reject the suggestions. Select the check mark to add the question.
Step 3: Save and train the knowledge base.
Select Save and Train to save the changes to the knowledge base.
Step 4: Publish the knowledge base.
Select Publish to allow the changes to be available from the GenerateAnswer API.
When 5 or more similar queries are clustered, every 30 minutes, QnA Maker suggests the alternate questions for you to accept or reject.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/how-to/improve-knowledge-base
You need to upload speech samples to a Speech Studio project. How should you upload the samples?
Correct Answer: C
Vote an answer
Explanation: Only visible for Pass4Leader members. You can sign-up / login (it's free).
Your company has a repotting solution that has paginated reports. The reports query a dimensional model in a data warehouse. Which type of processing does the reporting solution use?
Correct Answer: C
Vote an answer
Explanation: Only visible for Pass4Leader members. You can sign-up / login (it's free).
