AI-103: Developing AI Apps and Agents on Azure

Question

You are building a Python application that collects customer comments before they are posted to a public forum. You need to send a text comment to Azure AI Content Safety and return the self-harm severity value from the response. How should the code be completed?

Question Image

Select

def get_self_harm_severity (comment: str) -> int:
    key = os.environ["CONTENT_SAFETY_KEY"]
    endpoint = os.environ["CONTENT_SAFETY_ENDPOINT"]
    client = ContentSafetyClient(endpoint, AzureKeyCredential(key))
    request = 
    response = 
    result = next(
            item for item in response.categories_analysis
            if item.category == TextCategory.SELF_HARM

            )
    return result.severity

Explanation

The Azure AI Content Safety Python SDK's AnalyzeTextOptions class requires a 'text' parameter of type str, so the request must be constructed as AnalyzeTextOptions(text=comment) — passing the raw string, not a list, and not misusing the 'categories' parameter or attempting to call TextCategory.SELF_HARM as a constructor. To submit the request, the ContentSafetyClient exposes an analyze_text(request) method (analyze_image is for images, moderate_text does not exist in this SDK, and the .path(...).post(...) syntax belongs to the JavaScript REST client, not the Python SDK). The resulting AnalyzeTextResult exposes a categories_analysis collection that is filtered for TextCategory.SELF_HARM to obtain and return its severity value, matching the pattern shown in Microsoft's official Content Safety Python quickstart.

Learn more

AI-103: Developing AI Apps and Agents on Azure

AstroTutor

Notes

Readiness

QuestionQ103

Community Discussion