DOWNLOAD the newest ExamPrepAway AI-901 PDF dumps from Cloud Storage for free: https://drive.google.com/open?id=14464PvoCqSuOJAXiFwBGsggzrgY2BhOo
The design of our AI-901 learning materials is ingenious and delicate. Every detail is perfect. For example, if you choose to study our learning materials on our windows software, you will find the interface our learning materials are concise and beautiful, so it can allow you to study AI-901 learning materials in a concise and undisturbed environment. In addition, you will find a lot of small buttons, which can give you a lot of help. Some buttons are used to hide or show the answer. What's more important is that we have spare space, so you can take notes under each question in the process of learning AI-901 Learning Materials.
| Section | Weight | Objectives |
|---|---|---|
| Describe features of Natural Language Processing (NLP) workloads on Azure (15-20%) | 15-20% | - Identify features of common NLP workload scenarios
|
| Describe features of generative AI workloads on Azure (20-25%) | 20-25% | - Identify generative AI services and capabilities in Microsoft Azure
|
| Describe Artificial Intelligence workloads and considerations (15-20%) | 15-20% | - Identify features of common AI workloads
|
| Describe features of computer vision workloads on Azure (15-20%) | 15-20% | - Identify common types of computer vision solution
|
| Describe fundamental principles of machine learning on Azure (15-20%) | 15-20% | - Identify common machine learning techniques
|
This document of AI-901 exam questions is very convenient. Furthermore, the Microsoft AI-901 PDF questions collection is printable which enables you to study without any smart device. This can be helpful since many applicants prefer off-screen study. All these features of Microsoft AI-901 Pdf Format are just to facilitate your preparation for the AI-901 examination.
NEW QUESTION # 67
You have a Microsoft Foundry project named project1 that contains an Azure OpenAI resource named Resource1.
To Resource1, you deploy a gpt-4.1-mini model by using a model deployment named my-mini-gpt.
You need to connect to my-mini-gpt from an application.
How should you complete the Python code? To answer, drag the appropriate values to the correct targets.
Each value may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation:
client = OpenAI(
api_key= " ... " ,
base_url= " https://resource1.openai.azure.com/openai/v1/ " ,
)
response = client.responses.create(
model= " my-mini-gpt " ,
)
For Azure OpenAI in Microsoft Foundry, the base_url uses the Azure OpenAI resource name in the endpoint format:
https:// < resource-name > .openai.azure.com/openai/v1/
In the question, the Azure OpenAI resource is named Resource1 , so the first blank must be resource1 .
Microsoft documentation for Azure OpenAI v1 endpoints confirms that the endpoint must use the ...openai.
azure.com/openai/v1/ path.
For the model parameter, Azure OpenAI requires the deployment name , not the underlying model name.
Microsoft states that Azure OpenAI always requires the deployment name when calling APIs, even when the parameter is named model.
The deployed model is gpt-4.1-mini , but the deployment name is my-mini-gpt . Therefore, the second blank must be:
model= " my-mini-gpt "
So the correct selections are:
base_url blank = resource1
model blank = my-mini-gpt
NEW QUESTION # 68
Drag and Drop Question
Match the description to the corresponding Microsoft Foundry tools.
To answer, drag the appropriate description from the column on the left to its tool on the right.
Each description may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation:
Box 1: Transcribes spoken input
Speech recognition in Microsoft Foundry transcribes spoken input into text using built-in speech- to-text capabilities.
Transcription FeaturesReal-time transcription: Converts microphone inputs or live audio streams into text instantly.
Batch transcription: Processes pre-recorded audio or video files asynchronously.
Advanced audio models: Leverages tools like GPT-transcribe and GPT-live-transcribe to handle natural speech patterns, numbers, addresses, and industry-specific terminology.
Broad language support: Handles over 140 locales and languages for spoken input.
Box 2: Generates spoken output
Speech synthesis in Microsoft Foundry (via Azure Speech in Foundry Tools) converts text input into realistic, human-like spoken audio output.
Reference:
https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-to-text
NEW QUESTION # 69
Hotspot Question
Select the answer that correctly completes the sentence.
Answer:
Explanation:
NEW QUESTION # 70
Select the answer that correctly completes the sentence.
Answer:
Explanation:
Explanation:
Ongoing monitoring, feedback, and evaluation are goals of the Reliability & Safety principle.
The Microsoft responsible AI principle of Reliability and safety focuses on ensuring that AI systems operate consistently, safely, and as intended across different conditions. This includes testing, monitoring, collecting feedback, and evaluating system performance over time.
Why the other options are incorrect:
Human oversight and control aligns more closely with accountability.
Data governance and management aligns more closely with privacy and security.
The minimization of stereotyping, demeaning, and erasing outputs aligns more closely with fairness and inclusiveness.
NEW QUESTION # 71
You are developing a voice application that listens for spoken commands and converts them into text by using Azure Speech in Foundry Tools.
How should you complete the Python code? To answer, select the appropriate option in the answer area.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation:
The correct Python method is:
recognizer.recognize_once()
Completed code:
import azure.cognitiveservices.speech as speechsdk
speech_config = speechsdk.SpeechConfig(subscription=key, region=region) recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config) recognizer.recognize_once() Microsoft's Azure Speech documentation for Foundry Tools explains that Speech to text is used for real-time speech recognition and converting spoken audio into text. The Python Speech SDK uses a SpeechRecognizer object for recognition from audio input, such as a microphone.
Why the other options are incorrect:
recognizer.speak_text_async( " Ready " ) is incorrect because speaking text is text-to-speech , not speech-to- text recognition.
recognizer.start_continuous_recognition() can be used for continuous recognition, but the code shown is asking for the basic method to recognize spoken input and convert it to text from the SpeechRecognizer.
recognizer.start_keyword_recognition() is used for keyword/wake-word recognition, not general speech-to- text transcription of spoken commands.
Therefore, the correct answer is:
recognizer.recognize_once()
NEW QUESTION # 72
......
Different from other similar education platforms, the AI-901 quiz guide will allocate materials for multi-plate distribution, rather than random accumulation without classification. The AI-901 prepare torrent is absorbed in the advantages of the traditional learning platform and realize their shortcomings, so as to develop the AI-901 test material more suitable for users of various cultural levels. And the AI-901 test material provided many study parts of the plates is good enough to arouse the enthusiasm of the user, allow the user to keep attention of highly concentrated.
AI-901 Dumps PDF: https://www.examprepaway.com/Microsoft/braindumps.AI-901.ete.file.html
P.S. Free 2026 Microsoft AI-901 dumps are available on Google Drive shared by ExamPrepAway: https://drive.google.com/open?id=14464PvoCqSuOJAXiFwBGsggzrgY2BhOo