azure-native.cognitiveservices.SubscriptionRaiPolicy

Azure Native v3.13.0, Jan 28 26

This is the latest version of Azure Native. Use the Azure Native v2 docs if using the v2 version of this package.

Azure Native v3.13.0 published on Wednesday, Jan 28, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-azure-native

This is the latest version of Azure Native. Use the Azure Native v2 docs if using the v2 version of this package.

Azure Native v3.13.0 published on Wednesday, Jan 28, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-azure-native

Example Usage

PutRaiPolicy

using System.Collections.Generic;
using System.Linq;
using Pulumi;
using AzureNative = Pulumi.AzureNative;

return await Deployment.RunAsync(() => 
{
    var subscriptionRaiPolicy = new AzureNative.CognitiveServices.SubscriptionRaiPolicy("subscriptionRaiPolicy", new()
    {
        Properties = new AzureNative.CognitiveServices.Inputs.RaiPolicyPropertiesArgs
        {
            BasePolicyName = "Microsoft.Default",
            ContentFilters = new[]
            {
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = false,
                    Enabled = false,
                    Name = "Hate",
                    SeverityThreshold = AzureNative.CognitiveServices.ContentLevel.High,
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Prompt,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Hate",
                    SeverityThreshold = AzureNative.CognitiveServices.ContentLevel.Medium,
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Completion,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Sexual",
                    SeverityThreshold = AzureNative.CognitiveServices.ContentLevel.High,
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Prompt,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Sexual",
                    SeverityThreshold = AzureNative.CognitiveServices.ContentLevel.Medium,
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Completion,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Selfharm",
                    SeverityThreshold = AzureNative.CognitiveServices.ContentLevel.High,
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Prompt,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Selfharm",
                    SeverityThreshold = AzureNative.CognitiveServices.ContentLevel.Medium,
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Completion,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Violence",
                    SeverityThreshold = AzureNative.CognitiveServices.ContentLevel.Medium,
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Prompt,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Violence",
                    SeverityThreshold = AzureNative.CognitiveServices.ContentLevel.Medium,
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Completion,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Jailbreak",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Prompt,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Protected Material Text",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Completion,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Protected Material Code",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Completion,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    Blocking = true,
                    Enabled = true,
                    Name = "Profanity",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Prompt,
                },
            },
            Mode = AzureNative.CognitiveServices.RaiPolicyMode.Asynchronous_filter,
        },
        RaiPolicyName = "raiPolicyName",
    });

});

package main

import (
	cognitiveservices "github.com/pulumi/pulumi-azure-native-sdk/cognitiveservices/v3"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := cognitiveservices.NewSubscriptionRaiPolicy(ctx, "subscriptionRaiPolicy", &cognitiveservices.SubscriptionRaiPolicyArgs{
			Properties: &cognitiveservices.RaiPolicyPropertiesArgs{
				BasePolicyName: pulumi.String("Microsoft.Default"),
				ContentFilters: cognitiveservices.RaiPolicyContentFilterArray{
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking:          pulumi.Bool(false),
						Enabled:           pulumi.Bool(false),
						Name:              pulumi.String("Hate"),
						SeverityThreshold: pulumi.String(cognitiveservices.ContentLevelHigh),
						Source:            pulumi.String(cognitiveservices.RaiPolicyContentSourcePrompt),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking:          pulumi.Bool(true),
						Enabled:           pulumi.Bool(true),
						Name:              pulumi.String("Hate"),
						SeverityThreshold: pulumi.String(cognitiveservices.ContentLevelMedium),
						Source:            pulumi.String(cognitiveservices.RaiPolicyContentSourceCompletion),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking:          pulumi.Bool(true),
						Enabled:           pulumi.Bool(true),
						Name:              pulumi.String("Sexual"),
						SeverityThreshold: pulumi.String(cognitiveservices.ContentLevelHigh),
						Source:            pulumi.String(cognitiveservices.RaiPolicyContentSourcePrompt),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking:          pulumi.Bool(true),
						Enabled:           pulumi.Bool(true),
						Name:              pulumi.String("Sexual"),
						SeverityThreshold: pulumi.String(cognitiveservices.ContentLevelMedium),
						Source:            pulumi.String(cognitiveservices.RaiPolicyContentSourceCompletion),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking:          pulumi.Bool(true),
						Enabled:           pulumi.Bool(true),
						Name:              pulumi.String("Selfharm"),
						SeverityThreshold: pulumi.String(cognitiveservices.ContentLevelHigh),
						Source:            pulumi.String(cognitiveservices.RaiPolicyContentSourcePrompt),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking:          pulumi.Bool(true),
						Enabled:           pulumi.Bool(true),
						Name:              pulumi.String("Selfharm"),
						SeverityThreshold: pulumi.String(cognitiveservices.ContentLevelMedium),
						Source:            pulumi.String(cognitiveservices.RaiPolicyContentSourceCompletion),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking:          pulumi.Bool(true),
						Enabled:           pulumi.Bool(true),
						Name:              pulumi.String("Violence"),
						SeverityThreshold: pulumi.String(cognitiveservices.ContentLevelMedium),
						Source:            pulumi.String(cognitiveservices.RaiPolicyContentSourcePrompt),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking:          pulumi.Bool(true),
						Enabled:           pulumi.Bool(true),
						Name:              pulumi.String("Violence"),
						SeverityThreshold: pulumi.String(cognitiveservices.ContentLevelMedium),
						Source:            pulumi.String(cognitiveservices.RaiPolicyContentSourceCompletion),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking: pulumi.Bool(true),
						Enabled:  pulumi.Bool(true),
						Name:     pulumi.String("Jailbreak"),
						Source:   pulumi.String(cognitiveservices.RaiPolicyContentSourcePrompt),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking: pulumi.Bool(true),
						Enabled:  pulumi.Bool(true),
						Name:     pulumi.String("Protected Material Text"),
						Source:   pulumi.String(cognitiveservices.RaiPolicyContentSourceCompletion),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking: pulumi.Bool(true),
						Enabled:  pulumi.Bool(true),
						Name:     pulumi.String("Protected Material Code"),
						Source:   pulumi.String(cognitiveservices.RaiPolicyContentSourceCompletion),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						Blocking: pulumi.Bool(true),
						Enabled:  pulumi.Bool(true),
						Name:     pulumi.String("Profanity"),
						Source:   pulumi.String(cognitiveservices.RaiPolicyContentSourcePrompt),
					},
				},
				Mode: pulumi.String(cognitiveservices.RaiPolicyMode_Asynchronous_filter),
			},
			RaiPolicyName: pulumi.String("raiPolicyName"),
		})
		if err != nil {
			return err
		}
		return nil
	})
}

package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.azurenative.cognitiveservices.SubscriptionRaiPolicy;
import com.pulumi.azurenative.cognitiveservices.SubscriptionRaiPolicyArgs;
import com.pulumi.azurenative.cognitiveservices.inputs.RaiPolicyPropertiesArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }

    public static void stack(Context ctx) {
        var subscriptionRaiPolicy = new SubscriptionRaiPolicy("subscriptionRaiPolicy", SubscriptionRaiPolicyArgs.builder()
            .properties(RaiPolicyPropertiesArgs.builder()
                .basePolicyName("Microsoft.Default")
                .contentFilters(                
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(false)
                        .enabled(false)
                        .name("Hate")
                        .severityThreshold("High")
                        .source("Prompt")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Hate")
                        .severityThreshold("Medium")
                        .source("Completion")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Sexual")
                        .severityThreshold("High")
                        .source("Prompt")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Sexual")
                        .severityThreshold("Medium")
                        .source("Completion")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Selfharm")
                        .severityThreshold("High")
                        .source("Prompt")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Selfharm")
                        .severityThreshold("Medium")
                        .source("Completion")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Violence")
                        .severityThreshold("Medium")
                        .source("Prompt")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Violence")
                        .severityThreshold("Medium")
                        .source("Completion")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Jailbreak")
                        .source("Prompt")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Protected Material Text")
                        .source("Completion")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Protected Material Code")
                        .source("Completion")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .blocking(true)
                        .enabled(true)
                        .name("Profanity")
                        .source("Prompt")
                        .build())
                .mode("Asynchronous_filter")
                .build())
            .raiPolicyName("raiPolicyName")
            .build());

    }
}

import * as pulumi from "@pulumi/pulumi";
import * as azure_native from "@pulumi/azure-native";

const subscriptionRaiPolicy = new azure_native.cognitiveservices.SubscriptionRaiPolicy("subscriptionRaiPolicy", {
    properties: {
        basePolicyName: "Microsoft.Default",
        contentFilters: [
            {
                blocking: false,
                enabled: false,
                name: "Hate",
                severityThreshold: azure_native.cognitiveservices.ContentLevel.High,
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Prompt,
            },
            {
                blocking: true,
                enabled: true,
                name: "Hate",
                severityThreshold: azure_native.cognitiveservices.ContentLevel.Medium,
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Completion,
            },
            {
                blocking: true,
                enabled: true,
                name: "Sexual",
                severityThreshold: azure_native.cognitiveservices.ContentLevel.High,
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Prompt,
            },
            {
                blocking: true,
                enabled: true,
                name: "Sexual",
                severityThreshold: azure_native.cognitiveservices.ContentLevel.Medium,
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Completion,
            },
            {
                blocking: true,
                enabled: true,
                name: "Selfharm",
                severityThreshold: azure_native.cognitiveservices.ContentLevel.High,
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Prompt,
            },
            {
                blocking: true,
                enabled: true,
                name: "Selfharm",
                severityThreshold: azure_native.cognitiveservices.ContentLevel.Medium,
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Completion,
            },
            {
                blocking: true,
                enabled: true,
                name: "Violence",
                severityThreshold: azure_native.cognitiveservices.ContentLevel.Medium,
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Prompt,
            },
            {
                blocking: true,
                enabled: true,
                name: "Violence",
                severityThreshold: azure_native.cognitiveservices.ContentLevel.Medium,
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Completion,
            },
            {
                blocking: true,
                enabled: true,
                name: "Jailbreak",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Prompt,
            },
            {
                blocking: true,
                enabled: true,
                name: "Protected Material Text",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Completion,
            },
            {
                blocking: true,
                enabled: true,
                name: "Protected Material Code",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Completion,
            },
            {
                blocking: true,
                enabled: true,
                name: "Profanity",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Prompt,
            },
        ],
        mode: azure_native.cognitiveservices.RaiPolicyMode.Asynchronous_filter,
    },
    raiPolicyName: "raiPolicyName",
});

import pulumi
import pulumi_azure_native as azure_native

subscription_rai_policy = azure_native.cognitiveservices.SubscriptionRaiPolicy("subscriptionRaiPolicy",
    properties={
        "base_policy_name": "Microsoft.Default",
        "content_filters": [
            {
                "blocking": False,
                "enabled": False,
                "name": "Hate",
                "severity_threshold": azure_native.cognitiveservices.ContentLevel.HIGH,
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.PROMPT,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Hate",
                "severity_threshold": azure_native.cognitiveservices.ContentLevel.MEDIUM,
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.COMPLETION,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Sexual",
                "severity_threshold": azure_native.cognitiveservices.ContentLevel.HIGH,
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.PROMPT,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Sexual",
                "severity_threshold": azure_native.cognitiveservices.ContentLevel.MEDIUM,
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.COMPLETION,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Selfharm",
                "severity_threshold": azure_native.cognitiveservices.ContentLevel.HIGH,
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.PROMPT,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Selfharm",
                "severity_threshold": azure_native.cognitiveservices.ContentLevel.MEDIUM,
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.COMPLETION,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Violence",
                "severity_threshold": azure_native.cognitiveservices.ContentLevel.MEDIUM,
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.PROMPT,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Violence",
                "severity_threshold": azure_native.cognitiveservices.ContentLevel.MEDIUM,
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.COMPLETION,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Jailbreak",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.PROMPT,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Protected Material Text",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.COMPLETION,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Protected Material Code",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.COMPLETION,
            },
            {
                "blocking": True,
                "enabled": True,
                "name": "Profanity",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.PROMPT,
            },
        ],
        "mode": azure_native.cognitiveservices.RaiPolicyMode.ASYNCHRONOUS_FILTER,
    },
    rai_policy_name="raiPolicyName")

resources:
  subscriptionRaiPolicy:
    type: azure-native:cognitiveservices:SubscriptionRaiPolicy
    properties:
      properties:
        basePolicyName: Microsoft.Default
        contentFilters:
          - blocking: false
            enabled: false
            name: Hate
            severityThreshold: High
            source: Prompt
          - blocking: true
            enabled: true
            name: Hate
            severityThreshold: Medium
            source: Completion
          - blocking: true
            enabled: true
            name: Sexual
            severityThreshold: High
            source: Prompt
          - blocking: true
            enabled: true
            name: Sexual
            severityThreshold: Medium
            source: Completion
          - blocking: true
            enabled: true
            name: Selfharm
            severityThreshold: High
            source: Prompt
          - blocking: true
            enabled: true
            name: Selfharm
            severityThreshold: Medium
            source: Completion
          - blocking: true
            enabled: true
            name: Violence
            severityThreshold: Medium
            source: Prompt
          - blocking: true
            enabled: true
            name: Violence
            severityThreshold: Medium
            source: Completion
          - blocking: true
            enabled: true
            name: Jailbreak
            source: Prompt
          - blocking: true
            enabled: true
            name: Protected Material Text
            source: Completion
          - blocking: true
            enabled: true
            name: Protected Material Code
            source: Completion
          - blocking: true
            enabled: true
            name: Profanity
            source: Prompt
        mode: Asynchronous_filter
      raiPolicyName: raiPolicyName

Create SubscriptionRaiPolicy Resource

Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

Constructor syntax

new SubscriptionRaiPolicy(name: string, args?: SubscriptionRaiPolicyArgs, opts?: CustomResourceOptions);

@overload
def SubscriptionRaiPolicy(resource_name: str,
                          args: Optional[SubscriptionRaiPolicyArgs] = None,
                          opts: Optional[ResourceOptions] = None)

@overload
def SubscriptionRaiPolicy(resource_name: str,
                          opts: Optional[ResourceOptions] = None,
                          properties: Optional[RaiPolicyPropertiesArgs] = None,
                          rai_policy_name: Optional[str] = None,
                          tags: Optional[Mapping[str, str]] = None)

func NewSubscriptionRaiPolicy(ctx *Context, name string, args *SubscriptionRaiPolicyArgs, opts ...ResourceOption) (*SubscriptionRaiPolicy, error)

public SubscriptionRaiPolicy(string name, SubscriptionRaiPolicyArgs? args = null, CustomResourceOptions? opts = null)

public SubscriptionRaiPolicy(String name, SubscriptionRaiPolicyArgs args)
public SubscriptionRaiPolicy(String name, SubscriptionRaiPolicyArgs args, CustomResourceOptions options)

type: azure-native:cognitiveservices:SubscriptionRaiPolicy
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

Parameters

name string: The unique name of the resource.
args SubscriptionRaiPolicyArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

resource_name str: The unique name of the resource.
args SubscriptionRaiPolicyArgs: The arguments to resource properties.
opts ResourceOptions: Bag of options to control resource's behavior.

ctx Context: Context object for the current deployment.
name string: The unique name of the resource.
args SubscriptionRaiPolicyArgs: The arguments to resource properties.
opts ResourceOption: Bag of options to control resource's behavior.

name string: The unique name of the resource.
args SubscriptionRaiPolicyArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

name String: The unique name of the resource.
args SubscriptionRaiPolicyArgs: The arguments to resource properties.
options CustomResourceOptions: Bag of options to control resource's behavior.

Constructor example

The following reference example uses placeholder values for all input properties.

var subscriptionRaiPolicyResource = new AzureNative.CognitiveServices.SubscriptionRaiPolicy("subscriptionRaiPolicyResource", new()
{
    Properties = new AzureNative.CognitiveServices.Inputs.RaiPolicyPropertiesArgs
    {
        BasePolicyName = "string",
        ContentFilters = new[]
        {
            new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
            {
                Action = "string",
                Blocking = false,
                Enabled = false,
                Name = "string",
                SeverityThreshold = "string",
                Source = "string",
            },
        },
        CustomBlocklists = new[]
        {
            new AzureNative.CognitiveServices.Inputs.CustomBlocklistConfigArgs
            {
                Blocking = false,
                BlocklistName = "string",
                Source = "string",
            },
        },
        CustomTopics = new[]
        {
            new AzureNative.CognitiveServices.Inputs.CustomTopicConfigArgs
            {
                Blocking = false,
                Source = "string",
                TopicName = "string",
            },
        },
        Mode = "string",
        SafetyProviders = new[]
        {
            new AzureNative.CognitiveServices.Inputs.SafetyProviderConfigArgs
            {
                Blocking = false,
                SafetyProviderName = "string",
                Source = "string",
            },
        },
    },
    RaiPolicyName = "string",
    Tags = 
    {
        { "string", "string" },
    },
});

example, err := cognitiveservices.NewSubscriptionRaiPolicy(ctx, "subscriptionRaiPolicyResource", &cognitiveservices.SubscriptionRaiPolicyArgs{
	Properties: &cognitiveservices.RaiPolicyPropertiesArgs{
		BasePolicyName: pulumi.String("string"),
		ContentFilters: cognitiveservices.RaiPolicyContentFilterArray{
			&cognitiveservices.RaiPolicyContentFilterArgs{
				Action:            pulumi.String("string"),
				Blocking:          pulumi.Bool(false),
				Enabled:           pulumi.Bool(false),
				Name:              pulumi.String("string"),
				SeverityThreshold: pulumi.String("string"),
				Source:            pulumi.String("string"),
			},
		},
		CustomBlocklists: cognitiveservices.CustomBlocklistConfigArray{
			&cognitiveservices.CustomBlocklistConfigArgs{
				Blocking:      pulumi.Bool(false),
				BlocklistName: pulumi.String("string"),
				Source:        pulumi.String("string"),
			},
		},
		CustomTopics: cognitiveservices.CustomTopicConfigArray{
			&cognitiveservices.CustomTopicConfigArgs{
				Blocking:  pulumi.Bool(false),
				Source:    pulumi.String("string"),
				TopicName: pulumi.String("string"),
			},
		},
		Mode: pulumi.String("string"),
		SafetyProviders: cognitiveservices.SafetyProviderConfigArray{
			&cognitiveservices.SafetyProviderConfigArgs{
				Blocking:           pulumi.Bool(false),
				SafetyProviderName: pulumi.String("string"),
				Source:             pulumi.String("string"),
			},
		},
	},
	RaiPolicyName: pulumi.String("string"),
	Tags: pulumi.StringMap{
		"string": pulumi.String("string"),
	},
})

var subscriptionRaiPolicyResource = new SubscriptionRaiPolicy("subscriptionRaiPolicyResource", SubscriptionRaiPolicyArgs.builder()
    .properties(RaiPolicyPropertiesArgs.builder()
        .basePolicyName("string")
        .contentFilters(RaiPolicyContentFilterArgs.builder()
            .action("string")
            .blocking(false)
            .enabled(false)
            .name("string")
            .severityThreshold("string")
            .source("string")
            .build())
        .customBlocklists(CustomBlocklistConfigArgs.builder()
            .blocking(false)
            .blocklistName("string")
            .source("string")
            .build())
        .customTopics(CustomTopicConfigArgs.builder()
            .blocking(false)
            .source("string")
            .topicName("string")
            .build())
        .mode("string")
        .safetyProviders(SafetyProviderConfigArgs.builder()
            .blocking(false)
            .safetyProviderName("string")
            .source("string")
            .build())
        .build())
    .raiPolicyName("string")
    .tags(Map.of("string", "string"))
    .build());

subscription_rai_policy_resource = azure_native.cognitiveservices.SubscriptionRaiPolicy("subscriptionRaiPolicyResource",
    properties={
        "base_policy_name": "string",
        "content_filters": [{
            "action": "string",
            "blocking": False,
            "enabled": False,
            "name": "string",
            "severity_threshold": "string",
            "source": "string",
        }],
        "custom_blocklists": [{
            "blocking": False,
            "blocklist_name": "string",
            "source": "string",
        }],
        "custom_topics": [{
            "blocking": False,
            "source": "string",
            "topic_name": "string",
        }],
        "mode": "string",
        "safety_providers": [{
            "blocking": False,
            "safety_provider_name": "string",
            "source": "string",
        }],
    },
    rai_policy_name="string",
    tags={
        "string": "string",
    })

const subscriptionRaiPolicyResource = new azure_native.cognitiveservices.SubscriptionRaiPolicy("subscriptionRaiPolicyResource", {
    properties: {
        basePolicyName: "string",
        contentFilters: [{
            action: "string",
            blocking: false,
            enabled: false,
            name: "string",
            severityThreshold: "string",
            source: "string",
        }],
        customBlocklists: [{
            blocking: false,
            blocklistName: "string",
            source: "string",
        }],
        customTopics: [{
            blocking: false,
            source: "string",
            topicName: "string",
        }],
        mode: "string",
        safetyProviders: [{
            blocking: false,
            safetyProviderName: "string",
            source: "string",
        }],
    },
    raiPolicyName: "string",
    tags: {
        string: "string",
    },
});

type: azure-native:cognitiveservices:SubscriptionRaiPolicy
properties:
    properties:
        basePolicyName: string
        contentFilters:
            - action: string
              blocking: false
              enabled: false
              name: string
              severityThreshold: string
              source: string
        customBlocklists:
            - blocking: false
              blocklistName: string
              source: string
        customTopics:
            - blocking: false
              source: string
              topicName: string
        mode: string
        safetyProviders:
            - blocking: false
              safetyProviderName: string
              source: string
    raiPolicyName: string
    tags:
        string: string

SubscriptionRaiPolicy Resource Properties

To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

Inputs

In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

The SubscriptionRaiPolicy resource accepts the following input properties:

Properties Pulumi.AzureNative.CognitiveServices.Inputs.RaiPolicyProperties: Properties of Cognitive Services RaiPolicy.
RaiPolicyName string: The name of the RaiPolicy associated with the Cognitive Services Account
Tags Dictionary<string, string>: Resource tags.

Properties RaiPolicyPropertiesArgs: Properties of Cognitive Services RaiPolicy.
RaiPolicyName string: The name of the RaiPolicy associated with the Cognitive Services Account
Tags map[string]string: Resource tags.

properties RaiPolicyProperties: Properties of Cognitive Services RaiPolicy.
raiPolicyName String: The name of the RaiPolicy associated with the Cognitive Services Account
tags Map<String,String>: Resource tags.

properties RaiPolicyProperties: Properties of Cognitive Services RaiPolicy.
raiPolicyName string: The name of the RaiPolicy associated with the Cognitive Services Account
tags {[key: string]: string}: Resource tags.

properties RaiPolicyPropertiesArgs: Properties of Cognitive Services RaiPolicy.
rai_policy_name str: The name of the RaiPolicy associated with the Cognitive Services Account
tags Mapping[str, str]: Resource tags.

properties Property Map: Properties of Cognitive Services RaiPolicy.
raiPolicyName String: The name of the RaiPolicy associated with the Cognitive Services Account
tags Map<String>: Resource tags.

Outputs

All input properties are implicitly available as output properties. Additionally, the SubscriptionRaiPolicy resource produces the following output properties:

AzureApiVersion string: The Azure API version of the resource.
Etag string: Resource Etag.
Id string: The provider-assigned unique ID for this managed resource.
Name string: The name of the resource
SystemData Pulumi.AzureNative.CognitiveServices.Outputs.SystemDataResponse: Azure Resource Manager metadata containing createdBy and modifiedBy information.
Type string: The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"

AzureApiVersion string: The Azure API version of the resource.
Etag string: Resource Etag.
Id string: The provider-assigned unique ID for this managed resource.
Name string: The name of the resource
SystemData SystemDataResponse: Azure Resource Manager metadata containing createdBy and modifiedBy information.
Type string: The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"

azureApiVersion String: The Azure API version of the resource.
etag String: Resource Etag.
id String: The provider-assigned unique ID for this managed resource.
name String: The name of the resource
systemData SystemDataResponse: Azure Resource Manager metadata containing createdBy and modifiedBy information.
type String: The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"

azureApiVersion string: The Azure API version of the resource.
etag string: Resource Etag.
id string: The provider-assigned unique ID for this managed resource.
name string: The name of the resource
systemData SystemDataResponse: Azure Resource Manager metadata containing createdBy and modifiedBy information.
type string: The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"

azure_api_version str: The Azure API version of the resource.
etag str: Resource Etag.
id str: The provider-assigned unique ID for this managed resource.
name str: The name of the resource
system_data SystemDataResponse: Azure Resource Manager metadata containing createdBy and modifiedBy information.
type str: The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"

azureApiVersion String: The Azure API version of the resource.
etag String: Resource Etag.
id String: The provider-assigned unique ID for this managed resource.
name String: The name of the resource
systemData Property Map: Azure Resource Manager metadata containing createdBy and modifiedBy information.
type String: The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"

Supporting Types

ContentLevel, ContentLevelArgs

Low: Low
Medium: Medium
High: High

ContentLevelLow: Low
ContentLevelMedium: Medium
ContentLevelHigh: High

Low: Low
Medium: Medium
High: High

Low: Low
Medium: Medium
High: High

LOW: Low
MEDIUM: Medium
HIGH: High

"Low": Low
"Medium": Medium
"High": High

CustomBlocklistConfig, CustomBlocklistConfigArgs

Gets or sets the source to which filter applies.

Blocking bool: If blocking would occur.
BlocklistName string: Name of ContentFilter.
Source string | Pulumi.AzureNative.CognitiveServices.RaiPolicyContentSource: Content source to apply the Content Filters.

Blocking bool: If blocking would occur.
BlocklistName string: Name of ContentFilter.
Source string | RaiPolicyContentSource: Content source to apply the Content Filters.

blocking Boolean: If blocking would occur.
blocklistName String: Name of ContentFilter.
source String | RaiPolicyContentSource: Content source to apply the Content Filters.

blocking boolean: If blocking would occur.
blocklistName string: Name of ContentFilter.
source string | RaiPolicyContentSource: Content source to apply the Content Filters.

blocking bool: If blocking would occur.
blocklist_name str: Name of ContentFilter.
source str | RaiPolicyContentSource: Content source to apply the Content Filters.

blocking Boolean: If blocking would occur.
blocklistName String: Name of ContentFilter.
source String | "Prompt" | "Completion" | "PreToolCall" | "PostToolCall" | "PreRun" | "PostRun": Content source to apply the Content Filters.

CustomBlocklistConfigResponse, CustomBlocklistConfigResponseArgs

Gets or sets the source to which filter applies.

Blocking bool: If blocking would occur.
BlocklistName string: Name of ContentFilter.
Source string: Content source to apply the Content Filters.

Blocking bool: If blocking would occur.
BlocklistName string: Name of ContentFilter.
Source string: Content source to apply the Content Filters.

blocking Boolean: If blocking would occur.
blocklistName String: Name of ContentFilter.
source String: Content source to apply the Content Filters.

blocking boolean: If blocking would occur.
blocklistName string: Name of ContentFilter.
source string: Content source to apply the Content Filters.

blocking bool: If blocking would occur.
blocklist_name str: Name of ContentFilter.
source str: Content source to apply the Content Filters.

blocking Boolean: If blocking would occur.
blocklistName String: Name of ContentFilter.
source String: Content source to apply the Content Filters.

CustomTopicConfig, CustomTopicConfigArgs

Gets or sets the source to which filter applies.

Blocking bool: If blocking would occur.
Source string | Pulumi.AzureNative.CognitiveServices.RaiPolicyContentSource: Content source to apply the Content Filters.
TopicName string: Name of RAI topic.

Blocking bool: If blocking would occur.
Source string | RaiPolicyContentSource: Content source to apply the Content Filters.
TopicName string: Name of RAI topic.

blocking Boolean: If blocking would occur.
source String | RaiPolicyContentSource: Content source to apply the Content Filters.
topicName String: Name of RAI topic.

blocking boolean: If blocking would occur.
source string | RaiPolicyContentSource: Content source to apply the Content Filters.
topicName string: Name of RAI topic.

blocking bool: If blocking would occur.
source str | RaiPolicyContentSource: Content source to apply the Content Filters.
topic_name str: Name of RAI topic.

blocking Boolean: If blocking would occur.
source String | "Prompt" | "Completion" | "PreToolCall" | "PostToolCall" | "PreRun" | "PostRun": Content source to apply the Content Filters.
topicName String: Name of RAI topic.

CustomTopicConfigResponse, CustomTopicConfigResponseArgs

Gets or sets the source to which filter applies.

Blocking bool: If blocking would occur.
Source string: Content source to apply the Content Filters.
TopicName string: Name of RAI topic.

Blocking bool: If blocking would occur.
Source string: Content source to apply the Content Filters.
TopicName string: Name of RAI topic.

blocking Boolean: If blocking would occur.
source String: Content source to apply the Content Filters.
topicName String: Name of RAI topic.

blocking boolean: If blocking would occur.
source string: Content source to apply the Content Filters.
topicName string: Name of RAI topic.

blocking bool: If blocking would occur.
source str: Content source to apply the Content Filters.
topic_name str: Name of RAI topic.

blocking Boolean: If blocking would occur.
source String: Content source to apply the Content Filters.
topicName String: Name of RAI topic.

RaiActionType, RaiActionTypeArgs

None: None
BLOCKING: BLOCKING
ANNOTATING: ANNOTATING
HITL: HITL
RETRY: RETRY

RaiActionTypeNone: None
RaiActionTypeBLOCKING: BLOCKING
RaiActionTypeANNOTATING: ANNOTATING
RaiActionTypeHITL: HITL
RaiActionTypeRETRY: RETRY

None: None
BLOCKING: BLOCKING
ANNOTATING: ANNOTATING
HITL: HITL
RETRY: RETRY

None: None
BLOCKING: BLOCKING
ANNOTATING: ANNOTATING
HITL: HITL
RETRY: RETRY

NONE: None
BLOCKING: BLOCKING
ANNOTATING: ANNOTATING
HITL: HITL
RETRY: RETRY

"None": None
"BLOCKING": BLOCKING
"ANNOTATING": ANNOTATING
"HITL": HITL
"RETRY": RETRY

RaiPolicyContentFilter, RaiPolicyContentFilterArgs

Azure OpenAI Content Filter.

Action string | Pulumi.AzureNative.CognitiveServices.RaiActionType: The action types to apply to the content filters
Blocking bool: If blocking would occur.
Enabled bool: If the ContentFilter is enabled.
Name string: Name of ContentFilter.
SeverityThreshold string | Pulumi.AzureNative.CognitiveServices.ContentLevel: Level at which content is filtered.
Source string | Pulumi.AzureNative.CognitiveServices.RaiPolicyContentSource: Content source to apply the Content Filters.

Action string | RaiActionType: The action types to apply to the content filters
Blocking bool: If blocking would occur.
Enabled bool: If the ContentFilter is enabled.
Name string: Name of ContentFilter.
SeverityThreshold string | ContentLevel: Level at which content is filtered.
Source string | RaiPolicyContentSource: Content source to apply the Content Filters.

action String | RaiActionType: The action types to apply to the content filters
blocking Boolean: If blocking would occur.
enabled Boolean: If the ContentFilter is enabled.
name String: Name of ContentFilter.
severityThreshold String | ContentLevel: Level at which content is filtered.
source String | RaiPolicyContentSource: Content source to apply the Content Filters.

action string | RaiActionType: The action types to apply to the content filters
blocking boolean: If blocking would occur.
enabled boolean: If the ContentFilter is enabled.
name string: Name of ContentFilter.
severityThreshold string | ContentLevel: Level at which content is filtered.
source string | RaiPolicyContentSource: Content source to apply the Content Filters.

action str | RaiActionType: The action types to apply to the content filters
blocking bool: If blocking would occur.
enabled bool: If the ContentFilter is enabled.
name str: Name of ContentFilter.
severity_threshold str | ContentLevel: Level at which content is filtered.
source str | RaiPolicyContentSource: Content source to apply the Content Filters.

action String | "None" | "BLOCKING" | "ANNOTATING" | "HITL" | "RETRY": The action types to apply to the content filters
blocking Boolean: If blocking would occur.
enabled Boolean: If the ContentFilter is enabled.
name String: Name of ContentFilter.
severityThreshold String | "Low" | "Medium" | "High": Level at which content is filtered.
source String | "Prompt" | "Completion" | "PreToolCall" | "PostToolCall" | "PreRun" | "PostRun": Content source to apply the Content Filters.

RaiPolicyContentFilterResponse, RaiPolicyContentFilterResponseArgs

Azure OpenAI Content Filter.

Action string: The action types to apply to the content filters
Blocking bool: If blocking would occur.
Enabled bool: If the ContentFilter is enabled.
Name string: Name of ContentFilter.
SeverityThreshold string: Level at which content is filtered.
Source string: Content source to apply the Content Filters.

Action string: The action types to apply to the content filters
Blocking bool: If blocking would occur.
Enabled bool: If the ContentFilter is enabled.
Name string: Name of ContentFilter.
SeverityThreshold string: Level at which content is filtered.
Source string: Content source to apply the Content Filters.

action String: The action types to apply to the content filters
blocking Boolean: If blocking would occur.
enabled Boolean: If the ContentFilter is enabled.
name String: Name of ContentFilter.
severityThreshold String: Level at which content is filtered.
source String: Content source to apply the Content Filters.

action string: The action types to apply to the content filters
blocking boolean: If blocking would occur.
enabled boolean: If the ContentFilter is enabled.
name string: Name of ContentFilter.
severityThreshold string: Level at which content is filtered.
source string: Content source to apply the Content Filters.

action str: The action types to apply to the content filters
blocking bool: If blocking would occur.
enabled bool: If the ContentFilter is enabled.
name str: Name of ContentFilter.
severity_threshold str: Level at which content is filtered.
source str: Content source to apply the Content Filters.

action String: The action types to apply to the content filters
blocking Boolean: If blocking would occur.
enabled Boolean: If the ContentFilter is enabled.
name String: Name of ContentFilter.
severityThreshold String: Level at which content is filtered.
source String: Content source to apply the Content Filters.

RaiPolicyContentSource, RaiPolicyContentSourceArgs

Prompt: Prompt
Completion: Completion
PreToolCall: PreToolCall
PostToolCall: PostToolCall
PreRun: PreRun
PostRun: PostRun

RaiPolicyContentSourcePrompt: Prompt
RaiPolicyContentSourceCompletion: Completion
RaiPolicyContentSourcePreToolCall: PreToolCall
RaiPolicyContentSourcePostToolCall: PostToolCall
RaiPolicyContentSourcePreRun: PreRun
RaiPolicyContentSourcePostRun: PostRun

Prompt: Prompt
Completion: Completion
PreToolCall: PreToolCall
PostToolCall: PostToolCall
PreRun: PreRun
PostRun: PostRun

Prompt: Prompt
Completion: Completion
PreToolCall: PreToolCall
PostToolCall: PostToolCall
PreRun: PreRun
PostRun: PostRun

PROMPT: Prompt
COMPLETION: Completion
PRE_TOOL_CALL: PreToolCall
POST_TOOL_CALL: PostToolCall
PRE_RUN: PreRun
POST_RUN: PostRun

"Prompt": Prompt
"Completion": Completion
"PreToolCall": PreToolCall
"PostToolCall": PostToolCall
"PreRun": PreRun
"PostRun": PostRun

RaiPolicyMode, RaiPolicyModeArgs

Default: Default
Deferred: Deferred
Blocking: Blocking
Asynchronous_filter: Asynchronous_filter

RaiPolicyModeDefault: Default
RaiPolicyModeDeferred: Deferred
RaiPolicyModeBlocking: Blocking
RaiPolicyMode_Asynchronous_filter: Asynchronous_filter

Default: Default
Deferred: Deferred
Blocking: Blocking
Asynchronous_filter: Asynchronous_filter

Default: Default
Deferred: Deferred
Blocking: Blocking
Asynchronous_filter: Asynchronous_filter

DEFAULT: Default
DEFERRED: Deferred
BLOCKING: Blocking
ASYNCHRONOUS_FILTER: Asynchronous_filter

"Default": Default
"Deferred": Deferred
"Blocking": Blocking
"Asynchronous_filter": Asynchronous_filter

RaiPolicyProperties, RaiPolicyPropertiesArgs

Azure OpenAI Content Filters properties.

BasePolicyName string: Name of Rai policy.
ContentFilters List<Pulumi.AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilter>: The list of Content Filters.
CustomBlocklists List<Pulumi.AzureNative.CognitiveServices.Inputs.CustomBlocklistConfig>: The list of custom Blocklist.
CustomTopics List<Pulumi.AzureNative.CognitiveServices.Inputs.CustomTopicConfig>: The list of custom rai topics.
Mode string | Pulumi.AzureNative.CognitiveServices.RaiPolicyMode: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
SafetyProviders List<Pulumi.AzureNative.CognitiveServices.Inputs.SafetyProviderConfig>: The list of Safety Providers.

BasePolicyName string: Name of Rai policy.
ContentFilters []RaiPolicyContentFilter: The list of Content Filters.
CustomBlocklists []CustomBlocklistConfig: The list of custom Blocklist.
CustomTopics []CustomTopicConfig: The list of custom rai topics.
Mode string | RaiPolicyMode: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
SafetyProviders []SafetyProviderConfig: The list of Safety Providers.

basePolicyName String: Name of Rai policy.
contentFilters List<RaiPolicyContentFilter>: The list of Content Filters.
customBlocklists List<CustomBlocklistConfig>: The list of custom Blocklist.
customTopics List<CustomTopicConfig>: The list of custom rai topics.
mode String | RaiPolicyMode: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
safetyProviders List<SafetyProviderConfig>: The list of Safety Providers.

basePolicyName string: Name of Rai policy.
contentFilters RaiPolicyContentFilter[]: The list of Content Filters.
customBlocklists CustomBlocklistConfig[]: The list of custom Blocklist.
customTopics CustomTopicConfig[]: The list of custom rai topics.
mode string | RaiPolicyMode: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
safetyProviders SafetyProviderConfig[]: The list of Safety Providers.

base_policy_name str: Name of Rai policy.
content_filters Sequence[RaiPolicyContentFilter]: The list of Content Filters.
custom_blocklists Sequence[CustomBlocklistConfig]: The list of custom Blocklist.
custom_topics Sequence[CustomTopicConfig]: The list of custom rai topics.
mode str | RaiPolicyMode: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
safety_providers Sequence[SafetyProviderConfig]: The list of Safety Providers.

basePolicyName String: Name of Rai policy.
contentFilters List<Property Map>: The list of Content Filters.
customBlocklists List<Property Map>: The list of custom Blocklist.
customTopics List<Property Map>: The list of custom rai topics.
mode String | "Default" | "Deferred" | "Blocking" | "Asynchronous_filter": Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
safetyProviders List<Property Map>: The list of Safety Providers.

RaiPolicyPropertiesResponse, RaiPolicyPropertiesResponseArgs

Azure OpenAI Content Filters properties.

Type string: Content Filters policy type.
BasePolicyName string: Name of Rai policy.
ContentFilters List<Pulumi.AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterResponse>: The list of Content Filters.
CustomBlocklists List<Pulumi.AzureNative.CognitiveServices.Inputs.CustomBlocklistConfigResponse>: The list of custom Blocklist.
CustomTopics List<Pulumi.AzureNative.CognitiveServices.Inputs.CustomTopicConfigResponse>: The list of custom rai topics.
Mode string: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
SafetyProviders List<Pulumi.AzureNative.CognitiveServices.Inputs.SafetyProviderConfigResponse>: The list of Safety Providers.

Type string: Content Filters policy type.
BasePolicyName string: Name of Rai policy.
ContentFilters []RaiPolicyContentFilterResponse: The list of Content Filters.
CustomBlocklists []CustomBlocklistConfigResponse: The list of custom Blocklist.
CustomTopics []CustomTopicConfigResponse: The list of custom rai topics.
Mode string: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
SafetyProviders []SafetyProviderConfigResponse: The list of Safety Providers.

type String: Content Filters policy type.
basePolicyName String: Name of Rai policy.
contentFilters List<RaiPolicyContentFilterResponse>: The list of Content Filters.
customBlocklists List<CustomBlocklistConfigResponse>: The list of custom Blocklist.
customTopics List<CustomTopicConfigResponse>: The list of custom rai topics.
mode String: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
safetyProviders List<SafetyProviderConfigResponse>: The list of Safety Providers.

type string: Content Filters policy type.
basePolicyName string: Name of Rai policy.
contentFilters RaiPolicyContentFilterResponse[]: The list of Content Filters.
customBlocklists CustomBlocklistConfigResponse[]: The list of custom Blocklist.
customTopics CustomTopicConfigResponse[]: The list of custom rai topics.
mode string: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
safetyProviders SafetyProviderConfigResponse[]: The list of Safety Providers.

type str: Content Filters policy type.
base_policy_name str: Name of Rai policy.
content_filters Sequence[RaiPolicyContentFilterResponse]: The list of Content Filters.
custom_blocklists Sequence[CustomBlocklistConfigResponse]: The list of custom Blocklist.
custom_topics Sequence[CustomTopicConfigResponse]: The list of custom rai topics.
mode str: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
safety_providers Sequence[SafetyProviderConfigResponse]: The list of Safety Providers.

type String: Content Filters policy type.
basePolicyName String: Name of Rai policy.
contentFilters List<Property Map>: The list of Content Filters.
customBlocklists List<Property Map>: The list of custom Blocklist.
customTopics List<Property Map>: The list of custom rai topics.
mode String: Rai policy mode. The enum value mapping is as below: Default = 0, Deferred=1, Blocking=2, Asynchronous_filter =3. Please use 'Asynchronous_filter' after 2025-06-01. It is the same as 'Deferred' in previous version.
safetyProviders List<Property Map>: The list of Safety Providers.

SafetyProviderConfig, SafetyProviderConfigArgs

Gets or sets the source to which safety providers applies.

Blocking bool: If blocking would occur.
SafetyProviderName string: Name of RAI Safety Provider.
Source string | Pulumi.AzureNative.CognitiveServices.RaiPolicyContentSource: Content source to apply the Content Filters.

Blocking bool: If blocking would occur.
SafetyProviderName string: Name of RAI Safety Provider.
Source string | RaiPolicyContentSource: Content source to apply the Content Filters.

blocking Boolean: If blocking would occur.
safetyProviderName String: Name of RAI Safety Provider.
source String | RaiPolicyContentSource: Content source to apply the Content Filters.

blocking boolean: If blocking would occur.
safetyProviderName string: Name of RAI Safety Provider.
source string | RaiPolicyContentSource: Content source to apply the Content Filters.

blocking bool: If blocking would occur.
safety_provider_name str: Name of RAI Safety Provider.
source str | RaiPolicyContentSource: Content source to apply the Content Filters.

blocking Boolean: If blocking would occur.
safetyProviderName String: Name of RAI Safety Provider.
source String | "Prompt" | "Completion" | "PreToolCall" | "PostToolCall" | "PreRun" | "PostRun": Content source to apply the Content Filters.

SafetyProviderConfigResponse, SafetyProviderConfigResponseArgs

Gets or sets the source to which safety providers applies.

Blocking bool: If blocking would occur.
SafetyProviderName string: Name of RAI Safety Provider.
Source string: Content source to apply the Content Filters.

Blocking bool: If blocking would occur.
SafetyProviderName string: Name of RAI Safety Provider.
Source string: Content source to apply the Content Filters.

blocking Boolean: If blocking would occur.
safetyProviderName String: Name of RAI Safety Provider.
source String: Content source to apply the Content Filters.

blocking boolean: If blocking would occur.
safetyProviderName string: Name of RAI Safety Provider.
source string: Content source to apply the Content Filters.

blocking bool: If blocking would occur.
safety_provider_name str: Name of RAI Safety Provider.
source str: Content source to apply the Content Filters.

blocking Boolean: If blocking would occur.
safetyProviderName String: Name of RAI Safety Provider.
source String: Content source to apply the Content Filters.

SystemDataResponse, SystemDataResponseArgs

Metadata pertaining to creation and last modification of the resource.

CreatedAt string: The timestamp of resource creation (UTC).
CreatedBy string: The identity that created the resource.
CreatedByType string: The type of identity that created the resource.
LastModifiedAt string: The timestamp of resource last modification (UTC)
LastModifiedBy string: The identity that last modified the resource.
LastModifiedByType string: The type of identity that last modified the resource.

CreatedAt string: The timestamp of resource creation (UTC).
CreatedBy string: The identity that created the resource.
CreatedByType string: The type of identity that created the resource.
LastModifiedAt string: The timestamp of resource last modification (UTC)
LastModifiedBy string: The identity that last modified the resource.
LastModifiedByType string: The type of identity that last modified the resource.

createdAt String: The timestamp of resource creation (UTC).
createdBy String: The identity that created the resource.
createdByType String: The type of identity that created the resource.
lastModifiedAt String: The timestamp of resource last modification (UTC)
lastModifiedBy String: The identity that last modified the resource.
lastModifiedByType String: The type of identity that last modified the resource.

createdAt string: The timestamp of resource creation (UTC).
createdBy string: The identity that created the resource.
createdByType string: The type of identity that created the resource.
lastModifiedAt string: The timestamp of resource last modification (UTC)
lastModifiedBy string: The identity that last modified the resource.
lastModifiedByType string: The type of identity that last modified the resource.

created_at str: The timestamp of resource creation (UTC).
created_by str: The identity that created the resource.
created_by_type str: The type of identity that created the resource.
last_modified_at str: The timestamp of resource last modification (UTC)
last_modified_by str: The identity that last modified the resource.
last_modified_by_type str: The type of identity that last modified the resource.

createdAt String: The timestamp of resource creation (UTC).
createdBy String: The identity that created the resource.
createdByType String: The type of identity that created the resource.
lastModifiedAt String: The timestamp of resource last modification (UTC)
lastModifiedBy String: The identity that last modified the resource.
lastModifiedByType String: The type of identity that last modified the resource.

Import

An existing resource can be imported using its type token, name, and identifier, e.g.

$ pulumi import azure-native:cognitiveservices:SubscriptionRaiPolicy raiPolicyName /subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/raiPolicy/{raiPolicyName}

To learn more about importing existing cloud resources, see Importing resources.

Package Details

Repository: Azure Native pulumi/pulumi-azure-native
License: Apache-2.0

This is the latest version of Azure Native. Use the Azure Native v2 docs if using the v2 version of this package.

Azure Native v3.13.0 published on Wednesday, Jan 28, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-azure-native

azure-native.cognitiveservices.SubscriptionRaiPolicy

On this page

On this page

Example Usage

PutRaiPolicy

Create SubscriptionRaiPolicy Resource

Constructor syntax

Parameters

Constructor example

SubscriptionRaiPolicy Resource Properties

Inputs

Outputs

Supporting Types

ContentLevel, ContentLevelArgs

CustomBlocklistConfig, CustomBlocklistConfigArgs

CustomBlocklistConfigResponse, CustomBlocklistConfigResponseArgs

CustomTopicConfig, CustomTopicConfigArgs

CustomTopicConfigResponse, CustomTopicConfigResponseArgs

RaiActionType, RaiActionTypeArgs

RaiPolicyContentFilter, RaiPolicyContentFilterArgs

RaiPolicyContentFilterResponse, RaiPolicyContentFilterResponseArgs

RaiPolicyContentSource, RaiPolicyContentSourceArgs

RaiPolicyMode, RaiPolicyModeArgs

RaiPolicyProperties, RaiPolicyPropertiesArgs

RaiPolicyPropertiesResponse, RaiPolicyPropertiesResponseArgs

SafetyProviderConfig, SafetyProviderConfigArgs

SafetyProviderConfigResponse, SafetyProviderConfigResponseArgs

SystemDataResponse, SystemDataResponseArgs

Import

Package Details

On this page

On this page