Docs Home Pulumi IaC Pulumi ESC Pulumi Cloud Packages Tutorials
  1. Packages
  2. Azure Native
  3. API Docs
  4. cognitiveservices
  5. RaiPolicy
This is the latest version of Azure Native. Use the Azure Native v1 docs if using the v1 version of this package.
Azure Native v2.89.1 published on Sunday, Mar 2, 2025 by Pulumi
pulumi/pulumi-azure-native

azure-native.cognitiveservices.RaiPolicy

Explore with Pulumi AI

azure-native logo
This is the latest version of Azure Native. Use the Azure Native v1 docs if using the v1 version of this package.
Azure Native v2.89.1 published on Sunday, Mar 2, 2025 by Pulumi
pulumi/pulumi-azure-native

    Cognitive Services RaiPolicy. Azure REST API version: 2023-10-01-preview.

    Other available API versions: 2024-04-01-preview, 2024-06-01-preview, 2024-10-01.

    Example Usage

    PutRaiPolicy

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

return await Deployment.RunAsync(() => 
{
    var raiPolicy = new AzureNative.CognitiveServices.RaiPolicy("raiPolicy", new()
    {
        AccountName = "accountName",
        Properties = new AzureNative.CognitiveServices.Inputs.RaiPolicyPropertiesArgs
        {
            BasePolicyName = "Microsoft.Default",
            ContentFilters = new[]
            {
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    AllowedContentLevel = AzureNative.CognitiveServices.AllowedContentLevel.High,
                    Blocking = false,
                    Enabled = false,
                    Name = "hate",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Prompt,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    AllowedContentLevel = AzureNative.CognitiveServices.AllowedContentLevel.Medium,
                    Blocking = true,
                    Enabled = true,
                    Name = "hate",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Completion,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    AllowedContentLevel = AzureNative.CognitiveServices.AllowedContentLevel.High,
                    Blocking = true,
                    Enabled = true,
                    Name = "sexual",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Prompt,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    AllowedContentLevel = AzureNative.CognitiveServices.AllowedContentLevel.Medium,
                    Blocking = true,
                    Enabled = true,
                    Name = "sexual",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Completion,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    AllowedContentLevel = AzureNative.CognitiveServices.AllowedContentLevel.High,
                    Blocking = true,
                    Enabled = true,
                    Name = "selfharm",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Prompt,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    AllowedContentLevel = AzureNative.CognitiveServices.AllowedContentLevel.Medium,
                    Blocking = true,
                    Enabled = true,
                    Name = "selfharm",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Completion,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    AllowedContentLevel = AzureNative.CognitiveServices.AllowedContentLevel.Medium,
                    Blocking = true,
                    Enabled = true,
                    Name = "violence",
                    Source = AzureNative.CognitiveServices.RaiPolicyContentSource.Prompt,
                },
                new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
                {
                    AllowedContentLevel = AzureNative.CognitiveServices.AllowedContentLevel.Medium,
                    Blocking = true,
                    Enabled = true,
                    Name = "violence",
                    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.Deferred,
        },
        RaiPolicyName = "raiPolicyName",
        ResourceGroupName = "resourceGroupName",
    });

});

    package main

import (
	cognitiveservices "github.com/pulumi/pulumi-azure-native-sdk/cognitiveservices/v2"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := cognitiveservices.NewRaiPolicy(ctx, "raiPolicy", &cognitiveservices.RaiPolicyArgs{
			AccountName: pulumi.String("accountName"),
			Properties: &cognitiveservices.RaiPolicyPropertiesArgs{
				BasePolicyName: pulumi.String("Microsoft.Default"),
				ContentFilters: cognitiveservices.RaiPolicyContentFilterArray{
					&cognitiveservices.RaiPolicyContentFilterArgs{
						AllowedContentLevel: pulumi.String(cognitiveservices.AllowedContentLevelHigh),
						Blocking:            pulumi.Bool(false),
						Enabled:             pulumi.Bool(false),
						Name:                pulumi.String("hate"),
						Source:              pulumi.String(cognitiveservices.RaiPolicyContentSourcePrompt),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						AllowedContentLevel: pulumi.String(cognitiveservices.AllowedContentLevelMedium),
						Blocking:            pulumi.Bool(true),
						Enabled:             pulumi.Bool(true),
						Name:                pulumi.String("hate"),
						Source:              pulumi.String(cognitiveservices.RaiPolicyContentSourceCompletion),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						AllowedContentLevel: pulumi.String(cognitiveservices.AllowedContentLevelHigh),
						Blocking:            pulumi.Bool(true),
						Enabled:             pulumi.Bool(true),
						Name:                pulumi.String("sexual"),
						Source:              pulumi.String(cognitiveservices.RaiPolicyContentSourcePrompt),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						AllowedContentLevel: pulumi.String(cognitiveservices.AllowedContentLevelMedium),
						Blocking:            pulumi.Bool(true),
						Enabled:             pulumi.Bool(true),
						Name:                pulumi.String("sexual"),
						Source:              pulumi.String(cognitiveservices.RaiPolicyContentSourceCompletion),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						AllowedContentLevel: pulumi.String(cognitiveservices.AllowedContentLevelHigh),
						Blocking:            pulumi.Bool(true),
						Enabled:             pulumi.Bool(true),
						Name:                pulumi.String("selfharm"),
						Source:              pulumi.String(cognitiveservices.RaiPolicyContentSourcePrompt),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						AllowedContentLevel: pulumi.String(cognitiveservices.AllowedContentLevelMedium),
						Blocking:            pulumi.Bool(true),
						Enabled:             pulumi.Bool(true),
						Name:                pulumi.String("selfharm"),
						Source:              pulumi.String(cognitiveservices.RaiPolicyContentSourceCompletion),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						AllowedContentLevel: pulumi.String(cognitiveservices.AllowedContentLevelMedium),
						Blocking:            pulumi.Bool(true),
						Enabled:             pulumi.Bool(true),
						Name:                pulumi.String("violence"),
						Source:              pulumi.String(cognitiveservices.RaiPolicyContentSourcePrompt),
					},
					&cognitiveservices.RaiPolicyContentFilterArgs{
						AllowedContentLevel: pulumi.String(cognitiveservices.AllowedContentLevelMedium),
						Blocking:            pulumi.Bool(true),
						Enabled:             pulumi.Bool(true),
						Name:                pulumi.String("violence"),
						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.RaiPolicyModeDeferred),
			},
			RaiPolicyName:     pulumi.String("raiPolicyName"),
			ResourceGroupName: pulumi.String("resourceGroupName"),
		})
		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.RaiPolicy;
import com.pulumi.azurenative.cognitiveservices.RaiPolicyArgs;
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 raiPolicy = new RaiPolicy("raiPolicy", RaiPolicyArgs.builder()
            .accountName("accountName")
            .properties(RaiPolicyPropertiesArgs.builder()
                .basePolicyName("Microsoft.Default")
                .contentFilters(                
                    RaiPolicyContentFilterArgs.builder()
                        .allowedContentLevel("High")
                        .blocking(false)
                        .enabled(false)
                        .name("hate")
                        .source("Prompt")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .allowedContentLevel("Medium")
                        .blocking(true)
                        .enabled(true)
                        .name("hate")
                        .source("Completion")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .allowedContentLevel("High")
                        .blocking(true)
                        .enabled(true)
                        .name("sexual")
                        .source("Prompt")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .allowedContentLevel("Medium")
                        .blocking(true)
                        .enabled(true)
                        .name("sexual")
                        .source("Completion")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .allowedContentLevel("High")
                        .blocking(true)
                        .enabled(true)
                        .name("selfharm")
                        .source("Prompt")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .allowedContentLevel("Medium")
                        .blocking(true)
                        .enabled(true)
                        .name("selfharm")
                        .source("Completion")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .allowedContentLevel("Medium")
                        .blocking(true)
                        .enabled(true)
                        .name("violence")
                        .source("Prompt")
                        .build(),
                    RaiPolicyContentFilterArgs.builder()
                        .allowedContentLevel("Medium")
                        .blocking(true)
                        .enabled(true)
                        .name("violence")
                        .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("Deferred")
                .build())
            .raiPolicyName("raiPolicyName")
            .resourceGroupName("resourceGroupName")
            .build());

    }
}

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

const raiPolicy = new azure_native.cognitiveservices.RaiPolicy("raiPolicy", {
    accountName: "accountName",
    properties: {
        basePolicyName: "Microsoft.Default",
        contentFilters: [
            {
                allowedContentLevel: azure_native.cognitiveservices.AllowedContentLevel.High,
                blocking: false,
                enabled: false,
                name: "hate",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Prompt,
            },
            {
                allowedContentLevel: azure_native.cognitiveservices.AllowedContentLevel.Medium,
                blocking: true,
                enabled: true,
                name: "hate",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Completion,
            },
            {
                allowedContentLevel: azure_native.cognitiveservices.AllowedContentLevel.High,
                blocking: true,
                enabled: true,
                name: "sexual",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Prompt,
            },
            {
                allowedContentLevel: azure_native.cognitiveservices.AllowedContentLevel.Medium,
                blocking: true,
                enabled: true,
                name: "sexual",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Completion,
            },
            {
                allowedContentLevel: azure_native.cognitiveservices.AllowedContentLevel.High,
                blocking: true,
                enabled: true,
                name: "selfharm",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Prompt,
            },
            {
                allowedContentLevel: azure_native.cognitiveservices.AllowedContentLevel.Medium,
                blocking: true,
                enabled: true,
                name: "selfharm",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Completion,
            },
            {
                allowedContentLevel: azure_native.cognitiveservices.AllowedContentLevel.Medium,
                blocking: true,
                enabled: true,
                name: "violence",
                source: azure_native.cognitiveservices.RaiPolicyContentSource.Prompt,
            },
            {
                allowedContentLevel: azure_native.cognitiveservices.AllowedContentLevel.Medium,
                blocking: true,
                enabled: true,
                name: "violence",
                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.Deferred,
    },
    raiPolicyName: "raiPolicyName",
    resourceGroupName: "resourceGroupName",
});

    import pulumi
import pulumi_azure_native as azure_native

rai_policy = azure_native.cognitiveservices.RaiPolicy("raiPolicy",
    account_name="accountName",
    properties={
        "base_policy_name": "Microsoft.Default",
        "content_filters": [
            {
                "allowed_content_level": azure_native.cognitiveservices.AllowedContentLevel.HIGH,
                "blocking": False,
                "enabled": False,
                "name": "hate",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.PROMPT,
            },
            {
                "allowed_content_level": azure_native.cognitiveservices.AllowedContentLevel.MEDIUM,
                "blocking": True,
                "enabled": True,
                "name": "hate",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.COMPLETION,
            },
            {
                "allowed_content_level": azure_native.cognitiveservices.AllowedContentLevel.HIGH,
                "blocking": True,
                "enabled": True,
                "name": "sexual",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.PROMPT,
            },
            {
                "allowed_content_level": azure_native.cognitiveservices.AllowedContentLevel.MEDIUM,
                "blocking": True,
                "enabled": True,
                "name": "sexual",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.COMPLETION,
            },
            {
                "allowed_content_level": azure_native.cognitiveservices.AllowedContentLevel.HIGH,
                "blocking": True,
                "enabled": True,
                "name": "selfharm",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.PROMPT,
            },
            {
                "allowed_content_level": azure_native.cognitiveservices.AllowedContentLevel.MEDIUM,
                "blocking": True,
                "enabled": True,
                "name": "selfharm",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.COMPLETION,
            },
            {
                "allowed_content_level": azure_native.cognitiveservices.AllowedContentLevel.MEDIUM,
                "blocking": True,
                "enabled": True,
                "name": "violence",
                "source": azure_native.cognitiveservices.RaiPolicyContentSource.PROMPT,
            },
            {
                "allowed_content_level": azure_native.cognitiveservices.AllowedContentLevel.MEDIUM,
                "blocking": True,
                "enabled": True,
                "name": "violence",
                "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.DEFERRED,
    },
    rai_policy_name="raiPolicyName",
    resource_group_name="resourceGroupName")

    resources:
  raiPolicy:
    type: azure-native:cognitiveservices:RaiPolicy
    properties:
      accountName: accountName
      properties:
        basePolicyName: Microsoft.Default
        contentFilters:
          - allowedContentLevel: High
            blocking: false
            enabled: false
            name: hate
            source: Prompt
          - allowedContentLevel: Medium
            blocking: true
            enabled: true
            name: hate
            source: Completion
          - allowedContentLevel: High
            blocking: true
            enabled: true
            name: sexual
            source: Prompt
          - allowedContentLevel: Medium
            blocking: true
            enabled: true
            name: sexual
            source: Completion
          - allowedContentLevel: High
            blocking: true
            enabled: true
            name: selfharm
            source: Prompt
          - allowedContentLevel: Medium
            blocking: true
            enabled: true
            name: selfharm
            source: Completion
          - allowedContentLevel: Medium
            blocking: true
            enabled: true
            name: violence
            source: Prompt
          - allowedContentLevel: Medium
            blocking: true
            enabled: true
            name: violence
            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: Deferred
      raiPolicyName: raiPolicyName
      resourceGroupName: resourceGroupName

    Create RaiPolicy Resource

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

    Constructor syntax

    new RaiPolicy(name: string, args: RaiPolicyArgs, opts?: CustomResourceOptions);
    @overload
def RaiPolicy(resource_name: str,
              args: RaiPolicyArgs,
              opts: Optional[ResourceOptions] = None)

@overload
def RaiPolicy(resource_name: str,
              opts: Optional[ResourceOptions] = None,
              account_name: Optional[str] = None,
              resource_group_name: Optional[str] = None,
              properties: Optional[RaiPolicyPropertiesArgs] = None,
              rai_policy_name: Optional[str] = None,
              tags: Optional[Mapping[str, str]] = None)
    func NewRaiPolicy(ctx *Context, name string, args RaiPolicyArgs, opts ...ResourceOption) (*RaiPolicy, error)
    public RaiPolicy(string name, RaiPolicyArgs args, CustomResourceOptions? opts = null)
    public RaiPolicy(String name, RaiPolicyArgs args)
public RaiPolicy(String name, RaiPolicyArgs args, CustomResourceOptions options)

    type: azure-native:cognitiveservices:RaiPolicy
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 RaiPolicyArgs
    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 RaiPolicyArgs
    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 RaiPolicyArgs
    The arguments to resource properties.
    opts ResourceOption
    Bag of options to control resource's behavior.
    name string
    The unique name of the resource.
    args RaiPolicyArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    name String
    The unique name of the resource.
    args RaiPolicyArgs
    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 raiPolicyResource = new AzureNative.CognitiveServices.RaiPolicy("raiPolicyResource", new()
{
    AccountName = "string",
    ResourceGroupName = "string",
    Properties = new AzureNative.CognitiveServices.Inputs.RaiPolicyPropertiesArgs
    {
        BasePolicyName = "string",
        CompletionBlocklists = new[]
        {
            new AzureNative.CognitiveServices.Inputs.RaiBlocklistConfigArgs
            {
                Blocking = false,
                BlocklistName = "string",
            },
        },
        ContentFilters = new[]
        {
            new AzureNative.CognitiveServices.Inputs.RaiPolicyContentFilterArgs
            {
                AllowedContentLevel = "string",
                Blocking = false,
                Enabled = false,
                Name = "string",
                Source = "string",
            },
        },
        Mode = "string",
        PromptBlocklists = new[]
        {
            new AzureNative.CognitiveServices.Inputs.RaiBlocklistConfigArgs
            {
                Blocking = false,
                BlocklistName = "string",
            },
        },
    },
    RaiPolicyName = "string",
    Tags = 
    {
        { "string", "string" },
    },
});

    example, err := cognitiveservices.NewRaiPolicy(ctx, "raiPolicyResource", &cognitiveservices.RaiPolicyArgs{
	AccountName:       pulumi.String("string"),
	ResourceGroupName: pulumi.String("string"),
	Properties: &cognitiveservices.RaiPolicyPropertiesArgs{
		BasePolicyName: pulumi.String("string"),
		CompletionBlocklists: cognitiveservices.RaiBlocklistConfigArray{
			&cognitiveservices.RaiBlocklistConfigArgs{
				Blocking:      pulumi.Bool(false),
				BlocklistName: pulumi.String("string"),
			},
		},
		ContentFilters: cognitiveservices.RaiPolicyContentFilterArray{
			&cognitiveservices.RaiPolicyContentFilterArgs{
				AllowedContentLevel: pulumi.String("string"),
				Blocking:            pulumi.Bool(false),
				Enabled:             pulumi.Bool(false),
				Name:                pulumi.String("string"),
				Source:              pulumi.String("string"),
			},
		},
		Mode: pulumi.String("string"),
		PromptBlocklists: cognitiveservices.RaiBlocklistConfigArray{
			&cognitiveservices.RaiBlocklistConfigArgs{
				Blocking:      pulumi.Bool(false),
				BlocklistName: pulumi.String("string"),
			},
		},
	},
	RaiPolicyName: pulumi.String("string"),
	Tags: pulumi.StringMap{
		"string": pulumi.String("string"),
	},
})

    var raiPolicyResource = new RaiPolicy("raiPolicyResource", RaiPolicyArgs.builder()
    .accountName("string")
    .resourceGroupName("string")
    .properties(RaiPolicyPropertiesArgs.builder()
        .basePolicyName("string")
        .completionBlocklists(RaiBlocklistConfigArgs.builder()
            .blocking(false)
            .blocklistName("string")
            .build())
        .contentFilters(RaiPolicyContentFilterArgs.builder()
            .allowedContentLevel("string")
            .blocking(false)
            .enabled(false)
            .name("string")
            .source("string")
            .build())
        .mode("string")
        .promptBlocklists(RaiBlocklistConfigArgs.builder()
            .blocking(false)
            .blocklistName("string")
            .build())
        .build())
    .raiPolicyName("string")
    .tags(Map.of("string", "string"))
    .build());

    rai_policy_resource = azure_native.cognitiveservices.RaiPolicy("raiPolicyResource",
    account_name="string",
    resource_group_name="string",
    properties={
        "base_policy_name": "string",
        "completion_blocklists": [{
            "blocking": False,
            "blocklist_name": "string",
        }],
        "content_filters": [{
            "allowed_content_level": "string",
            "blocking": False,
            "enabled": False,
            "name": "string",
            "source": "string",
        }],
        "mode": "string",
        "prompt_blocklists": [{
            "blocking": False,
            "blocklist_name": "string",
        }],
    },
    rai_policy_name="string",
    tags={
        "string": "string",
    })

    const raiPolicyResource = new azure_native.cognitiveservices.RaiPolicy("raiPolicyResource", {
    accountName: "string",
    resourceGroupName: "string",
    properties: {
        basePolicyName: "string",
        completionBlocklists: [{
            blocking: false,
            blocklistName: "string",
        }],
        contentFilters: [{
            allowedContentLevel: "string",
            blocking: false,
            enabled: false,
            name: "string",
            source: "string",
        }],
        mode: "string",
        promptBlocklists: [{
            blocking: false,
            blocklistName: "string",
        }],
    },
    raiPolicyName: "string",
    tags: {
        string: "string",
    },
});

    type: azure-native:cognitiveservices:RaiPolicy
properties:
    accountName: string
    properties:
        basePolicyName: string
        completionBlocklists:
            - blocking: false
              blocklistName: string
        contentFilters:
            - allowedContentLevel: string
              blocking: false
              enabled: false
              name: string
              source: string
        mode: string
        promptBlocklists:
            - blocking: false
              blocklistName: string
    raiPolicyName: string
    resourceGroupName: string
    tags:
        string: string

    RaiPolicy 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 RaiPolicy resource accepts the following input properties:

    AccountName string
    The name of Cognitive Services account.
    ResourceGroupName string
    The name of the resource group. The name is case insensitive.
    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.
    AccountName string
    The name of Cognitive Services account.
    ResourceGroupName string
    The name of the resource group. The name is case insensitive.
    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.
    accountName String
    The name of Cognitive Services account.
    resourceGroupName String
    The name of the resource group. The name is case insensitive.
    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.
    accountName string
    The name of Cognitive Services account.
    resourceGroupName string
    The name of the resource group. The name is case insensitive.
    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.
    account_name str
    The name of Cognitive Services account.
    resource_group_name str
    The name of the resource group. The name is case insensitive.
    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.
    accountName String
    The name of Cognitive Services account.
    resourceGroupName String
    The name of the resource group. The name is case insensitive.
    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 RaiPolicy resource produces the following output properties:

    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
    Metadata pertaining to creation and last modification of the resource.
    Type string
    The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"
    Etag string
    Resource Etag.
    Id string
    The provider-assigned unique ID for this managed resource.
    Name string
    The name of the resource
    SystemData SystemDataResponse
    Metadata pertaining to creation and last modification of the resource.
    Type string
    The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"
    etag String
    Resource Etag.
    id String
    The provider-assigned unique ID for this managed resource.
    name String
    The name of the resource
    systemData SystemDataResponse
    Metadata pertaining to creation and last modification of the resource.
    type String
    The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"
    etag string
    Resource Etag.
    id string
    The provider-assigned unique ID for this managed resource.
    name string
    The name of the resource
    systemData SystemDataResponse
    Metadata pertaining to creation and last modification of the resource.
    type string
    The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"
    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
    Metadata pertaining to creation and last modification of the resource.
    type str
    The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"
    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
    Metadata pertaining to creation and last modification of the resource.
    type String
    The type of the resource. E.g. "Microsoft.Compute/virtualMachines" or "Microsoft.Storage/storageAccounts"

    Supporting Types

    AllowedContentLevel, AllowedContentLevelArgs

    Low
    Low
    Medium
    Medium
    High
    High
    AllowedContentLevelLow
    Low
    AllowedContentLevelMedium
    Medium
    AllowedContentLevelHigh
    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

    RaiBlocklistConfig, RaiBlocklistConfigArgs

    Blocking bool
    If blocking would occur.
    BlocklistName string
    Name of ContentFilter.
    Blocking bool
    If blocking would occur.
    BlocklistName string
    Name of ContentFilter.
    blocking Boolean
    If blocking would occur.
    blocklistName String
    Name of ContentFilter.
    blocking boolean
    If blocking would occur.
    blocklistName string
    Name of ContentFilter.
    blocking bool
    If blocking would occur.
    blocklist_name str
    Name of ContentFilter.
    blocking Boolean
    If blocking would occur.
    blocklistName String
    Name of ContentFilter.

    RaiBlocklistConfigResponse, RaiBlocklistConfigResponseArgs

    Blocking bool
    If blocking would occur.
    BlocklistName string
    Name of ContentFilter.
    Blocking bool
    If blocking would occur.
    BlocklistName string
    Name of ContentFilter.
    blocking Boolean
    If blocking would occur.
    blocklistName String
    Name of ContentFilter.
    blocking boolean
    If blocking would occur.
    blocklistName string
    Name of ContentFilter.
    blocking bool
    If blocking would occur.
    blocklist_name str
    Name of ContentFilter.
    blocking Boolean
    If blocking would occur.
    blocklistName String
    Name of ContentFilter.

    RaiPolicyContentFilter, RaiPolicyContentFilterArgs

    AllowedContentLevel string | Pulumi.AzureNative.CognitiveServices.AllowedContentLevel
    Level at which content is filtered.
    Blocking bool
    If blocking would occur.
    Enabled bool
    If the ContentFilter is enabled.
    Name string
    Name of ContentFilter.
    Source string | Pulumi.AzureNative.CognitiveServices.RaiPolicyContentSource
    Content source to apply the Content Filters.
    AllowedContentLevel string | AllowedContentLevel
    Level at which content is filtered.
    Blocking bool
    If blocking would occur.
    Enabled bool
    If the ContentFilter is enabled.
    Name string
    Name of ContentFilter.
    Source string | RaiPolicyContentSource
    Content source to apply the Content Filters.
    allowedContentLevel String | AllowedContentLevel
    Level at which content is filtered.
    blocking Boolean
    If blocking would occur.
    enabled Boolean
    If the ContentFilter is enabled.
    name String
    Name of ContentFilter.
    source String | RaiPolicyContentSource
    Content source to apply the Content Filters.
    allowedContentLevel string | AllowedContentLevel
    Level at which content is filtered.
    blocking boolean
    If blocking would occur.
    enabled boolean
    If the ContentFilter is enabled.
    name string
    Name of ContentFilter.
    source string | RaiPolicyContentSource
    Content source to apply the Content Filters.
    allowed_content_level str | AllowedContentLevel
    Level at which content is filtered.
    blocking bool
    If blocking would occur.
    enabled bool
    If the ContentFilter is enabled.
    name str
    Name of ContentFilter.
    source str | RaiPolicyContentSource
    Content source to apply the Content Filters.
    allowedContentLevel String | "Low" | "Medium" | "High"
    Level at which content is filtered.
    blocking Boolean
    If blocking would occur.
    enabled Boolean
    If the ContentFilter is enabled.
    name String
    Name of ContentFilter.
    source String | "Prompt" | "Completion"
    Content source to apply the Content Filters.

    RaiPolicyContentFilterResponse, RaiPolicyContentFilterResponseArgs

    AllowedContentLevel string
    Level at which content is filtered.
    Blocking bool
    If blocking would occur.
    Enabled bool
    If the ContentFilter is enabled.
    Name string
    Name of ContentFilter.
    Source string
    Content source to apply the Content Filters.
    AllowedContentLevel string
    Level at which content is filtered.
    Blocking bool
    If blocking would occur.
    Enabled bool
    If the ContentFilter is enabled.
    Name string
    Name of ContentFilter.
    Source string
    Content source to apply the Content Filters.
    allowedContentLevel String
    Level at which content is filtered.
    blocking Boolean
    If blocking would occur.
    enabled Boolean
    If the ContentFilter is enabled.
    name String
    Name of ContentFilter.
    source String
    Content source to apply the Content Filters.
    allowedContentLevel string
    Level at which content is filtered.
    blocking boolean
    If blocking would occur.
    enabled boolean
    If the ContentFilter is enabled.
    name string
    Name of ContentFilter.
    source string
    Content source to apply the Content Filters.
    allowed_content_level str
    Level at which content is filtered.
    blocking bool
    If blocking would occur.
    enabled bool
    If the ContentFilter is enabled.
    name str
    Name of ContentFilter.
    source str
    Content source to apply the Content Filters.
    allowedContentLevel String
    Level at which content is filtered.
    blocking Boolean
    If blocking would occur.
    enabled Boolean
    If the ContentFilter is enabled.
    name String
    Name of ContentFilter.
    source String
    Content source to apply the Content Filters.

    RaiPolicyContentSource, RaiPolicyContentSourceArgs

    Prompt
    Prompt
    Completion
    Completion
    RaiPolicyContentSourcePrompt
    Prompt
    RaiPolicyContentSourceCompletion
    Completion
    Prompt
    Prompt
    Completion
    Completion
    Prompt
    Prompt
    Completion
    Completion
    PROMPT
    Prompt
    COMPLETION
    Completion
    "Prompt"
    Prompt
    "Completion"
    Completion

    RaiPolicyMode, RaiPolicyModeArgs

    Default
    Default
    Deferred
    Deferred
    Blocking
    Blocking
    RaiPolicyModeDefault
    Default
    RaiPolicyModeDeferred
    Deferred
    RaiPolicyModeBlocking
    Blocking
    Default
    Default
    Deferred
    Deferred
    Blocking
    Blocking
    Default
    Default
    Deferred
    Deferred
    Blocking
    Blocking
    DEFAULT
    Default
    DEFERRED
    Deferred
    BLOCKING
    Blocking
    "Default"
    Default
    "Deferred"
    Deferred
    "Blocking"
    Blocking

    RaiPolicyProperties, RaiPolicyPropertiesArgs

    BasePolicyName string
    Name of the base Content Filters.
    CompletionBlocklists []RaiBlocklistConfig
    The list of blocklists for completion.
    ContentFilters []RaiPolicyContentFilter
    The list of Content Filters.
    Mode string | RaiPolicyMode
    Content Filters mode.
    PromptBlocklists []RaiBlocklistConfig
    The list of blocklists for prompt.
    basePolicyName String
    Name of the base Content Filters.
    completionBlocklists List<RaiBlocklistConfig>
    The list of blocklists for completion.
    contentFilters List<RaiPolicyContentFilter>
    The list of Content Filters.
    mode String | RaiPolicyMode
    Content Filters mode.
    promptBlocklists List<RaiBlocklistConfig>
    The list of blocklists for prompt.
    basePolicyName string
    Name of the base Content Filters.
    completionBlocklists RaiBlocklistConfig[]
    The list of blocklists for completion.
    contentFilters RaiPolicyContentFilter[]
    The list of Content Filters.
    mode string | RaiPolicyMode
    Content Filters mode.
    promptBlocklists RaiBlocklistConfig[]
    The list of blocklists for prompt.
    base_policy_name str
    Name of the base Content Filters.
    completion_blocklists Sequence[RaiBlocklistConfig]
    The list of blocklists for completion.
    content_filters Sequence[RaiPolicyContentFilter]
    The list of Content Filters.
    mode str | RaiPolicyMode
    Content Filters mode.
    prompt_blocklists Sequence[RaiBlocklistConfig]
    The list of blocklists for prompt.
    basePolicyName String
    Name of the base Content Filters.
    completionBlocklists List<Property Map>
    The list of blocklists for completion.
    contentFilters List<Property Map>
    The list of Content Filters.
    mode String | "Default" | "Deferred" | "Blocking"
    Content Filters mode.
    promptBlocklists List<Property Map>
    The list of blocklists for prompt.

    RaiPolicyPropertiesResponse, RaiPolicyPropertiesResponseArgs

    PolicyType string
    Content Filters policy type.
    BasePolicyName string
    Name of the base Content Filters.
    CompletionBlocklists []RaiBlocklistConfigResponse
    The list of blocklists for completion.
    ContentFilters []RaiPolicyContentFilterResponse
    The list of Content Filters.
    Mode string
    Content Filters mode.
    PromptBlocklists []RaiBlocklistConfigResponse
    The list of blocklists for prompt.
    policyType String
    Content Filters policy type.
    basePolicyName String
    Name of the base Content Filters.
    completionBlocklists List<RaiBlocklistConfigResponse>
    The list of blocklists for completion.
    contentFilters List<RaiPolicyContentFilterResponse>
    The list of Content Filters.
    mode String
    Content Filters mode.
    promptBlocklists List<RaiBlocklistConfigResponse>
    The list of blocklists for prompt.
    policyType string
    Content Filters policy type.
    basePolicyName string
    Name of the base Content Filters.
    completionBlocklists RaiBlocklistConfigResponse[]
    The list of blocklists for completion.
    contentFilters RaiPolicyContentFilterResponse[]
    The list of Content Filters.
    mode string
    Content Filters mode.
    promptBlocklists RaiBlocklistConfigResponse[]
    The list of blocklists for prompt.
    policy_type str
    Content Filters policy type.
    base_policy_name str
    Name of the base Content Filters.
    completion_blocklists Sequence[RaiBlocklistConfigResponse]
    The list of blocklists for completion.
    content_filters Sequence[RaiPolicyContentFilterResponse]
    The list of Content Filters.
    mode str
    Content Filters mode.
    prompt_blocklists Sequence[RaiBlocklistConfigResponse]
    The list of blocklists for prompt.
    policyType String
    Content Filters policy type.
    basePolicyName String
    Name of the base Content Filters.
    completionBlocklists List<Property Map>
    The list of blocklists for completion.
    contentFilters List<Property Map>
    The list of Content Filters.
    mode String
    Content Filters mode.
    promptBlocklists List<Property Map>
    The list of blocklists for prompt.

    SystemDataResponse, SystemDataResponseArgs

    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:RaiPolicy raiPolicyName /subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/raiPolicies/{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
    azure-native logo
    This is the latest version of Azure Native. Use the Azure Native v1 docs if using the v1 version of this package.
    Azure Native v2.89.1 published on Sunday, Mar 2, 2025 by Pulumi
    pulumi/pulumi-azure-native