Merge branch 'main' into release-rolling-upgrades-on-flex

Author: v-alje

articles/active-directory-b2c/TOC.yml

@@ -824,8 +824,6 @@
     href: user-flow-versions-legacy.md
 - name: Resources
   items:
-  - name: Azure Roadmap
-    href: https://azure.microsoft.com/updates/?status=nowavailable,inpreview,indevelopment&category=identity,security&query=b2c
   - name: Frequently asked questions
     href: ./faq.yml
     displayName: FAQ

articles/ai-services/openai/assistants-reference.md

@@ -5,7 +5,7 @@ description: Learn how to use Azure OpenAI's Python & REST API with Assistants.
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 05/22/2024
+ms.date: 06/13/2024
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
@@ -35,7 +35,7 @@ Create an assistant with a model and instructions.
 | name | string or null | Optional | The name of the assistant. The maximum length is 256 characters.|
 | description| string or null | Optional | The description of the assistant. The maximum length is 512 characters.|
 | instructions | string or null | Optional | The system instructions that the assistant uses. The maximum length is 256,000 characters.|
-| tools | array | Optional | Defaults to []. A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can currently be of types `code_interpreter`, or `function`.|
+| tools | array | Optional | Defaults to []. A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can currently be of types `code_interpreter`, or `function`. A `function` description can be a maximum of 1,024 characters. |
 | file_ids | array | Optional | Defaults to []. A list of file IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order.|
 | metadata | map | Optional | Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.|
 | temperature | number or null | Optional | Defaults to 1. Determines what sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. |
@@ -360,7 +360,7 @@ Modifies an assistant.
 | `name` | string or null | Optional | The name of the assistant. The maximum length is 256 characters. |
 | `description` | string or null | Optional | The description of the assistant. The maximum length is 512 characters. |
 | `instructions` | string or null | Optional | The system instructions that the assistant uses. The maximum length is 32768 characters. |
-| `tools` | array | Optional | Defaults to []. A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, or function. |
+| `tools` | array | Optional | Defaults to []. A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, or function. A `function` description can be a maximum of 1,024 characters. |
 | `file_ids` | array | Optional | Defaults to []. A list of File IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order. If a file was previously attached to the list but does not show up in the list, it will be deleted from the assistant. |
 | `metadata` | map | Optional | Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long. |
 
@@ -517,7 +517,7 @@ Assistants use the [same API for file upload as fine-tuning](/rest/api/azureopen
 | `description` | string or null | The description of the assistant. The maximum length is 512 characters.|
 | `model` | string | Name of the model deployment name to use.|
 | `instructions` | string or null | The system instructions that the assistant uses. The maximum length is 32768 characters.|
-| `tools` | array | A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, or function.|
+| `tools` | array | A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, or function. A `function` description can be a maximum of 1,024 characters.|
 | `file_ids` | array | A list of file IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order.|
 | `metadata` | map | Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.|
 

articles/ai-services/openai/quotas-limits.md

@@ -27,6 +27,7 @@ The following sections provide you with a quick guide to the default quotas and
 | OpenAI resources per region per Azure subscription | 30 |
 | Default DALL-E 2 quota limits | 2 concurrent requests |
 | Default DALL-E 3 quota limits| 2 capacity units (6 requests per minute)|
+| Default Whisper quota limits | 3 requests per minute |
 | Maximum prompt tokens per request | Varies per model. For more information, see [Azure OpenAI Service models](./concepts/models.md)|
 | Max fine-tuned model deployments | 5 |
 | Total number of training jobs per resource | 100 |
@@ -48,6 +49,7 @@ The following sections provide you with a quick guide to the default quotas and
 | GPT-4o max images per request (# of images in the messages array/conversation history) | 10 |
 | GPT-4 `vision-preview` & GPT-4 `turbo-2024-04-09` default max tokens | 16 <br><br> Increase the `max_tokens` parameter value to avoid truncated responses. GPT-4o max tokens defaults to 4096. |
 
+
 ## Regional quota limits
 
 [!INCLUDE [Quota](./includes/model-matrix/quota.md)]
@@ -99,7 +101,7 @@ If your Azure subscription is linked to certain [offer types](https://azure.micr
 |Azure for Students, Free Trials | 1 K (all models)|
 | Monthly credit card based accounts <sup>1</sup> | GPT 3.5 Turbo Series: 30 K <br> GPT-4 series: 8 K  <br> |
 
-<sup>1</sup>This currently applies to [offer type 0003P](https://azure.microsoft.com/support/legal/offer-details/)
+<sup>1</sup> This currently applies to [offer type 0003P](https://azure.microsoft.com/support/legal/offer-details/)
 
 In the Azure portal you can view what offer type is associated with your subscription by navigating to your subscription and checking the subscriptions overview pane. Offer type corresponds to the plan field in the subscription overview.
 

articles/ai-services/openai/whats-new.md

@@ -10,7 +10,7 @@ ms.custom:
   - ignite-2023
   - references_regions
 ms.topic: whats-new
-ms.date: 06/11/2024
+ms.date: 06/13/2024
 recommendations: false
 ---
 
@@ -20,6 +20,10 @@ This article provides a summary of the latest releases and major documentation u
 
 ## June 2024
 
+### Token based billing for fine-tuning
+
+* Azure OpenAI fine-tuning billing is now based on the number of tokens in your training file – instead of the total elapsed training time. This can result in a significant cost reduction for some training runs, and makes estimating fine-tuning costs much easier. To learn more, you can consult the [official announcement](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/pricing-update-token-based-billing-for-fine-tuning-training/ba-p/4164465).
+
 ### GPT-4o released in new regions
 
 * GPT-4o is now also available in:

articles/ai-services/speech-service/text-to-speech-avatar/content-credentials.md

@@ -0,0 +1,48 @@
+---
+title: Content Credentials in Azure Text to Speech Avatar
+titleSuffix: Azure Text to Speech Avatar
+description: Learn about the content credentials feature, which lets you verify that a video was generated by the Azure text to speech avatar system.
+author: sally-baolian
+ms.author: v-baolianzou
+ms.service: azure-ai-speech
+ms.topic: conceptual 
+ms.date: 6/11/2024
+manager: nitinme
+---
+
+# Content credentials
+
+The high-quality models in the Azure text to speech avatar feature generate realistic avatar videos from text input. To improve the transparency of the generated content, the Azure text to speech avatar provides content credentials, a tamper-evident way to disclose the origin and history of the 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?
+
+Content credentials in the Azure text to speech avatar provide customers with information about the origin of an avatar video. This information is represented by a manifest attached to the video. The manifest is cryptographically signed by a certificate that traces back to Azure text to speech avatar.
+
+The manifest contains several key pieces of information:
+
+| Field name | Field content |
+| --- | --- |
+| `"generator"` | This field has a value of `"Microsoft Azure Text To Speech Avatar Service"` for all applicable videos, attesting to the AI-generated nature of the video. |
+| `"when"` | The timestamp of when the content credentials were created. |
+
+Content credentials in the Azure text to speech avatar can help people understand when video content is generated by the Azure text to speech avatar system. For more information on how to responsibly build solutions with text to speech avatar models, visit the [Text to speech transparency note](/legal/cognitive-services/speech-service/text-to-speech/transparency-note?context=/azure/ai-services/speech-service/context/context).
+
+## Limitations
+
+The content credentials are only supported in video files generated by batch synthesis of text to speech avatar, and only `mp4` file format is supported.  
+
+## How do I leverage content credentials in my solution today?
+
+You may leverage content credentials by:
+
+- Ensuring that your Azure text to speech avatar generated video files contain content credentials
+
+No additional set-up is necessary. Content credentials are automatically applied to all applicable videos generated by the Azure text to speech avatar.
+
+## Verifying that a video file has content credentials
+
+As for now, self-serve verification of content credentials for text to speech avatar video isn't yet available. You can contact [[email protected]](mailto:[email protected]) through email for verification of content credentials of Azure text to speech avatar generated videos.
+
+## Next steps
+
+* [Use batch synthesis for text to speech avatar](./batch-synthesis-avatar.md)

articles/ai-services/speech-service/toc.yml

@@ -200,6 +200,8 @@ items:
       - name: What is text to speech avatar?
         href: text-to-speech-avatar/what-is-text-to-speech-avatar.md
         displayName: avatar
+      - name: Content credentials
+        href: text-to-speech-avatar/content-credentials.md
       - name: How to synthesize text to speech avatar
         items:
         - name: Real-time synthesis

articles/ai-studio/reference/reference-model-inference-api.md

@@ -32,7 +32,7 @@ While foundational models excel in specific domains, they lack a uniform set of
 > * Use smaller models that can run faster on specific tasks.
 > * Compose multiple models to develop intelligent experiences.
 
-Having a uniform way to consume foundational models allow developers to realize all those benefits without changing a single line of code on their applications.
+Having a uniform way to consume foundational models allow developers to realize all those benefits without sacrificing portability or changing the underlying code.
 
 ## Availability
 
@@ -43,8 +43,8 @@ Models deployed to [serverless API endpoints](../how-to/deploy-models-serverless
 > [!div class="checklist"]
 > * [Cohere Embed V3](../how-to/deploy-models-cohere-embed.md) family of models
 > * [Cohere Command R](../how-to/deploy-models-cohere-command.md) family of models
-> * [Meta Llama 2](../how-to/deploy-models-llama.md) family of models
-> * [Meta Llama 3](../how-to/deploy-models-llama.md) family of models
+> * [Meta Llama 2 chat](../how-to/deploy-models-llama.md) family of models
+> * [Meta Llama 3 instruct](../how-to/deploy-models-llama.md) family of models
 > * [Mistral-Small](../how-to/deploy-models-mistral.md)
 > * [Mistral-Large](../how-to/deploy-models-mistral.md)
 > * [Phi-3](../how-to/deploy-models-phi-3.md) family of models
@@ -154,6 +154,49 @@ __Response__
 > [!TIP]
 > You can inspect the property `details.loc` to understand the location of the offending parameter and `details.input` to see the value that was passed in the request.
 
+## Content safety
+
+The Azure AI model inference API supports [Azure AI Content Safety](../concepts/content-filtering.md). When using deployments with Azure AI Content Safety 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 following example shows the response for a chat completion request that has triggered content safety. 
+
+__Request__
+
+```HTTP/1.1
+POST /chat/completions?api-version=2024-04-01-preview
+Authorization: Bearer <bearer-token>
+Content-Type: application/json
+```
+
+```JSON
+{
+    "messages": [
+    {
+        "role": "system",
+        "content": "You are a helpful assistant"
+    },
+    {
+        "role": "user",
+        "content": "Chopping tomatoes and cutting them into cubes or wedges are great ways to practice your knife skills."
+    }
+    ],
+    "temperature": 0,
+    "top_p": 1,
+}
+```
+
+__Response__
+
+```JSON
+{
+    "status": 400,
+    "code": "content_filter",
+    "message": "The response was filtered",
+    "param": "messages",
+    "type": null
+}
+```
+
 ## Getting started
 
 The Azure AI Model Inference API is currently supported in models deployed as [Serverless API endpoints](../how-to/deploy-models-serverless.md). Deploy any of the [supported models](#availability) to a new [Serverless API endpoints](../how-to/deploy-models-serverless.md) to get started. Then you can consume the API in the following ways: