AI-900 Practice Question: Describe features of computer vision workloads on Azure

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✓

  Step 1: Provision an Azure Text Analytics resource, then Step 2: Retrieve the endpoint and key, then Step 3: Instantiate the Text Analytics client, then Step 4: Submit a document for analysis and process the response.

  Why this is correct

  In the correct sequence, you first provision an Azure Text Analytics (Azure AI Language) resource in your subscription, which is what generates the service's endpoint and access keys. After provisioning, you retrieve these credentials, because they establish authenticated access to the API. You then instantiate the Text Analytics client using the endpoint and key, and finally submit a document through that client to analyze sentiment, key phrases, entities, or language and process the returned result.

• ✗

  Step 2: Retrieve the endpoint and key, then Step 1: Provision the resource, then Step 3: Instantiate the client, then Step 4: Submit a document.

  Why it's wrong here

  This order is invalid because retrieving the endpoint and key must happen after the Text Analytics resource is provisioned, since the provisioning step aggregates and creates those credentials. A request for an endpoint or key before any resource exists would return a 404 or an empty result, because there is no service instance to attribute them to. Only after provisioning can you retrieve the credentials and continue with authentication.

• ✗

  Step 1: Provision the resource, then Step 3: Instantiate the client, then Step 2: Retrieve the endpoint and key, then Step 4: Submit a document.

  Why it's wrong here

  This arrangement places client instantiation before credential retrieval, but the Text Analytics client constructor requires both an endpoint and a key/credential object, so it will fail with a credential or configuration error if those values are not yet available. You cannot meaningfully create a connected client without the resource's endpoint and key; authentication is a prerequisite for client creation. The correct dependency is that credentials must exist and be retrieved by the SDK before the client is built.

• ✗

  Step 1: Provision the resource, then Step 2: Retrieve the endpoint and key, then Step 4: Submit a document, then Step 3: Instantiate the client.

  Why it's wrong here

  This order tries to submit a document before instantiating the client, but the Text Analytics SDK's analysis methods are instance methods on the authenticated client object, so there is no way to send a request without first creating that client. The client holds the service endpoint, credential, and configuration such as retry policy and regional endpoint; skipping instantiation leaves you without an object to execute the HTTP call. Therefore, client creation must precede document submission.

Go deeper

Related to this question