Merge pull request #734 from msakande/content-filtering-preview

add preview indicator for content filtering

Author: Stacyrch140

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

@@ -462,7 +462,7 @@ response = client.complete(
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -943,7 +943,7 @@ var result = await client.path("/chat/completions").post({
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -1455,7 +1455,7 @@ response = client.Complete(requestOptions);
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -2084,7 +2084,7 @@ View the response from the model:
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 

articles/ai-studio/how-to/deploy-models-jais.md

@@ -244,7 +244,7 @@ response = client.complete(
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -512,7 +512,7 @@ var response = await client.path("/chat/completions").post({
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -802,7 +802,7 @@ Console.WriteLine($"Response: {response.Value.Choices[0].Message.Content}");
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -1125,7 +1125,7 @@ extra-parameters: pass-through
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 

articles/ai-studio/how-to/deploy-models-jamba.md

@@ -217,7 +217,7 @@ The `document` object has the following fields:
 - `id` (optional; str) - unique identifier. will be linked to in citations. up to 128 characters.
 - `content` (required; str) - the content of the document
 - `metadata` (optional; array of **Metadata)**
-  - `key` (required; str) - type of metadata, like ‘author’, ‘date’, ‘url’, etc. Should be things the model understands.
+  - `key` (required; str) - type of metadata, like 'author', 'date', 'url', etc. Should be things the model understands.
   - `value` (required; str) - value of the metadata
 
 #### Request example
@@ -410,7 +410,7 @@ Quota is managed per deployment. Each deployment has a rate limit of 200,000 tok
 
 ## Content filtering
 
-Models deployed as a serverless API are protected by Azure AI content safety. With Azure AI content safety enabled, 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 [Azure AI Content Safety](/azure/ai-services/content-safety/overview).
+Models deployed as a serverless API are protected by Azure AI content safety. With Azure AI content safety enabled, 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 (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions. Learn more about [Azure AI Content Safety](/azure/ai-services/content-safety/overview).
 
 ## Related content
 

articles/ai-studio/how-to/deploy-models-llama.md

@@ -323,7 +323,7 @@ The following extra parameters can be passed to Meta Llama models:
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -665,7 +665,7 @@ The following extra parameters can be passed to Meta Llama models:
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -1025,7 +1025,7 @@ The following extra parameters can be passed to Meta Llama models:
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -1410,7 +1410,7 @@ The following extra parameters can be passed to Meta Llama chat models:
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs 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.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.