ContentSafetyClient Class

Definition

Namespace:: Azure.AI.ContentSafety

Assembly:: Azure.AI.ContentSafety.dll

Package:: Azure.AI.ContentSafety v1.0.0

Package:: Azure.AI.ContentSafety v1.1.0-beta.1

Source:: ContentSafetyClient.cs

Source:: ContentSafetyClient.cs

Important

Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.

The ContentSafetyClient.

public class ContentSafetyClient

type ContentSafetyClient = class

Public Class ContentSafetyClient

Inheritance: Object
ContentSafetyClient

Constructors

Name	Description
ContentSafetyClient()	Initializes a new instance of ContentSafetyClient for mocking.
ContentSafetyClient(ContentSafetyClientSettings)	Initializes a new instance of ContentSafetyClient from a ContentSafetyClientSettings.
ContentSafetyClient(Uri, AzureKeyCredential, ContentSafetyClientOptions)	Initializes a new instance of ContentSafetyClient.
ContentSafetyClient(Uri, AzureKeyCredential)	Initializes a new instance of ContentSafetyClient.
ContentSafetyClient(Uri, TokenCredential, ContentSafetyClientOptions)	Initializes a new instance of ContentSafetyClient.
ContentSafetyClient(Uri, TokenCredential)	Initializes a new instance of ContentSafetyClient.

Properties

Name	Description
Pipeline	The HTTP pipeline for sending and receiving REST requests and responses.

Methods

Name	Description
AnalyzeImage(AnalyzeImageOptions, CancellationToken)	A synchronous API for the analysis of potentially harmful image content. Currently, it supports four categories: Hate, SelfHarm, Sexual, and Violence.
AnalyzeImage(BinaryData, CancellationToken)	Analyze Image with Binary Data.
AnalyzeImage(RequestContent, RequestContext)	[Protocol Method] A synchronous API for the analysis of potentially harmful image content. Currently, it supports four categories: Hate, SelfHarm, Sexual, and Violence. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.
AnalyzeImage(Uri, CancellationToken)	Analyze Image with Blob URI.
AnalyzeImageAsync(AnalyzeImageOptions, CancellationToken)	A synchronous API for the analysis of potentially harmful image content. Currently, it supports four categories: Hate, SelfHarm, Sexual, and Violence.
AnalyzeImageAsync(BinaryData, CancellationToken)	Analyze Image with Binary Data Async.
AnalyzeImageAsync(RequestContent, RequestContext)	[Protocol Method] A synchronous API for the analysis of potentially harmful image content. Currently, it supports four categories: Hate, SelfHarm, Sexual, and Violence. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.
AnalyzeImageAsync(Uri, CancellationToken)	Analyze Image with Blob URI Async.
AnalyzeText(AnalyzeTextOptions, CancellationToken)	A synchronous API for the analysis of potentially harmful text content. Currently, it supports four categories: Hate, SelfHarm, Sexual, and Violence.
AnalyzeText(RequestContent, RequestContext)	[Protocol Method] A synchronous API for the analysis of potentially harmful text content. Currently, it supports four categories: Hate, SelfHarm, Sexual, and Violence. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.
AnalyzeText(String, CancellationToken)	Analyze Text.
AnalyzeTextAsync(AnalyzeTextOptions, CancellationToken)	A synchronous API for the analysis of potentially harmful text content. Currently, it supports four categories: Hate, SelfHarm, Sexual, and Violence.
AnalyzeTextAsync(RequestContent, RequestContext)	[Protocol Method] A synchronous API for the analysis of potentially harmful text content. Currently, it supports four categories: Hate, SelfHarm, Sexual, and Violence. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.
AnalyzeTextAsync(String, CancellationToken)	Analyze Text Async.
DetectTextProtectedMaterial(DetectTextProtectedMaterialOptions, CancellationToken)	A synchronous API for detecting protected material in the given text.
DetectTextProtectedMaterial(RequestContent, RequestContext)	[Protocol Method] A synchronous API for detecting protected material in the given text. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.
DetectTextProtectedMaterialAsync(DetectTextProtectedMaterialOptions, CancellationToken)	A synchronous API for detecting protected material in the given text.
DetectTextProtectedMaterialAsync(RequestContent, RequestContext)	[Protocol Method] A synchronous API for detecting protected material in the given text. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.
ShieldPrompt(RequestContent, RequestContext)	[Protocol Method] A synchronous API for shielding prompt from direct and indirect injection attacks. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.
ShieldPrompt(ShieldPromptOptions, CancellationToken)	A synchronous API for shielding prompt from direct and indirect injection attacks.
ShieldPromptAsync(RequestContent, RequestContext)	[Protocol Method] A synchronous API for shielding prompt from direct and indirect injection attacks. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.
ShieldPromptAsync(ShieldPromptOptions, CancellationToken)	A synchronous API for shielding prompt from direct and indirect injection attacks.
UnifiedModerate(RequestContent, RequestContext)	[Protocol Method] A synchronous API that evaluates input, output, a proposed tool call, or a completed tool result against an applicable Agent Control Specification policy and returns the enforced content and policy verdict. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.
UnifiedModerate(UnifiedModerateConfig, CancellationToken)	A synchronous API that evaluates input, output, a proposed tool call, or a completed tool result against an applicable Agent Control Specification policy and returns the enforced content and policy verdict.
UnifiedModerateAsync(RequestContent, RequestContext)	[Protocol Method] A synchronous API that evaluates input, output, a proposed tool call, or a completed tool result against an applicable Agent Control Specification policy and returns the enforced content and policy verdict. This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.
UnifiedModerateAsync(UnifiedModerateConfig, CancellationToken)	A synchronous API that evaluates input, output, a proposed tool call, or a completed tool result against an applicable Agent Control Specification policy and returns the enforced content and policy verdict.

Applies to

Feedback

Was this page helpful?