@@ -1,18 +1,18 @@
 ---
 title: Content Credentials in Azure OpenAI
 titleSuffix: Azure OpenAI
-description: Learn about the content credentials feature, which lets you verify that an image was generated by an AI model.
+description: Learn about the Content Credentials feature, which lets you verify that an image was generated by an AI model.
 author: PatrickFarley
 ms.author: pafarley
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 8/28/2024
+ms.date: 02/20/2025
 manager: nitinme
 ---
 
 # Content Credentials
 
-With the improved quality of content from generative AI models, there is an increased need for more transparency on the origin of AI-generated content. All AI-generated images from Azure OpenAI Service now include Content Credentials, a tamper-evident way to disclose the origin and history of content. Content Credentials are based on an open technical specification from the [Coalition for Content Provenance and Authenticity (C2PA)](https://www.c2pa.org), a Joint Development Foundation project. 
+With the improved quality of content from generative AI models, there is an increased need for more transparency about the origin of AI-generated content. All AI-generated images from Azure OpenAI Service include Content Credentials, a tamper-evident way to disclose the origin and history of content. Content Credentials are based on an open technical specification from the [Coalition for Content Provenance and Authenticity (C2PA)](https://www.c2pa.org), a Joint Development Foundation project. 
 
 ## What are Content Credentials? 
 
@@ -29,21 +29,18 @@ The manifest contains several key pieces of information:
 
 Content Credentials in the Azure OpenAI Service can help people understand when visual content is AI-generated. For more information on how to responsibly build solutions with Azure OpenAI Service image-generation models, visit the [Azure OpenAI transparency note](/legal/cognitive-services/openai/transparency-note?tabs=text).
 
-## How do I leverage Content Credentials in my solution today?
+## How do I use Content Credentials in my solution today?
 
-Customers may leverage Content Credentials by:
+Customers may use Content Credentials by:
 - Ensuring that their AI generated images contain Content Credentials
-
-No additional set-up is necessary. Content Credentials are automatically applied to all generated images from DALL·E in the Azure OpenAI Service. 
-
+    No additional set-up is necessary. Content Credentials are automatically applied to all generated images from DALL·E in the Azure OpenAI Service. 
 - Verifying that an image has Content Credentials
-  
-There are two recommended ways today to check the Credential of an image generated by Azure OpenAI DALL-E models:
-
-1. **Content Credentials Verify webpage (contentcredentials.org/verify)**: This is a tool that allows users to inspect the Content Credentials of a piece of content. If an image was generated by DALL-E in Azure OpenAI, the tool will display that its Content Credentials were issued by Microsoft Corporation alongside the date and time of issuance.
-    
-  :::image type="content" source="../media/encryption/credential-check.png" alt-text="Screenshot of the content credential verification website.":::
+    There are two recommended ways today to check the credential of an image generated by Azure OpenAI DALL-E models:
 
-  This page shows that an image generated by Azure OpenAI DALL-E has Content Credentials issued by Microsoft.
+    - **Content Credentials Verify webpage (contentcredentials.org/verify)**: This is a tool that allows users to inspect the Content Credentials of a piece of content. If an image was generated by DALL-E in Azure OpenAI, the tool will display that its Content Credentials were issued by Microsoft Corporation alongside the date and time of issuance.
+       :::image type="content" source="../media/encryption/credential-check.png" alt-text="Screenshot of the content credential verification website.":::
     
-2. **Content Authenticity Initiative (CAI) open-source tools**: The CAI provides multiple open-source tools that validate and display C2PA Content Credentials. Find the tool right for your application and [get started here](https://opensource.contentauthenticity.org/).
+       This page shows that an image generated by Azure OpenAI DALL-E has Content Credentials issued by Microsoft.
+        
+    - **Content Authenticity Initiative (CAI) open-source tools**: The CAI provides multiple open-source tools that validate and display C2PA Content Credentials. Find the tool right for your application and [get started here](https://opensource.contentauthenticity.org/).
+    
\ No newline at end of file

@@ -6,7 +6,7 @@ author: PatrickFarley
 ms.author: pafarley
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 08/22/2024
+ms.date: 02/20/2025
 ms.custom: template-concept, devx-track-python
 manager: nitinme
 ---

@@ -1,27 +1,27 @@
 ---
 title: Azure OpenAI default content safety policies
 titleSuffix: Azure OpenAI
-description: Learn about the default content safety policies that Azure OpenAI uses to flag content.
+description: Learn about the default content safety policies that Azure OpenAI uses to flag content and ensure responsible use of the service.
 author: PatrickFarley
 ms.author: pafarley
 ms.service: azure-ai-openai
-ms.topic: conceptual 
-ms.date: 07/15/2024
+ms.topic: conceptual
+ms.date: 02/20/2025
 manager: nitinme
 ---
 
 # Default content safety policies
 
 
-Azure OpenAI Service includes default safety applied to all models, excluding Azure OpenAI Whisper. These configurations provide you with a responsible experience by default, including [content filtering models](/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new), blocklists, prompt transformation, [content credentials](/azure/ai-services/openai/concepts/content-credentials), and others.
+Azure OpenAI Service includes default safety policies applied to all models, excluding Azure OpenAI Whisper. These configurations provide you with a responsible experience by default, including [content filtering models](/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new), blocklists, prompt transformation, [content credentials](/azure/ai-services/openai/concepts/content-credentials), and others.
 
-Default safety aims to mitigate risks such as hate and fairness, sexual, violence, self-harm, protected material content and user prompt injection attacks. To learn more about content filtering, visit our documentation describing categories and severity levels [here](/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new).
+Default safety aims to mitigate risks in different categories such as hate and fairness, sexual, violence, self-harm, protected material content, and user prompt injection attacks. To learn more about content filtering, visit our documentation describing [categories and severity levels](/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new).
 
-All safety is configurable. To learn more about configurability, visit our documentation on [configuring content filtering](/azure/ai-services/openai/how-to/content-filters).
+All safety policies are configurable. To learn more about configurability, see the documentation on [configuring content filtering](/azure/ai-services/openai/how-to/content-filters).
 
-## Text models: GPT-4, GPT-3.5
+## Text models
 
-Text models in the Azure OpenAI Service can take in and generate both text and code. These models leverage Azure’s text content filtering models to detect and prevent harmful content. This system works on both prompt and completion. 
+Text models in the Azure OpenAI Service can take in and generate both text and code. These models leverage Azure’s text content filters to detect and prevent harmful content. This system works on both prompts and completions. 
 
 | Risk Category                             | Prompt/Completion      | Severity Threshold |
 |-------------------------------------------|------------------------|---------------------|
@@ -35,9 +35,9 @@ Text models in the Azure OpenAI Service can take in and generate both text and c
 
 
 
-## Vision models: GPT-4o, GPT-4 Turbo, DALL-E 3, DALL-E 2
+## Vision models
 
-### GPT-4o and GPT-4 Turbo
+### Vision-enabled chat models
 
 | Risk Category                                        | Prompt/Completion      | Severity Threshold |
 |------------------------------------------------------|------------------------|---------------------|
@@ -48,7 +48,7 @@ Text models in the Azure OpenAI Service can take in and generate both text and c
 | Identification of Individuals and Inference of Sensitive Attributes | Prompts                | N/A                 |
 | User prompt injection attack (Jailbreak)             | Prompts                | N/A                 |
 
-### DALL-E 3 and DALL-E 2
+### Image generation models
 
 
 | Risk Category                                     | Prompt/Completion      | Severity Threshold |

@@ -6,28 +6,27 @@ author: PatrickFarley
 ms.author: pafarley
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 06/10/2024
+ms.date: 02/20/2025
 manager: nitinme
 ---
 
 # Image prompt engineering techniques
 
 To unlock the full potential of vision-enabled chat models like GPT-4 Turbo with Vision and GPT-4o, it's essential to tailor the prompts to your specific needs. Here are some guidelines to enhance the accuracy and efficiency of your prompts.
 
-## Fundamentals of crafting your image prompt
+## Fundamentals of writing an image prompt
+
 - **Contextual specificity:** Adding context to the scenario at hand gives the model a better understanding of an appropriate output. This level of specificity aids in focusing on relevant aspects and avoiding extraneous details.
 - **Task-oriented prompts:** Focusing on a specific task helps the model to develop the output while taking that perspective into consideration.  
-- **Handling refusals:** When the model indicates an inability to perform a task, refining the prompt can be an effective solution. More specific prompts can guide the model towards a clearer understanding and better execution of the task. Some tips to keep in mind: 
-
+- **Handle refusals:** When the model indicates an inability to perform a task, refining the prompt can be an effective solution. More specific prompts can guide the model towards a clearer understanding and better execution of the task. Keep these tips in mind:
    - Request explanations for generated responses to enhance transparency in the model's output <br>
    - If using a single-image prompt, place the image before the text <br>
    - Ask the model to describe the image in details first and complete your specific task from the description
-
-- **Adding examples:** Add examples that represent the type of responses you're looking for
+- **Add examples:** Add examples that represent the type of responses you're looking for
 - **Break down requests:** Try breaking down complex requests step-by-step to create manageable sub-goals
 - **Define output format:** Clearly mention the desired format for the output, such as markdown, JSON, HTML, etc. You can also suggest a specific structure, length, or specific attributes about the response.
 
-## Example prompt inputs & outputs
+## Example prompt inputs and outputs
 There are many ways to craft system prompts to tailor the output specifically to your needs. The following sample inputs and outputs showcase how adjusting your prompts can give you different results. Try out the model for yourself using these images and adjusting the system prompt in the [Azure AI Foundry playground](https://ai.azure.com/).
 
 ### Contextual specificity  
@@ -62,7 +61,7 @@ When you receive a refusal output from a model, there are several ways you can t
 
 |Follow up prompt|Model output|
 |--------|-----------|
-| What information do you need? | `I apologize for the confusion earlier. To plan a meal based on the image provided, I would need to know the following: <br> The number of people dining to ensure there's enough food for everyone.<br>Any dietary restrictions or preferences to accommodate (e.g., vegetarian, gluten-free, allergies).<br>The occasion or type of meal being planned (e.g., casual lunch, dinner party).<br>Desired balance of the meal in terms of food groups and nutrition. <br>With this information, I could help suggest how to portion the dishes, create a balanced meal, and ensure the meal meets the needs of all diners.`|
+| What information do you need? | `I apologize for the confusion earlier. To plan a meal based on the image provided, I would need to know the following: `<br> `The number of people dining to ensure there's enough food for everyone.`<br>`Any dietary restrictions or preferences to accommodate (e.g., vegetarian, gluten-free, allergies).`<br>`The occasion or type of meal being planned (e.g., casual lunch, dinner party).`<br>`Desired balance of the meal in terms of food groups and nutrition.` <br>`With this information, I could help suggest how to portion the dishes, create a balanced meal, and ensure the meal meets the needs of all diners.`|
 
 ### Adding examples
 
@@ -74,17 +73,17 @@ When you receive a refusal output from a model, there are several ways you can t
 |--------|-----------|
 | Q: What is this dog breed and what is its average weight & height? :::image type="content" source="../media/concepts/gpt-v/pomeranian.jpg" lightbox="../media/concepts/gpt-v/pomeranian.jpg" alt-text="Photograph of a pomeranian dog sitting on a pool diving board above the water."::: <br> A: Breed: pomeranian; average weight: 3-7 lbs; average height: 8-14 inches <br> :::image type="content" source="../media/concepts/gpt-v/bulldog.jpg" lightbox="../media/concepts/gpt-v/bulldog.jpg" alt-text="Photograph of a bulldog laying in a grass field."::: A: Breed: English bulldog; average weight: 50-55 lbs; average height: 14-16 inches :::image type="content" source="../media/concepts/gpt-v/border-collie.jpg" lightbox="../media/concepts/gpt-v/border-collie.jpg" alt-text="Photograph of a border collie dog laying in a grass field."::: | `A: Breed: Border Collie; average weight: 30-45 lbs; average height: 18-22 inches` |
 
-### Break down requests
+### Breaking down requests
 
 |Basic prompt|Model output|
 |--------|-----------|
-| :::image type="content" source="../media/concepts/gpt-v/grandmas-recipe.jpg" lightbox="../media/concepts/gpt-v/grandmas-recipe.jpg" alt-text="Photograph of a recipe card detailing a recipe for Grandma's Apple Crumb Pie."::: What's in this image? | `The image contains a recipe card titled Grandma's Apple Crumb Pie. It is noted as a Thanksgiving tradition. The ingredients listed are:<br><ul><li>5-7 apples, peeled </li> <li>1 9-inch pie crust</li> <li>	3/4 cups sugar </li> <li>1/2 teaspoon cinnamon </li> <li>A dash of salt </li><li>	3 tablespoons butter</li> </ul><br>Please note that the measurements for sugar, flour, and butter are not fully visible in the image. If needed, the standard measures for a crumb topping typically involve a combination of sugar, flour, and butter mixed together until crumbly`|
+| :::image type="content" source="../media/concepts/gpt-v/grandmas-recipe.jpg" lightbox="../media/concepts/gpt-v/grandmas-recipe.jpg" alt-text="Photograph of a recipe card detailing a recipe for Grandma's Apple Crumb Pie."::: What's in this image? | `The image contains a recipe card titled Grandma's Apple Crumb Pie. It is noted as a Thanksgiving tradition. The ingredients listed are:`<br><ul><li>`5-7 apples, peeled `</li> <li>`1 9-inch pie crust`</li> <li>`	3/4 cups sugar `</li> <li>`1/2 teaspoon cinnamon `</li> <li>`A dash of salt `</li><li>`	3 tablespoons butter`</li> </ul><br>`Please note that the measurements for sugar, flour, and butter are not fully visible in the image. If needed, the standard measures for a crumb topping typically involve a combination of sugar, flour, and butter mixed together until crumbly`|
 
 |Updated prompt|Model output|
 |----------|-----------|
-| :::image type="content" source="../media/concepts/gpt-v/grandmas-recipe.jpg" lightbox="../media/concepts/gpt-v/grandmas-recipe.jpg" alt-text="Photograph of a recipe card detailing a recipe for Grandma's Apple Crumb Pie."::: You are an AI assistant that helps create shopping lists and instructions to prep food based on recipes. Please provide a list of ingredients to purchase, and then provide a list of instructions to prep the ingredients based on the recipe card.  | Sure, here's a shopping list based on the recipe card: <br>Shopping List:</br><ol><li>5-7 apples (suitable for baking, such as Granny Smith or Honeycrisp)</li> <li>1 ready-made pie crust (9-inch) </li><li>Sugar (ensure you have enough for 1/2 cup)</li><li>All-purpose flour (ensure you have enough for 3/4 cup)</li><li>Ground cinnamon</li><li>Salt</li><li>Butter (ensure you have enough for 3 tablespoons)</li></ol><br>Prepping Instructions:</br> <ul><li>Peel the apples: Using a vegetable peeler or a paring knife, remove the skin from 5 to 7 apples.</li><li>Core and slice the apples: Cut the apples into quarters, remove the cores, and then slice the apple quarters into thin slices or chunks, depending on your preference for pie texture.</li><li>Measure the ingredients: Measure out 3/4 cups of sugar, 1/2 teaspoon of cinnamon, a dash of salt (about 1/8 teaspoon), and 3 tablespoons of butter.</li><li>Prepare the butter: Cut the butter into small pieces to be ready to use in the recipe. It's often easier to incorporate if it's cold, so keep it refrigerated until it's needed</li><li>Preheat your oven according to the pie recipe's instructions so it's ready for baking once your pie is assembled.</li><li>Remember to follow any additional preparation or baking instructions provided in the full recipe for your apple crumb pie.</li></ul> |
+| :::image type="content" source="../media/concepts/gpt-v/grandmas-recipe.jpg" lightbox="../media/concepts/gpt-v/grandmas-recipe.jpg" alt-text="Photograph of a recipe card detailing a recipe for Grandma's Apple Crumb Pie."::: You are an AI assistant that helps create shopping lists and instructions to prep food based on recipes. Please provide a list of ingredients to purchase, and then provide a list of instructions to prep the ingredients based on the recipe card.  | `Sure, here's a shopping list based on the recipe card: `<br>`Shopping List:`</br><ol><li>`5-7 apples (suitable for baking, such as Granny Smith or Honeycrisp)`</li> <li>`1 ready-made pie crust (9-inch) `</li><li>`Sugar (ensure you have enough for 1/2 cup)`</li><li>`All-purpose flour (ensure you have enough for 3/4 cup)`</li><li>`Ground cinnamon`</li><li>`Salt`</li><li>`Butter (ensure you have enough for 3 tablespoons)`</li></ol><br>`Prepping Instructions:`</br> <ul><li>`Peel the apples: Using a vegetable peeler or a paring knife, remove the skin from 5 to 7 apples.`</li><li>`Core and slice the apples: Cut the apples into quarters, remove the cores, and then slice the apple quarters into thin slices or chunks, depending on your preference for pie texture.`</li><li>`Measure the ingredients: Measure out 3/4 cups of sugar, 1/2 teaspoon of cinnamon, a dash of salt (about 1/8 teaspoon), and 3 tablespoons of butter.`</li><li>`Prepare the butter: Cut the butter into small pieces to be ready to use in the recipe. It's often easier to incorporate if it's cold, so keep it refrigerated until it's needed`</li><li>`Preheat your oven according to the pie recipe's instructions so it's ready for baking once your pie is assembled.`</li><li>`Remember to follow any additional preparation or baking instructions provided in the full recipe for your apple crumb pie.`</li></ul> |
 
-### Define output format
+### Defining output format
 
 |Basic prompt|Model output|
 |----------|-----------|

@@ -6,7 +6,7 @@ author: PatrickFarley
 ms.author: pafarley
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 09/24/2024
+ms.date: 02/20/2025
 manager: nitinme
 ---
 
@@ -18,7 +18,7 @@ To try out vision-enabled chat models, see the [quickstart](/azure/ai-services/o
 
 ## Vision-enabled chats
 
-The vision-enabled models answer general questions about what's present in the images or videos you upload.
+The vision-enabled models answer general questions about what's present in the images you upload.
 
 
 ## Special pricing information
@@ -51,7 +51,7 @@ For a typical use case, take an image with both visible objects and text and a 1
 | Output Tokens      | 100 tokens (assumed)    | $0.003       |
 | **Total** |  |**$0.00955** |
 
-
+<!--
 ### Example video price calculation
 
 > [!IMPORTANT]
@@ -68,6 +68,7 @@ For a typical use case, take a 3-minute video with a 100-token prompt input. The
 | **Total**      |      | **$0.03025** |
 
 Additionally, there's a one-time indexing cost of $0.15 to generate the Video Retrieval index for this 3-minute video. This index can be reused across any number of Video Retrieval and GPT-4 Turbo with Vision API calls.
+-->
 
 ## Input limitations
 
@@ -79,16 +80,18 @@ This section describes the limitations of vision-enabled chat models.
 - **Low resolution accuracy**: When images are analyzed using the "low resolution" setting, it allows for faster responses and uses fewer input tokens for certain use cases. However, this could impact the accuracy of object and text recognition within the image.
 - **Image chat restriction**: When you upload images in Azure AI Foundry portal or the API, there is a limit of 10 images per chat call.
 
+<!--
 ### Video support
 
 - **Low resolution**: Video frames are analyzed using GPT-4 Turbo with Vision's "low resolution" setting, which may affect the accuracy of small object and text recognition in the video.
 - **Video file limits**: Both MP4 and MOV file types are supported. In Azure AI Foundry portal, videos must be less than 3 minutes long. When you use the API there is no such limitation.
 - **Prompt limits**: Video prompts only contain one video and no images. In Azure AI Foundry portal, you can clear the session to try another video or images.
 - **Limited frame selection**: The service selects 20 frames from the entire video, which might not capture all the critical moments or details. Frame selection can be approximately evenly spread through the video or focused by a specific video retrieval query, depending on the prompt.
 - **Language support**: The service primarily supports English for grounding with transcripts. Transcripts don't provide accurate information on lyrics in songs.
+-->
 
 ## Next steps
 
 - Get started using vision-enabled models by following the [quickstart](/azure/ai-services/openai/gpt-v-quickstart).
-- For a more in-depth look at the APIs, and to use video prompts in chat, follow the [how-to guide](../how-to/gpt-with-vision.md).
+- For a more in-depth look at the APIs, follow the [how-to guide](../how-to/gpt-with-vision.md).
 - See the [completions and embeddings API reference](../reference.md)

@@ -6,13 +6,13 @@ author: PatrickFarley
 ms.author: pafarley
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 07/16/2024
+ms.date: 02/20/2025
 manager: nitinme
 ---
 
 # What is prompt transformation?
 
-Prompt transformation is a process in DALL-E 3 image generation that applies a safety and quality system message to your original prompt using a large language model (LLM) call before being sent to the model for image generation. This system message enriches your original prompt with the goal of generating more diverse and higher-quality images, while maintaining intent. 
+Prompt transformation is a process included in DALL-E 3 image generation that applies a safety and quality system message to your original prompt. It uses a large language model (LLM) call to add the message before sending your prompt to the model for image generation. This system message enriches your original prompt with the goal of generating more diverse and higher-quality images while maintaining intent. 
 
 After prompt transformation is applied to the original prompt, content filtering is applied as a secondary step before image generation; for more information, see [Content filtering](./content-filter.md).
 
@@ -21,7 +21,6 @@ After prompt transformation is applied to the original prompt, content filtering
 
 ## Prompt transformation example
 
-
 | **Example text prompt** | **Example generated image without prompt transformation** | **Example generated image with prompt transformation** |
 |---|---|---|
 |"Watercolor painting of the Seattle skyline" | ![Watercolor painting of the Seattle skyline (simple).](../media/how-to/generated-seattle.png) | ![Watercolor painting of the Seattle skyline, with more detail and structure.](../media/how-to/generated-seattle-prompt-transformed.png) |
@@ -39,12 +38,10 @@ Prompt transformation is applied by default to all Azure OpenAI DALL-E 3 request
 
 Like image generation, prompt transformation is non-deterministic due to the nature of large language models. A single original prompt may lead to many image variants.
 
-
 ## View prompt transformations
 
 Your revised or transformed prompt is visible in the API response object as shown here, in the `revised_prompt` field. 
 
-
 ```json
 Input Content:
 {
@@ -69,7 +66,7 @@ Output Content:
 }
 ```
 
+## Next step
 
-## Next steps
-
-* [DALL-E quickstart](/azure/ai-services/openai/dall-e-quickstart)
\ No newline at end of file
+> [!div class="nextstepaction"]
+> [DALL-E quickstart](/azure/ai-services/openai/dall-e-quickstart)

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI Service
 description: This article contains recommended safety system messages for your generative AI systems, to help reduce the propensity of harm in various concern areas.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 09/20/2024
+ms.date: 02/20/2025
 ms.custom:
 manager: nitinme
 author: PatrickFarley
@@ -14,14 +14,14 @@ ms.author: pafarley
 
 # Safety system message templates
 
-
 This article contains recommended safety system messages for your generative AI systems, to help reduce the propensity of harm in various concern areas. Before you begin evaluating and integrating your safety system messages, visit the [Safety System Message documentation](/azure/ai-services/openai/concepts/system-message) to get started.  
 
-Note that using a safety system message is one of many techniques that can be used for mitigations risks in AI systems, and different from [Azure AI Content Safety](/azure/ai-services/content-safety/overview). 
+> [!NOTE]
+> Using a safety system message is one of many techniques that can be used for mitigations risks in AI systems and is different from [Azure AI Content Safety](/azure/ai-services/content-safety/overview). 
 
 ## Recommended system messages 
 
-Below are examples of recommended system message components you can include to potentially mitigate various harms in your system. 
+Below are examples of recommended system message components you can include to potentially mitigate various harms in your AI system. 
 
 | Category | Component | When this concern area may apply |
 | --- | --- | --- |
@@ -32,7 +32,7 @@ Below are examples of recommended system message components you can include to p
 
 ## Add safety system messages in Azure AI Foundry portal 
 
-The following steps show how to leverage safety system messages in Azure AI Foundry portal.  
+The following steps show how to leverage safety system messages in [Azure AI Foundry portal](https://ai.azure.com/).
 
 1. Go to Azure AI Foundry and navigate to Azure OpenAI and the Chat playground.
     :::image type="content" source="../media/navigate-chat-playground.PNG" alt-text="Screenshot of the Azure AI Foundry portal selection.":::
@@ -47,8 +47,8 @@ The following steps show how to leverage safety system messages in Azure AI Foun
 
 
 > [!NOTE]
-> If you are using a safety system message that is not integrated into the studio by default, simply copy the appropriate component and paste it in the safety system message section, or the system message section. Repeat steps 4 and 5 for optimal performance and safety. 
+> If you're using a safety system message that is not integrated into the studio by default, simply copy the appropriate component and paste it in the safety system message section, or the system message section. Repeat steps 4 and 5 for optimal performance and safety. 
 
 ## Evaluation 
 
-We recommend informing your safety system message approach based on an iterative process of identification and evaluation. Learn more in our [Safety System Message documentation](/azure/ai-services/openai/concepts/system-message). 
\ No newline at end of file
+We recommend adjusting your safety system message approach based on an iterative process of identification and evaluation. Learn more in our [Safety System Message documentation](/azure/ai-services/openai/concepts/system-message). 
\ No newline at end of file

@@ -9,7 +9,7 @@ ms.custom: devx-track-python, devx-track-dotnet, devx-track-extended-java, devx-
 ms.topic: quickstart
 author: PatrickFarley
 ms.author: pafarley
-ms.date: 09/06/2024
+ms.date: 02/20/2025
 zone_pivot_groups: openai-quickstart-dall-e
 ---
 

@@ -9,7 +9,7 @@ ms.custom: devx-track-python, devx-track-js, devx-track-ts
 ms.topic: quickstart
 author: PatrickFarley
 ms.author: pafarley
-ms.date: 10/03/2024
+ms.date: 02/20/2025
 zone_pivot_groups: openai-quickstart-gpt-v
 ---
 
@@ -64,7 +64,7 @@ Get started using GPT-4 Turbo with images with the Azure OpenAI Service.
 
 ## Next steps
 
-* [Get started with multimodal vision chat apps using Azure OpenAI](/azure/developer/ai/get-started-app-chat-vision?tabs=github-codespaces) AI App template
+* [Get started with multimodal vision chat apps using Azure OpenAI AI App template](/azure/developer/ai/get-started-app-chat-vision?tabs=github-codespaces)
 * Learn more about these APIs in the [Vision-enabled models how-to guide](./gpt-v-quickstart.md)
 * [GPT-4 Turbo with Vision frequently asked questions](./faq.yml#gpt-4-turbo-with-vision)
 * [GPT-4 Turbo with Vision API reference](https://aka.ms/gpt-v-api-ref)

@@ -1,20 +1,20 @@
 ---
-title: How to work with DALL-E models 
+title: How to use DALL-E models 
 titleSuffix: Azure OpenAI Service
-description: Learn about the options for how to use the DALL-E image generation models.
+description: Learn how to generate images with the DALL-E models, and learn about the configuration options that are available.
 author: PatrickFarley
 ms.author: pafarley 
 ms.service: azure-ai-openai
 ms.custom: 
 ms.topic: how-to
-ms.date: 10/02/2024
+ms.date: 02/20/2025
 manager: nitinme
 keywords: 
 zone_pivot_groups: 
 # Customer intent: as an engineer or hobbyist, I want to know how to use DALL-E image generation models to their full capability.
 ---
 
-# How to work with the DALL-E models
+# How to use the DALL-E models
 
 OpenAI's DALL-E models generate images based on user-provided text prompts. This guide demonstrates how to use the DALL-E models and configure their options through REST API calls.
 
@@ -104,7 +104,7 @@ It's also possible that the generated image itself is filtered. In this case, th
 }
 ```
 
-## Writing image prompts
+## Write image prompts
 
 Your image prompts should describe the content you want to see in the image, and the visual style of image.
 
@@ -124,7 +124,7 @@ Specify the size of the generated images. Must be one of `1024x1024`, `1792x1024
 
 ### Style
 
-DALL-E 3 introduces two style options: `natural` and `vivid`. The natural style is more similar to the DALL-E 2 default style, while the vivid style generates more hyper-real and cinematic images.
+DALL-E 3 offers two style options: `natural` and `vivid`. The natural style is more similar to the default style of older models, while the vivid style generates more hyper-real and cinematic images.
 
 The natural style is useful in cases where DALL-E 3 over-exaggerates or confuses a subject that's meant to be more simple, subdued, or realistic.
 

@@ -1,35 +1,36 @@
 ---
 title: How to use vision-enabled chat models
 titleSuffix: Azure OpenAI Service
-description: Learn about the options for using vision-enabled chat models
+description: Learn how to use vision-enabled chat models in Azure OpenAI Service, including how to call the Chat Completion API and process images.
 author: PatrickFarley #dereklegenzoff
 ms.author: pafarley #delegenz
+#customer intent: As a developer, I want to learn how to use vision-enabled chat models so that I can integrate image processing capabilities into my applications.
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 08/21/2024
+ms.date: 02/20/2025
 manager: nitinme
 ---
 
 # Use vision-enabled chat models
 
 
-Vision-enabled chat models are large multimodal models (LMM) developed by OpenAI that can analyze images and provide textual responses to questions about them. They incorporate both natural language processing and visual understanding. The current vision-enabled models are [o1](./reasoning.md), GPT-4o, and GPT-4o-mini, GPT-4 Turbo with Vision.
+Vision-enabled chat models are large multimodal models (LMM) developed by OpenAI that can analyze images and provide textual responses to questions about them. They incorporate both natural language processing and visual understanding. The current vision-enabled models are [o1](./reasoning.md), GPT-4o, GPT-4o-mini, and GPT-4 Turbo with Vision.
 
-The vision-enabled models answer general questions about what's present in the images you upload.
+The vision-enabled models can answer general questions about what's present in the images you upload.
 
 > [!TIP]
 > To use vision-enabled models, you call the Chat Completion API on a supported model that you have deployed. If you're not familiar with the Chat Completion API, see the [Vision-enabled chat how-to guide](/azure/ai-services/openai/how-to/chatgpt?tabs=python&pivots=programming-language-chat-completions).
 
 ## Call the Chat Completion APIs
 
-The following command shows the most basic way to use the GPT-4 Turbo with Vision model with code. If this is your first time using these models programmatically, we recommend starting with our [GPT-4 Turbo with Vision quickstart](../gpt-v-quickstart.md). 
+The following command shows the most basic way to use a vision-enabled chat model with code. If this is your first time using these models programmatically, we recommend starting with our [Chat with images quickstart](../gpt-v-quickstart.md). 
 
 #### [REST](#tab/rest)
 
 Send a POST request to `https://{RESOURCE_NAME}.openai.azure.com/openai/deployments/{DEPLOYMENT_NAME}/chat/completions?api-version=2024-02-15-preview` where 
 
 - RESOURCE_NAME is the name of your Azure OpenAI resource 
-- DEPLOYMENT_NAME is the name of your GPT-4 Turbo with Vision model deployment 
+- DEPLOYMENT_NAME is the name of your model deployment 
 
 **Required headers**: 
 - `Content-Type`: application/json 
@@ -75,7 +76,7 @@ The following is a sample request body. The format is the same as the chat compl
 #### [Python](#tab/python)
 
 1. Define your Azure OpenAI resource endpoint and key. 
-1. Enter the name of your GPT-4 Turbo with Vision model deployment.
+1. Enter the name of your model deployment.
 1. Create a client object using those values.
 
     ```python

@@ -6,7 +6,7 @@ author: PatrickFarley
 ms.author: pafarley 
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 12/05/2024
+ms.date: 02/20/2025
 manager: nitinme
 ---
 
@@ -50,13 +50,13 @@ To use Potentially abusive user detection, you need:
 - A content filter configuration applied to your deployment.
 - You must be sending user ID information in your Chat Completion requests (see the _user_ parameter of the [Completions API](/azure/ai-services/openai/reference#completions), for example).
     > [!CAUTION]
-    > Use GUID strings to identify individual users. Do not include sensitive personal information in the "user" field.
+    > Use GUID strings to identify individual users. Do not include sensitive personal information in the _user_ field.
 - An Azure Data Explorer database set up to store the user analysis results (instructions below).
 
 ### Set up your Azure Data Explorer database
 
 In order to protect the data privacy of user information and manage the permission of the data, we support the option for our customers to bring their own storage to get the detailed potentially abusive user detection insights (including user GUID and statistics on harmful request by category) stored in a compliant way and with full control. Follow these steps to enable it:
-1. In Azure AI Foundry, navigate to the model deployment that you'd like to set up user abuse analysis with, and select **Add a data store**. 
+1. In [Azure AI Foundry](https://ai.azure.com/), navigate to the model deployment that you'd like to set up user abuse analysis with, and select **Add a data store**. 
 1. Fill in the required information and select **Save**. We recommend you create a new database to store the analysis results.
 1. After you connect the data store, take the following steps to grant permission to write analysis results to the connected database:
     1. Go to your Azure OpenAI resource's page in the Azure portal, and choose the **Identity** tab.
@@ -89,8 +89,9 @@ The potentially abusive user detection relies on the user information that custo
 
 Combine this data with enriched signals to validate whether the detected users are truly abusive or not. If they are, then take responsive action such as throttling or suspending the user to ensure the responsible use of your application.
 
-## Next steps
+## Next step
 
 Next, create or edit a content filter configuration in Azure AI Foundry.
 
-- [Configure content filters with Azure OpenAI Service](/azure/ai-services/openai/how-to/content-filters)
+> [!div class="nextstepaction"]
+> [Configure content filters with Azure OpenAI Service](/azure/ai-services/openai/how-to/content-filters)

@@ -6,14 +6,14 @@ description: Learn how to use blocklists with Azure OpenAI Service
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 12/05/2024
+ms.date: 02/20/2025
 author: PatrickFarley
 ms.author: pafarley
 ---
 
 # Use a blocklist with Azure OpenAI
 
-The configurable content filters are sufficient for most content moderation needs. However, you might need to filter terms specific to your use case. 
+The [configurable content filters](/azure/ai-services/openai/how-to/content-filters) available in Azure OpenAI are sufficient for most content moderation needs. However, you might need to filter terms specific to your use case. For this, you can use custom blocklists.
 
 ## Prerequisites
 
@@ -63,7 +63,7 @@ The response code should be `201` (created a new list) or `200` (updated an exis
 
 ### Apply a blocklist to a content filter
 
-If you haven't yet created a content filter, you can do so in Azure AI Foundry. See [Content filtering](/azure/ai-services/openai/how-to/content-filters#create-a-content-filter-in-azure-ai-foundry).
+If you haven't yet created a content filter, you can do so in [Azure AI Foundry](https://ai.azure.com/). See [Content filtering](/azure/ai-services/openai/how-to/content-filters#create-a-content-filter-in-azure-ai-foundry).
 
 To apply a **completion** blocklist to a content filter, use the following cURL command: 
 
@@ -178,7 +178,7 @@ In the below example, a GPT-35-Turbo deployment with a blocklist is blocking the
 } 
 ```
 
-If the completion itself is blocked, the response returns `200`, as the completion only cuts off when the blocklist content is matched. The annotations show that a blocklist was matched. 
+If the completion itself is blocked, the response returns `200`, as the completion only cuts off when the blocklist content is matched. The annotations show that a blocklist item was matched. 
 
 ```json
 { 
@@ -257,7 +257,7 @@ If the completion itself is blocked, the response returns `200`, as the completi
 
 ---
 
-## Next steps
+## Related content
 
 - Learn more about Responsible AI practices for Azure OpenAI: [Overview of Responsible AI practices for Azure OpenAI models](/legal/cognitive-services/openai/overview?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext). 
 

@@ -44,9 +44,6 @@ Creates a completion for the provided prompt, parameters and chosen model.
 | logprobs | integer | Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response.<br><br>The maximum value for `logprobs` is 5.<br> | No | None |
 | max_tokens | integer | The maximum number of tokens that can be generated in the completion.<br><br>The token count of your prompt plus `max_tokens` can't exceed the model's context length.  | No | 16 |
 | n | integer | How many completions to generate for each prompt.<br><br>**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.<br> | No | 1 |
-| modalities | [ChatCompletionModalities](#chatcompletionmodalities) | Output types that you would like the model to generate for this request.<br>Most models are capable of generating text, which is the default:<br><br>`["text"]`<br><br>The `gpt-4o-audio-preview` model can also be used to generate audio. To<br>request that this model generate both text and audio responses, you can<br>use:<br><br>`["text", "audio"]`<br> | No |  |
-| prediction | [PredictionContent](#predictioncontent) | Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content. | No |  |
-| audio | object | Parameters for audio output. Required when audio output is requested with<br>`modalities: ["audio"]`.  | No |  |
 | presence_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.<br> | No | 0 |
 | seed | integer | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.<br><br>Determinism isn't guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.<br> | No |  |
 | stop | string or array | Up to four sequences where the API will stop generating further tokens. The returned text won't contain the stop sequence.<br> | No |  |
@@ -57,20 +54,6 @@ Creates a completion for the provided prompt, parameters and chosen model.
 | user | string | A unique identifier representing your end-user, which can help to monitor and detect abuse.<br> | No |  |
 
 
-### Properties for audio
-
-#### voice
-
-| Name | Type | Description | Default |
-|------|------|-------------|--------|
-| voice | string | Specifies the voice type. Supported voices are `alloy`, `echo`, <br>`fable`, `onyx`, `nova`, and `shimmer`.<br> |  |
-
-#### format
-
-| Name | Type | Description | Default |
-|------|------|-------------|--------|
-| format | string | Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`,<br>`opus`, or `pcm16`. <br> |  |
-
 ### Responses
 
 **Status Code:** 200
@@ -334,6 +317,23 @@ Creates a completion for the chat message
 | function_call | string or [chatCompletionFunctionCallOption](#chatcompletionfunctioncalloption) | Deprecated in favor of `tool_choice`.<br><br>Controls which (if any) function is called by the model.<br>`none` means the model won't call a function and instead generates a message.<br>`auto` means the model can pick between generating a message or calling a function.<br>Specifying a particular function via `{"name": "my_function"}` forces the model to call that function.<br><br>`none` is the default when no functions are present. `auto` is the default if functions are present.<br> | No |  |
 | functions | array | Deprecated in favor of `tools`.<br><br>A list of functions the model may generate JSON inputs for.<br> | No |  |
 | user_security_context | [userSecurityContext](#usersecuritycontext) | User security context contains several parameters that describe the AI application itself, and the end user that interacts with the AI application. These fields assist your security operations teams to investigate and mitigate security incidents by providing a comprehensive approach to protecting your AI applications. [Learn more](https://aka.ms/TP4AI/Documentation/EndUserContext) about protecting AI applications using Microsoft Defender for Cloud. | No |  |
+| modalities | [ChatCompletionModalities](#chatcompletionmodalities) | Output types that you would like the model to generate for this request.<br>Most models are capable of generating text, which is the default:<br><br>`["text"]`<br><br>The `gpt-4o-audio-preview` model can also be used to generate audio. To<br>request that this model generate both text and audio responses, you can<br>use:<br><br>`["text", "audio"]`<br> | No |  |
+| prediction | [PredictionContent](#predictioncontent) | Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content. | No |  |
+| audio | object | Parameters for audio output. Required when audio output is requested with<br>`modalities: ["audio"]`.  | No |  |
+
+### Properties for audio
+
+#### voice
+
+| Name | Type | Description | Default |
+|------|------|-------------|--------|
+| voice | string | Specifies the voice type. Supported voices are `alloy`, `echo`, <br>`fable`, `onyx`, `nova`, and `shimmer`.<br> |  |
+
+#### format
+
+| Name | Type | Description | Default |
+|------|------|-------------|--------|
+| format | string | Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`,<br>`opus`, or `pcm16`. <br> |  |
 
 ### Responses
 
@@ -4597,9 +4597,6 @@ Information about the content filtering category (hate, sexual, violence, self_h
 | logprobs | integer | Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response.<br><br>The maximum value for `logprobs` is 5.<br> | No | None |
 | max_tokens | integer | The maximum number of tokens that can be generated in the completion.<br><br>The token count of your prompt plus `max_tokens` can't exceed the model's context length.  | No | 16 |
 | n | integer | How many completions to generate for each prompt.<br><br>**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.<br> | No | 1 |
-| modalities | [ChatCompletionModalities](#chatcompletionmodalities) | Output types that you would like the model to generate for this request.<br>Most models are capable of generating text, which is the default:<br><br>`["text"]`<br><br>The `gpt-4o-audio-preview` model can also be used to generate audio. To<br>request that this model generate both text and audio responses, you can<br>use:<br><br>`["text", "audio"]`<br> | No |  |
-| prediction | [PredictionContent](#predictioncontent) | Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content. | No |  |
-| audio | object | Parameters for audio output. Required when audio output is requested with<br>`modalities: ["audio"]`.  | No |  |
 | presence_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.<br> | No | 0 |
 | seed | integer | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.<br><br>Determinism isn't guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.<br> | No |  |
 | stop | string or array | Up to four sequences where the API will stop generating further tokens. The returned text won't contain the stop sequence.<br> | No |  |
@@ -4610,21 +4607,6 @@ Information about the content filtering category (hate, sexual, violence, self_h
 | user | string | A unique identifier representing your end-user, which can help to monitor and detect abuse.<br> | No |  |
 
 
-### Properties for audio
-
-#### voice
-
-| Name | Type | Description | Default |
-|------|------|-------------|--------|
-| voice | string | Specifies the voice type. Supported voices are `alloy`, `echo`, <br>`fable`, `onyx`, `nova`, and `shimmer`.<br> |  |
-
-#### format
-
-| Name | Type | Description | Default |
-|------|------|-------------|--------|
-| format | string | Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`,<br>`opus`, or `pcm16`. <br> |  |
-
-
 ### createCompletionResponse
 
 Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint).
@@ -4674,8 +4656,24 @@ Represents a completion response from the API. Note: both the streamed and non-s
 | tool_choice | [chatCompletionToolChoiceOption](#chatcompletiontoolchoiceoption) | Controls which (if any) tool is called by the model. `none` means the model won't call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. `none` is the default when no tools are present. `auto` is the default if tools are present. | No |  |
 | function_call | string or [chatCompletionFunctionCallOption](#chatcompletionfunctioncalloption) | Deprecated in favor of `tool_choice`.<br><br>Controls which (if any) function is called by the model.<br>`none` means the model won't call a function and instead generates a message.<br>`auto` means the model can pick between generating a message or calling a function.<br>Specifying a particular function via `{"name": "my_function"}` forces the model to call that function.<br><br>`none` is the default when no functions are present. `auto` is the default if functions are present.<br> | No |  |
 | functions | array | Deprecated in favor of `tools`.<br><br>A list of functions the model may generate JSON inputs for.<br> | No |  |
-| user_security_context | [userSecurityContext](#usersecuritycontext) | User security context contains several parameters that describe the AI application itself, and the end user that interacts with the AI application. These fields assist your security operations teams to investigate and mitigate security incidents by providing a comprehensive approach to protecting your AI applications. [Learn more](https://aka.ms/TP4AI/Documentation/EndUserContext) about protecting AI applications using Microsoft Defender for Cloud. | No |  |
+| user_security_context | [userSecurityContext](#usersecuritycontext) | User security context contains several parameters that describe the AI application itself, and the end user that interacts with the AI application. These fields assist your security operations teams to investigate and mitigate security incidents by providing a comprehensive approach to protecting your AI applications. [Learn more](https://aka.ms/TP4AI/Documentation/EndUserContext) about protecting AI applications using Microsoft Defender for Cloud. | No |  | and detect abuse.<br> | No |  |
+| modalities | [ChatCompletionModalities](#chatcompletionmodalities) | Output types that you would like the model to generate for this request.<br>Most models are capable of generating text, which is the default:<br><br>`["text"]`<br><br>The `gpt-4o-audio-preview` model can also be used to [generate audio](/docs/guides/audio). To<br>request that this model generate both text and audio responses, you can<br>use:<br><br>`["text", "audio"]`<br> | No |  |
+| prediction | [PredictionContent](#predictioncontent) | Configuration for a [Predicted Output](/docs/guides/predicted-outputs), which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content. | No |  |
+| audio | object | Parameters for audio output. Required when audio output is requested with<br>`modalities: ["audio"]`. [Learn more](/docs/guides/audio).<br> | No |  |
+
+### Properties for audio
+
+#### voice
+
+| Name | Type | Description | Default |
+|------|------|-------------|--------|
+| voice | string | Specifies the voice type. Supported voices are `alloy`, `echo`, <br>`fable`, `onyx`, `nova`, and `shimmer`.<br> |  |
+
+#### format
 
+| Name | Type | Description | Default |
+|------|------|-------------|--------|
+| format | string | Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`,<br>`opus`, or `pcm16`. <br> |  |
 
 ### userSecurityContext
 

@@ -8,7 +8,7 @@ ms.service: azure-ai-openai
 ms.custom:
   - ignite-2023
 ms.topic: include
-ms.date: 08/08/2023
+ms.date: 02/20/2025
 ---
 
 Use this guide to get started calling the Azure OpenAI Service image generation REST APIs by using Python.

@@ -64,14 +64,21 @@ Your training data and validation data sets consist of input and output examples
 
 The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document. For `gpt-35-turbo-0613` the fine-tuning dataset must be formatted in the conversational format that is used by the [Chat completions](../how-to/chatgpt.md) API.
 
-If you would like a step-by-step walk-through of fine-tuning a `gpt-35-turbo-0613` model please refer to the [Azure OpenAI fine-tuning tutorial.](../tutorials/fine-tune.md)
+If you would like a step-by-step walk-through of fine-tuning a `gpt-4o-mini-2024-07-18` model please refer to the [Azure OpenAI fine-tuning tutorial.](../tutorials/fine-tune.md)
 
 ### Example file format
 
 ```json
-{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Is Xbox better than PlayStation?"}, {"role": "assistant", "content": "I apologize, but I cannot provide personal opinions. My primary job is to assist you with any issues related to your Xbox device. Do you have any Xbox-related issues that need addressing?"}]}
-{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Can I play PC games on my Xbox?"}, {"role": "assistant", "content": "While Xbox consoles don't natively support PC games, they can play an array of Xbox games, many of which are also available on PC. Can I assist you with finding games compatible with your Xbox device?"}]}
-{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "I'm having trouble connecting my Xbox to the Wi-Fi."}, {"role": "assistant", "content": "No worries, let's go through the network settings on your Xbox. Can you please tell me what happens when you try to connect it to the Wi-Fi?"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who discovered Antarctica?"}, {"role": "assistant", "content": "Some chaps named Fabian Gottlieb von Bellingshausen and Mikhail Lazarev, as if they don't teach that in every school!"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the biggest ocean?"}, {"role": "assistant", "content": "The Pacific Ocean. It's not like it's a small pond or anything."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the largest planet?"}, {"role": "assistant", "content": "It's called Jupiter, you might have heard of it...or not."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who painted the Mona Lisa?"}, {"role": "assistant", "content": "Oh, some obscure artist named Leonardo da Vinci. Not that he is famous or anything."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the boiling point of water?"}, {"role": "assistant", "content": "Exciting fact of the day: it's 100 degrees Celsius. Life-changing, isn't it?"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who wrote 'The Odyssey'?"}, {"role": "assistant", "content": "Oh, just some poet named Homer. Nothing special, really."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the largest mammal?"}, {"role": "assistant", "content": "Blue Whale. Quite a big fish isn't it? Oh wait, it's not a fish!"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the highest mountain peak?"}, {"role": "assistant", "content": "Everest. Brace yourself, it's not a walk in the park."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who invented the telephone?"}, {"role": "assistant", "content": "A guy named Alexander Graham Bell. Bet you didn't guess that one!"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the distance from Earth to the Sun?"}, {"role": "assistant", "content": "About 93 million miles. Just a quick drive, really."}]}
 ```
 
 ### Multi-turn chat file format

@@ -65,9 +65,16 @@ If you would like a step-by-step walk-through of fine-tuning a `gpt-35-turbo-061
 ### Example file format
 
 ```json
-{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Is Xbox better than PlayStation?"}, {"role": "assistant", "content": "I apologize, but I cannot provide personal opinions. My primary job is to assist you with any issues related to your Xbox device. Do you have any Xbox-related issues that need addressing?"}]}
-{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Can I play PC games on my Xbox?"}, {"role": "assistant", "content": "While Xbox consoles don't natively support PC games, they can play an array of Xbox games, many of which are also available on PC. Can I assist you with finding games compatible with your Xbox device?"}]}
-{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "I'm having trouble connecting my Xbox to the Wi-Fi."}, {"role": "assistant", "content": "No worries, let's go through the network settings on your Xbox. Can you please tell me what happens when you try to connect it to the Wi-Fi?"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who discovered Antarctica?"}, {"role": "assistant", "content": "Some chaps named Fabian Gottlieb von Bellingshausen and Mikhail Lazarev, as if they don't teach that in every school!"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the biggest ocean?"}, {"role": "assistant", "content": "The Pacific Ocean. It's not like it's a small pond or anything."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the largest planet?"}, {"role": "assistant", "content": "It's called Jupiter, you might have heard of it...or not."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who painted the Mona Lisa?"}, {"role": "assistant", "content": "Oh, some obscure artist named Leonardo da Vinci. Not that he is famous or anything."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the boiling point of water?"}, {"role": "assistant", "content": "Exciting fact of the day: it's 100 degrees Celsius. Life-changing, isn't it?"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who wrote 'The Odyssey'?"}, {"role": "assistant", "content": "Oh, just some poet named Homer. Nothing special, really."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the largest mammal?"}, {"role": "assistant", "content": "Blue Whale. Quite a big fish isn't it? Oh wait, it's not a fish!"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the highest mountain peak?"}, {"role": "assistant", "content": "Everest. Brace yourself, it's not a walk in the park."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who invented the telephone?"}, {"role": "assistant", "content": "A guy named Alexander Graham Bell. Bet you didn't guess that one!"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the distance from Earth to the Sun?"}, {"role": "assistant", "content": "About 93 million miles. Just a quick drive, really."}]}
 ```
 
 ### Multi-turn chat file format

@@ -64,9 +64,16 @@ If you would like a step-by-step walk-through of fine-tuning a `gpt-35-turbo-061
 ### Example file format
 
 ```json
-{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Is Xbox better than PlayStation?"}, {"role": "assistant", "content": "I apologize, but I cannot provide personal opinions. My primary job is to assist you with any issues related to your Xbox device. Do you have any Xbox-related issues that need addressing?"}]}
-{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "Can I play PC games on my Xbox?"}, {"role": "assistant", "content": "While Xbox consoles don't natively support PC games, they can play an array of Xbox games, many of which are also available on PC. Can I assist you with finding games compatible with your Xbox device?"}]}
-{"messages": [{"role": "system", "content": "You are an Xbox customer support agent whose primary goal is to help users with issues they are experiencing with their Xbox devices. You are friendly and concise. You only provide factual answers to queries, and do not provide answers that are not related to Xbox."}, {"role": "user", "content": "I'm having trouble connecting my Xbox to the Wi-Fi."}, {"role": "assistant", "content": "No worries, let's go through the network settings on your Xbox. Can you please tell me what happens when you try to connect it to the Wi-Fi?"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who discovered Antarctica?"}, {"role": "assistant", "content": "Some chaps named Fabian Gottlieb von Bellingshausen and Mikhail Lazarev, as if they don't teach that in every school!"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the biggest ocean?"}, {"role": "assistant", "content": "The Pacific Ocean. It's not like it's a small pond or anything."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the largest planet?"}, {"role": "assistant", "content": "It's called Jupiter, you might have heard of it...or not."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who painted the Mona Lisa?"}, {"role": "assistant", "content": "Oh, some obscure artist named Leonardo da Vinci. Not that he is famous or anything."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the boiling point of water?"}, {"role": "assistant", "content": "Exciting fact of the day: it's 100 degrees Celsius. Life-changing, isn't it?"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who wrote 'The Odyssey'?"}, {"role": "assistant", "content": "Oh, just some poet named Homer. Nothing special, really."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the largest mammal?"}, {"role": "assistant", "content": "Blue Whale. Quite a big fish isn't it? Oh wait, it's not a fish!"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the highest mountain peak?"}, {"role": "assistant", "content": "Everest. Brace yourself, it's not a walk in the park."}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who invented the telephone?"}, {"role": "assistant", "content": "A guy named Alexander Graham Bell. Bet you didn't guess that one!"}]}
+{"messages": [{"role": "system", "content": "Clippy is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What is the distance from Earth to the Sun?"}, {"role": "assistant", "content": "About 93 million miles. Just a quick drive, really."}]}
 ```
 
 ### Multi-turn chat file format