Merge branch 'eur/release-build-azure-ai-studio-follow' into eur/build-ai-studio-follow-6

Author: eric-urban

articles/ai-studio/concepts/content-filtering.md

@@ -6,7 +6,7 @@ manager: nitinme
 ms.service: azure-ai-studio
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: how-to
 ms.date: 5/21/2024
 ms.reviewer: eur
 ms.author: pafarley
@@ -29,17 +29,60 @@ The content filtering models have been trained and tested on the following langu
 You can create a content filter or use the default content filter for Azure OpenAI model deployment, and can also use a default content filter for other text models curated by Azure AI in the [model catalog](../how-to/model-catalog-overview.md). The custom content filters for those models aren't yet available. Models available through Models as a Service have content filtering enabled by default and can't be configured.
 
 ## How to create a content filter? 
-For any model deployment in [Azure AI Studio](https://ai.azure.com), you could directly use the default content filter, but when you want to have more customized setting on content filter, for example set a stricter or looser filter, or enable more advanced capabilities, like jailbreak risk detection and protected material detection.  To create a content filter, you could go to **Build**, choose one of your projects, then select **Content filters** in the left navigation bar, and create a content filter. 
+For any model deployment in [Azure AI Studio](https://ai.azure.com), you could directly use the default content filter, but when you want to have more customized setting on content filter, for example set a stricter or looser filter, or enable more advanced capabilities, like jailbreak risk detection and protected material detection.  
 
-:::image type="content" source="../media/content-safety/content-filter/create-content-filter.png" alt-text="Screenshot of create content filter." lightbox="../media/content-safety/content-filter/create-content-filter.png":::
+Follow these steps to create a content filter:
 
-### Content filtering categories and configurability
+1. Go to [AI Studio](https://ai.azure.com) and select a project.
+1. Select **Content filters** from the left pane and then select **+ New content filter**.
 
-The content filtering system integrated in Azure AI Studio contains neural multi-class classification models aimed at detecting and filtering harmful content; the models cover four categories (hate, sexual, violence, and self-harm) across four severity levels (safe, low, medium, and high). Content detected at the 'safe' severity level is labeled in annotations but isn't subject to filtering and isn't configurable.
+    :::image type="content" source="../media/content-safety/content-filter/create-content-filter.png" alt-text="Screenshot of the button to create a new content filter." lightbox="../media/content-safety/content-filter/create-content-filter.png":::
+
+1. On the **Basic information** page, enter a name for your content filter. Select a connection to associate with the content filter. Then select **Next**.
+
+    :::image type="content" source="../media/content-safety/content-filter/create-content-filter-basic.png" alt-text="Screenshot of the option to select or enter basic information such as the filter name when creating a content filter." lightbox="../media/content-safety/content-filter/create-content-filter-basic.png":::
+
+1. On the **Input filters** page, you can set the filter for the input prompt. For example, you can enable prompt shields for jailbreak attacks. Then select **Next**.
+
+    :::image type="content" source="../media/content-safety/content-filter/configure-threshold.png" alt-text="Screenshot of the option to select input filters when creating a content filter." lightbox="../media/content-safety/content-filter/configure-threshold.png":::
+
+    Content will be annotated by category and blocked according to the threshold you set. For the violence, hate, sexual, and self-harm categories, adjust the slider to block content of high, medium, or low severity.
+
+1. On the **Output filters** page, you can set the filter for the output completion. For example, you can enable filters for protected material detection. Then select **Next**. 
+    
+    Content will be annotated by each category and blocked according to the threshold. For violent content, hate content, sexual content, and self-harm content category, adjust the threshold to block harmful content with equal or higher severity levels.
+
+1. Optionally, on the **Deployment** page, you can associate the content filter with a deployment. You can also associate the content filter with a deployment later. Then select **Create**.
+
+    :::image type="content" source="../media/content-safety/content-filter/create-content-filter-deployment.png" alt-text="Screenshot of the option to select a deployment when creating a content filter." lightbox="../media/content-safety/content-filter/create-content-filter-deployment.png":::
+
+    Content filtering configurations are created at the hub level in AI Studio. Learn more about configurability in the [Azure OpenAI docs](/azure/ai-services/openai/how-to/content-filters).
+
+1. On the **Review** page, review the settings and then select **Create filter**.
+
+
+## How to apply a content filter?
+
+A default content filter is set when you create a deployment. You can also apply your custom content filter to your deployment. 
+
+Follow these steps to apply a content filter to a deployment:
 
-:::image type="content" source="../media/content-safety/content-filter/configure-threshold.png" alt-text="Screenshot of configuring the threshold." lightbox="../media/content-safety/content-filter/configure-threshold.png":::
+1. Go to [AI Studio](https://ai.azure.com) and select a project.
+1. Select **Deployments** and choose one of your deployments, then select **Edit**.
 
-#### Categories
+    :::image type="content" source="../media/content-safety/content-filter/deployment-edit.png" alt-text="Screenshot of the button to edit a deployment." lightbox="../media/content-safety/content-filter/deployment-edit.png":::
+
+1. In the **Update deployment** window, select the content filter you want to apply to the deployment.
+
+    :::image type="content" source="../media/content-safety/content-filter/apply-content-filter.png" alt-text="Screenshot of apply content filter." lightbox="../media/content-safety/content-filter/apply-content-filter.png":::
+
+Now, you can go to the playground to test whether the content filter works as expected!
+
+## Content filtering categories and configurability
+
+The content filtering system integrated in Azure AI Studio contains neural multi-class classification models aimed at detecting and filtering harmful content; the models cover four categories (hate, sexual, violence, and self-harm) across four severity levels (safe, low, medium, and high). Content detected at the 'safe' severity level is labeled in annotations but isn't subject to filtering and isn't configurable.
+
+### Categories
 
 |Category|Description|
 |--------|-----------|
@@ -48,7 +91,7 @@ The content filtering system integrated in Azure AI Studio contains neural multi
 | Violence | The violence category describes language related to physical actions intended to hurt, injure, damage, or kill someone or something; describes weapons, etc.   |
 | Self-Harm | The self-harm category describes language related to physical actions intended to purposely hurt, injure, or damage one's body, or kill oneself.|
 
-#### Severity levels
+### Severity levels
 
 |Category|Description|
 |--------|-----------|
@@ -70,22 +113,8 @@ The default content filtering configuration for the GPT model series is set to f
 
 <sup>1</sup> For Azure OpenAI models, only customers who have been approved for modified content filtering have full content filtering control, including configuring content filters at severity level high only or turning off content filters. Apply for modified content filters via this form: [Azure OpenAI Limited Access Review: Modified Content Filters and Abuse Monitoring (microsoft.com)](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xURE01NDY1OUhBRzQ3MkQxMUhZSE1ZUlJKTiQlQCN0PWcu)
 
-Content filtering configurations are created within a Resource in Azure AI Studio and can be associated with Deployments. Learn more about configurability in the [Azure OpenAI docs](/azure/ai-services/openai/how-to/content-filters).
-
 Customers are responsible for ensuring that applications integrating Azure OpenAI comply with the [Code of Conduct](/legal/cognitive-services/openai/code-of-conduct?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext). 
 
-### More filters for generative AI scenarios
-You could also enable filters for generative AI scenarios: jailbreak risk detection and protected material detection. 
-
-:::image type="content" source="../media/content-safety/content-filter/additional-models.png" alt-text="Screenshot of additional models." lightbox="../media/content-safety/content-filter/additional-models.png":::
-
-## How to apply a content filter?
-
-A default content filter is set when you create a deployment. You can also apply your custom content filter to your deployment. Select **Deployments** and choose one of your deployments, then select **Edit**, a window of updating deployment will open up. Then you can update the deployment by selecting one of your created content filters.
-
-:::image type="content" source="../media/content-safety/content-filter/apply-content-filter.png" alt-text="Screenshot of apply content filter." lightbox="../media/content-safety/content-filter/apply-content-filter.png":::
-
-Now, you can go to the playground to test whether the content filter works as expected!
 
 ## Next steps
 

articles/ai-studio/concepts/deployments-overview.md

@@ -38,9 +38,9 @@ Azure OpenAI allows you to get access to the latest OpenAI models with the enter
 
 The model catalog offers access to a large variety of models across different modalities. Certain models in the model catalog can be deployed as a service with pay-as-you-go, providing a way to consume them as an API without hosting them on your subscription, while keeping the enterprise security and compliance organizations need.
 
-#### Deploy models with model as a service
+#### Deploy models with Model as a Service (Maas)
 
-This deployment option doesn't require quota from your subscription. You're billed per token in a pay-as-you-go fashion. Learn how to deploy and consume [Llama 2 model family](../how-to/deploy-models-llama.md) with model as a service.
+This deployment option doesn't require quota from your subscription. You deploy as a Serverless API deployment and are billed per token in a pay-as-you-go fashion. Learn how to deploy and consume [Llama 2 model family](../how-to/deploy-models-llama.md) with model as a service.
 
 #### Deploy models with hosted managed infrastructure
 
@@ -50,7 +50,7 @@ You can also host open models in your own subscription with managed infrastructu
 
 The following table describes how you're billed for deploying and inferencing LLMs in Azure AI Studio. See [monitor costs for models offered throughout the Azure Marketplace](../how-to/costs-plan-manage.md#monitor-costs-for-models-offered-through-the-azure-marketplace) to learn more about how to track costs.
 
-| Use case | Azure OpenAI models | Models deployed with pay-as-you-go | Models deployed to real-time endpoints |
+| Use case | Azure OpenAI models | Models deployed as Serverless APIs (pay-as-you-go) | Models deployed with managed compute |
 | --- | --- | --- | --- |
 | Deploying a model from the model catalog to your project | No, you aren't billed for deploying an Azure OpenAI model to your project. | Yes, you're billed per the infrastructure of the endpoint<sup>1</sup> | Yes, you're billed for the infrastructure hosting the model<sup>2</sup> |
 | Testing chat mode on Playground after deploying a model to your project | Yes, you're billed based on your token usage | Yes, you're billed based on your token usage | None. |

articles/ai-studio/how-to/create-manage-compute.md

@@ -50,7 +50,7 @@ To create a compute instance in Azure AI Studio:
 
     For more information on configuration details such as CPU and RAM, see [Azure Machine Learning pricing](https://azure.microsoft.com/pricing/details/machine-learning/) and [virtual machine sizes](/azure/virtual-machines/sizes).
 
-1. On the **Scheduling** page under **Auto shut down** make sure idle shutdown is enabled by default. You can opt to automatically shutdown compute after the instance has been idle for a set amount of time. If you disable auto shutdown costs continue to accrue even during periods of inactivity. For more information, see [Configure idle shutdown](#configure-idle-shutdown).
+1. On the **Scheduling** page under **Auto shut down** make sure idle shutdown is enabled by default. You can opt to automatically shut down compute after the instance has been idle for a set amount of time. If you disable auto shutdown costs continue to accrue even during periods of inactivity. For more information, see [Configure idle shutdown](#configure-idle-shutdown).
 
     :::image type="content" source="../media/compute/compute-scheduling.png" alt-text="Screenshot of the option to enable idle shutdown and create a schedule." lightbox="../media/compute/compute-scheduling.png":::
 
@@ -76,9 +76,6 @@ To create a compute instance in Azure AI Studio:
 
 To avoid getting charged for a compute instance that is switched on but inactive, configure when to shut down your compute instance due to inactivity.
 
-> [!IMPORTANT]
-> The compute won't be idle if you have a [prompt flow compute session](./create-manage-compute-session.md) in **Running** status on the compute. You need to delete any active compute sessions to make the compute instance eligible for idle shutdown. You also can't have any active [VS Code (Web)](./develop/vscode.md) sessions hosted on the compute instance.
-
 The setting can be configured during compute instance creation or modified for existing compute instances.
 
 For a new compute instance, configure idle shutdown during compute instance creation. For more information, see [Create a compute instance](#create-a-compute-instance) earlier in this article.
@@ -91,6 +88,9 @@ To configure idle shutdown for an existing compute instance follow these steps:
 
     :::image type="content" source="../media/compute/compute-schedule-update.png" alt-text="Screenshot of the option to change the idle shutdown schedule for a compute instance." lightbox="../media/compute/compute-schedule-update.png":::
 
+    > [!IMPORTANT]
+    > The compute won't be idle if you have a [prompt flow compute session](./create-manage-compute-session.md) in **Running** status on the compute. You need to delete any active compute sessions to make the compute instance eligible for idle shutdown. You also can't have any active [VS Code (Web)](./develop/vscode.md) sessions hosted on the compute instance.
+
 1. Update or add to the schedule. You can have a total of four schedules per compute instance. Then select **Update** to save your changes.
 
 ## Start or stop a compute instance

articles/ai-studio/how-to/deploy-models-cohere-command.md

@@ -102,7 +102,7 @@ To create a deployment:
 1. Return to the Deployments page, select the deployment, and note the endpoint's **Target** URL and the Secret **Key**. For more information on using the APIs, see the [reference](#reference-for-cohere-models-deployed-as-a-service) section.
 1. You can always find the endpoint's details, URL, and access keys by navigating to your **Project overview** page. Then, from the left sidebar of your project, select **Components** > **Deployments**.
 
-To learn about billing for the Cohere models deployed as a serverless API with pay-as-you-go token-based billing, see [Cost and quota considerations for Cohere models deployed as a service](#cost-and-quota-considerations-for-models-deployed-as-a-service).
+To learn about billing for the Cohere models deployed as a serverless API with pay-as-you-go token-based billing, see [Cost and quota considerations for models deployed as a serverless API](#cost-and-quota-considerations-for-models-deployed-as-a-serverless-api).
 
 ### Consume the Cohere models as a service
 
@@ -666,9 +666,9 @@ Command R+ tool/function calling, using LangChain|`cohere`, `langchain`, `langch
 
 ## Cost and quotas
 
-### Cost and quota considerations for models deployed as a service
+### Cost and quota considerations for models deployed as a serverless API
 
-Cohere models deployed as a service are offered by Cohere through the Azure Marketplace and integrated with Azure AI Studio for use. You can find the Azure Marketplace pricing when deploying the model.
+Cohere models deployed as a serverless API with pay-as-you-go billing are offered by Cohere through the Azure Marketplace and integrated with Azure AI Studio for use. You can find the Azure Marketplace pricing when deploying the model.
 
 Each time a project subscribes to a given offer from the Azure Marketplace, a new resource is created to track the costs associated with its consumption. The same resource is used to track costs associated with inference; however, multiple meters are available to track each scenario independently.
 
@@ -678,7 +678,7 @@ Quota is managed per deployment. Each deployment has a rate limit of 200,000 tok
 
 ## Content filtering
 
-Models deployed as a service with pay-as-you-go billing are protected by [Azure AI Content Safety](../../ai-services/content-safety/overview.md). With Azure AI content safety, both the prompt and completion pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions. Learn more about [content filtering here](../concepts/content-filtering.md).
+Models deployed as a serverless API with pay-as-you-go billing are protected by [Azure AI Content Safety](../../ai-services/content-safety/overview.md). With Azure AI content safety, both the prompt and completion pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions. Learn more about [content filtering here](../concepts/content-filtering.md).
 
 ## Related content