Merge pull request #3155 from MicrosoftDocs/main

02/25/2025 11:00 AM IST Publish

Author: PhilKang0704

.openpublishing.redirection.json

@@ -1,5 +1,15 @@
 {
   "redirections": [
+    {
+      "source_path": "articles/search/performance-benchmarks.md",
+      "redirect_url": "/previous-versions/azure/search/performance-benchmarks",
+      "redirect_document_id": false
+    },
+    {
+      "source_path": "articles/search/search-traffic-analytics.md",
+      "redirect_url": "/previous-versions/azure/search/search-traffic-analytics",
+      "redirect_document_id": false
+    },
     {
       "source_path": "articles/genomics/frequently-asked-questions-genomics.yml",
       "redirect_url": "/previous-versions/azure/genomics/frequently-asked-questions-genomics",

articles/ai-foundry/model-inference/includes/configure-entra-id/intro.md

@@ -47,3 +47,17 @@ To complete this article, you need:
   * Security principal: e.g. your user account.
   * Role definition: the *Cognitive Services User* role.
   * Scope: the Azure AI Services resource.
+
+* If you want to create a custom role definition instead of using *Cognitive Services User* role, ensure the role has the following permissions:
+
+  ```json
+  {
+    "permissions": [
+      {
+        "dataActions": [
+          "Microsoft.CognitiveServices/accounts/MaaS/*"
+        ]
+      }
+    ]
+  }
+  ```

articles/ai-services/openai/concepts/model-retirements.md

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn about the model deprecations and retirements in Azure OpenAI.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 02/20/2025
+ms.date: 02/24/2025
 ms.custom: 
 manager: nitinme
 author: mrbullwinkle
@@ -94,17 +94,15 @@ These models are currently available for use in Azure OpenAI Service.
 | Model | Version | Retirement date | Suggested replacements |
 | ---- | ---- | ---- | --- |
 | `dall-e-3` | 3 | No earlier than April 30, 2025 | |
-| `gpt-35-turbo` | 0301 | February 13, 2025<br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 21, 2025.   | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`  |
-| `gpt-35-turbo` | 0613 | February 13, 2025 <br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 21, 2025.  | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`|
 | `gpt-35-turbo-16k`| 0613 | April, 30, 2025 | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`|
 | `gpt-35-turbo` | 1106 | No earlier than May 31, 2025 <br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 21, 2025. | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini` |
 | `gpt-35-turbo` | 0125 | No earlier than May 31, 2025 | `gpt-4o-mini` |
 | `gpt-4`<br>`gpt-4-32k` | 0314 | June 6, 2025 | `gpt-4o` |
 | `gpt-4`<br>`gpt-4-32k` | 0613 | June 6, 2025 | `gpt-4o` |
 | `gpt-4` | turbo-2024-04-09 | No earlier than June 6, 2025 | `gpt-4o`|
-| `gpt-4` | 1106-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025 **<sup>1</sup>** <br>Retirement date: February 28, 2025  | `gpt-4o`|
-| `gpt-4` | 0125-preview |To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025 **<sup>1</sup>** <br>Retirement date: February 28, 2025  | `gpt-4o` |
-| `gpt-4` | vision-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025  **<sup>1</sup>** <br>Retirement date: February 28, 2025 | `gpt-4o`|
+| `gpt-4` | 1106-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025 **<sup>1</sup>** <br>Retirement date: April 02, 2025  | `gpt-4o`|
+| `gpt-4` | 0125-preview |To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025 **<sup>1</sup>** <br>Retirement date: April 02, 2025  | `gpt-4o` |
+| `gpt-4` | vision-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025  **<sup>1</sup>** <br>Retirement date: April 02, 2025 | `gpt-4o`|
 | `gpt-4o` | 2024-05-13 | No earlier than May 20, 2025 <br><br>Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `2024-08-06`, starting on February 13, 2025. | |
 | `gpt-4o` | 2024-08-06 | No earlier than August 6, 2025  | |
 | `gpt-4o` | 2024-11-20 | No earlier than November 20, 2025  | |
@@ -138,6 +136,8 @@ If you're an existing customer looking for information about these models, see [
 
 | Model | Deprecation date | Retirement date | Suggested replacement |
 | --------- | --------------------- | ------------------- | -------------------- |
+| `gpt-35-turbo` - 0301 | | February 13, 2025   | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`  |
+| `gpt-35-turbo` - 0613 | | February 13, 2025 | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`  |
 | babbage-002 | | January 27, 2025 |  |
 | davinci-002 | | January 27, 2025 | |
 | dall-e-2|  | January 27, 2025 | dalle-3 |

articles/ai-services/openai/how-to/create-resource.md

@@ -46,6 +46,7 @@ In this article, you review examples for creating and deploying resources in the
 
 ## Next steps
 
+- [Get started with the Azure OpenAI security building block](/azure/developer/ai/get-started-securing-your-ai-app?tabs=github-codespaces&pivots=python)
 - Make API calls and generate text with [Azure OpenAI Service quickstarts](../quickstart.md).
 - Learn more about the [Azure OpenAI Service models](../concepts/models.md).
 - For information on pricing visit the [Azure OpenAI pricing page](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/)

articles/ai-services/openai/how-to/role-based-access-control.md

@@ -208,5 +208,6 @@ Possible reasons why the user may **not** have permissions:
 
 ## Next steps
 
+- [Get started with the Azure OpenAI security building block](/azure/developer/ai/get-started-securing-your-ai-app?tabs=github-codespaces&pivots=python)
 - Learn more about [Azure-role based access control (Azure RBAC)](/azure/role-based-access-control/).
 - Also check out[assign Azure roles using the Azure portal](/azure/role-based-access-control/role-assignments-portal).

articles/ai-services/openai/includes/fine-tuning-studio.md

@@ -64,9 +64,16 @@ If you would like a step-by-step walk-through of fine-tuning a `gpt-4o-mini` (20
 ### 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 Azure OpenAI 

articles/ai-services/speech-service/batch-synthesis-properties.md

@@ -45,7 +45,7 @@ Batch synthesis properties are described in the following table.
 |`properties.outputFormat`|The audio output format.<br/><br/>For information about the accepted values, see [audio output formats](rest-text-to-speech.md#audio-outputs). The default output format is `riff-24khz-16bit-mono-pcm`.|
 |`properties.sentenceBoundaryEnabled`|Determines whether to generate sentence boundary data. This optional `bool` value ("true" or "false") is "false" by default.<br/><br/>If sentence boundary data is requested, then a corresponding `[nnnn].sentence.json` file is included in the results data ZIP file.|
 |`properties.succeededAudioCount`|The count of batch synthesis inputs to audio output succeeded.<br/><br/>This property is read-only.|
-|`properties.timeToLiveInHours`|A duration in hours after the synthesis job is created, when the synthesis results will be automatically deleted. This optional setting is `744` (31 days) by default. The maximum time to live is 31 days. The date and time of automatic deletion (for synthesis jobs with a status of "Succeeded" or "Failed") is equal to the `lastActionDateTime` + `timeToLiveInHours` properties.<br/><br/>Otherwise, you can call the [delete](./batch-synthesis.md#delete-batch-synthesis) synthesis method to remove the job sooner.|
+|`properties.timeToLiveInHours`|A duration in hours after the synthesis job is completed, when the synthesis results will be automatically deleted. This optional setting is `168` (7 days) by default. The maximum time to live is `744` (31 days). The date and time of automatic deletion (for synthesis jobs with a status of "Succeeded" or "Failed") is equal to the `lastActionDateTime` + `timeToLiveInHours` properties.<br/><br/>Otherwise, you can call the [delete](./batch-synthesis.md#delete-batch-synthesis) synthesis method to remove the job sooner.|
 |`properties.wordBoundaryEnabled`|Determines whether to generate word boundary data. This optional `bool` value ("true" or "false") is "false" by default.<br/><br/>If word boundary data is requested, then a corresponding `[nnnn].word.json` file is included in the results data ZIP file.|
 |`status`|The batch synthesis processing status.<br/><br/>The status should progress from "NotStarted" to "Running", and finally to either "Succeeded" or "Failed".<br/><br/>This property is read-only.|
 |`synthesisConfig`|The configuration settings to use for batch synthesis of plain text.<br/><br/>This property is only applicable when `inputKind` is set to `"PlainText"`.|

articles/ai-services/speech-service/batch-synthesis.md

@@ -83,7 +83,7 @@ You should receive a response body in the following format:
   "inputKind": "SSML",
   "customVoices": {},
   "properties": {
-    "timeToLiveInHours": 744,
+    "timeToLiveInHours": 168,
     "outputFormat": "riff-24khz-16bit-mono-pcm",
     "concatenateResult": false,
     "decompressOutputFiles": false,
@@ -115,7 +115,7 @@ You should receive a response body in the following format:
   "inputKind": "SSML",
   "customVoices": {},
   "properties": {
-    "timeToLiveInHours": 744,
+    "timeToLiveInHours": 168,
     "outputFormat": "riff-24khz-16bit-mono-pcm",
     "concatenateResult": false,
     "decompressOutputFiles": false,
@@ -159,7 +159,7 @@ You should receive a response body in the following format:
       "inputKind": "SSML",
       "customVoices": {},
       "properties": {
-        "timeToLiveInHours": 744,
+        "timeToLiveInHours": 168,
         "outputFormat": "riff-24khz-16bit-mono-pcm",
         "concatenateResult": false,
         "decompressOutputFiles": false,
@@ -186,7 +186,7 @@ You should receive a response body in the following format:
       "inputKind": "SSML",
       "customVoices": {},
       "properties": {
-        "timeToLiveInHours": 744,
+        "timeToLiveInHours": 168,
         "outputFormat": "riff-24khz-16bit-mono-pcm",
         "concatenateResult": false,
         "decompressOutputFiles": false,
@@ -215,7 +215,7 @@ The `value` property in the json response lists your synthesis requests. The lis
 
 ## Delete batch synthesis
 
-Delete the batch synthesis job history after you retrieved the audio output results. The Speech service keeps batch synthesis history for up to 31 days, or the duration of the request `timeToLiveInHours` property, whichever comes sooner. The date and time of automatic deletion (for synthesis jobs with a status of "Succeeded" or "Failed") is equal to the `lastActionDateTime` + `timeToLiveInHours` properties.
+Delete the batch synthesis job history after you retrieved the audio output results. The Speech service keeps batch synthesis history for 168 hours (7 days) by default. Alternatively, you can specify this retention period using the `timeToLiveInHours` property, up to 744 hours (31 days). The date and time of automatic deletion (for synthesis jobs with a status of "Succeeded" or "Failed") is equal to the `lastActionDateTime` + `timeToLiveInHours` properties.
 
 To delete a batch synthesis job, make an HTTP DELETE request using the URI as shown in the following example. Replace `YourSynthesisId` with your batch synthesis ID, replace `YourSpeechKey` with your Speech resource key, and replace `YourSpeechRegion` with your Speech resource region.
 
@@ -248,9 +248,7 @@ The summary file contains the synthesis results for each text input. Here's an e
   "status": "Succeeded",
   "results": [
     {
-      "contents": [
-        "<speak version=\"1.0\" xml:lang=\"en-US\"><voice name=\"en-US-JennyNeural\">The rainbow has seven colors.</voice></speak>"
-      ],
+      "contents": ["<speak version=\"1.0\" xml:lang=\"en-US\"><voice name=\"en-US-JennyNeural\">The rainbow has seven colors.</voice></speak>"],
       "status": "Succeeded",
       "audioFileName": "0001.wav",
       "properties": {

articles/search/cognitive-search-concept-intro.md

@@ -10,14 +10,14 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: conceptual
-ms.date: 09/04/2024
+ms.date: 02/24/2025
 ---
 
 # AI enrichment in Azure AI Search
 
 In Azure AI Search, *AI enrichment* refers to integration with [Azure AI services](/azure/ai-services/what-are-ai-services) to process content that isn't searchable in its raw form. Through enrichment, analysis and inference are used to create searchable content and structure where none previously existed. 
 
-Because Azure AI Search is used for text and vector queries, the purpose of AI enrichment is to improve the utility of your content in search-related scenarios. Raw content must be text or images (you can't enrich vectors), but the output of an enrichment pipeline can be vectorized and indexed in a vector index using skills like [Text Split skill](cognitive-search-skill-textsplit.md) for chunking and [AzureOpenAIEmbedding skill](cognitive-search-skill-azure-openai-embedding.md) for encoding. For more information about using skills in vector scenarios, see [Integrated data chunking and embedding](vector-search-integrated-vectorization.md).
+Because Azure AI Search is used for text and vector queries, the purpose of AI enrichment is to improve the utility of your content in search-related scenarios. Raw content must be text or images (you can't enrich vectors), but the output of an enrichment pipeline can be vectorized and indexed in a search index using skills like [Text Split skill](cognitive-search-skill-textsplit.md) for chunking and [AzureOpenAIEmbedding skill](cognitive-search-skill-azure-openai-embedding.md) for vector encoding. For more information about using skills in vector scenarios, see [Integrated data chunking and embedding](vector-search-integrated-vectorization.md).
 
 AI enrichment is based on [*skills*](cognitive-search-working-with-skillsets.md).
 

articles/search/index-ranking-similarity.md

@@ -8,7 +8,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 07/22/2024
+ms.date: 02/24/2025
 ---
 
 # Configure BM25 relevance scoring