Merge pull request #4343 from MicrosoftDocs/main

Merged by Learn.Build PR Management system

Author: learn-build-service-prod[bot]

articles/ai-foundry/how-to/fine-tune-managed-compute.md

@@ -5,7 +5,7 @@ description: Learn how to fine-tune models using a managed compute with Azure AI
 manager: scottpolly
 ms.service: azure-ai-foundry
 ms.topic: how-to
-ms.date: 11/22/2024
+ms.date: 04/25/2025
 ms.reviewer: vkann
 reviewer: kvijaykannan
 ms.author: mopeakande
@@ -77,4 +77,5 @@ In this section, you go through the steps to configure fine-tuning for your mode
 ## Related Contents
 
 - [Fine-tune models with Azure AI Foundry](../concepts/fine-tuning-overview.md)
-- [How to use Phi-3 family chat models](deploy-models-phi-3.md)
+- [How to generate chat completions with Azure AI model inference](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context)
+- [Featured models of Azure AI Foundry](../concepts/models-featured.md)

articles/ai-services/openai/azure-government.md

@@ -24,10 +24,18 @@ The following sections show model availability by region and deployment type. Mo
 <br>
 
 ## Standard deployment model availability
-|   **Region**  | **gpt-4o**, **2024-05-13** | **gpt-4o-mini**, **2024-07-18** | **gpt-4**, **1106-Preview** | **gpt-35-turbo**, **0125** | **gpt-35-turbo**, **1106** | **text-embedding-3-large**, **1** | **text-embedding-ada-002**, **2** |
-|:--------------|:--------------------------:|:-------------------------------:|:---------------------------:|:--------------------------:|:--------------------------:|:---------------------------------:|:---------------------------------:|
-| usgovarizona  | ✅ | ✅ | ✅ | ✅ | -  | ✅ | ✅ |
-| usgovvirginia | ✅ | -  | ✅ | ✅ | ✅ |  - | ✅ |
+|   **Region**  | **o3-mini USGov DataZone** | **gpt-4o**, **2024-05-13** | **gpt-4o-mini**, **2024-07-18** | **gpt-4**, **1106-Preview** | **gpt-35-turbo**, **0125** | **gpt-35-turbo**, **1106** | **text-embedding-3-large**, **1** | **text-embedding-ada-002**, **2** |
+|:--------------|:--------------------------:|:--------------------------:|:-------------------------------:|:---------------------------:|:--------------------------:|:--------------------------:|:---------------------------------:|:---------------------------------:|
+| usgovarizona  | ✅ | ✅ | ✅ | ✅ | ✅ | -  | ✅ | ✅ |
+| usgovvirginia | ✅ | ✅ | -  | ✅ | ✅ | ✅ |  - | ✅ |
+
+* USGov DataZone provides access to the model from both usgovarizona and usgovvirginia.
+* Data stored at rest remains in the designated Azure region of the resource.
+* Data may be processed for inferencing in either of the two Azure Government regions. 
+
+SKU name in code: DataZoneStandard
+
+Data zone standard deployments are available in the same Azure OpenAI resource as all other Azure OpenAI deployment types but allow you to leverage Azure global infrastructure to dynamically route traffic to the data center within the Microsoft defined data zone with the best availability for each request. Data zone standard provides higher default quotas than our Azure geography-based deployment types.
 
 To request quota increases for these models, submit a request at [https://aka.ms/AOAIGovQuota](https://aka.ms/AOAIGovQuota). Note the following maximum quota limits allowed via that form:
 

articles/ai-services/openai/includes/api-versions/latest-inference-preview.md

@@ -1215,17 +1215,21 @@ Generates a batch of images from a text caption on a given DALL-E or GPT-image-1
 
 **Content-Type**: application/json
 
+
 | Name | Type | Description | Required | Default |
 |------|------|-------------|----------|---------|
 | n | integer | The number of images to generate. | No | 1 |
 | prompt | string | A text description of the desired image(s). The maximum length is 4000 characters. | Yes |  |
 | quality | [imageQuality](#imagequality) | The quality of the image that will be generated. | No | standard (for DALL-E)</br>high (for GPT-image-1) |
 | response_format | [imagesResponseFormat](#imagesresponseformat) | The format in which the generated images are returned. | No | url |
 | size | [imageSize](#imagesize) | The size of the generated images. | No | 1024x1024 |
-| style | [imageStyle](#imagestyle) | The style of the generated images. | No | vivid |
+| style | [imageStyle](#imagestyle) | The style of the generated images. (DALL-E 3 only)| No | vivid |
 | user | string | A unique identifier representing your end-user, which can help to monitor and detect abuse. | No |  |
-| output_format | string | The format in which the generated images are returned. GPT-image-1 models only. | No | PNG |
-| output_compression | integer | The compression level (on a scale of 0-100) of the generated images. GPT-image-1 | No | 0 |
+| output_format | [imageOutputFormat](#imageoutputformat) | The format in which the generated images are returned. (GPT-image-1 only) | No | PNG |
+| safety | [imageSafety](#imagesafety) | The safety setting of the image generation process. (GPT-image-1 only) | No | auto |
+ | No | auto |
+| background | [imageBackground](#imagebackground) | The desired appearance of the background of the image. (GPT-image-1 only) | No | auto |
+| compression_level | integer | The compression level (on a scale of 0-100) of the generated images. (GPT-image-1 only) | No | 0 |
 
 ### Responses
 
@@ -1355,6 +1359,7 @@ Generates an image based on an input image and text prompt instructions. Require
 
 **Content-Type**: application/json
 
+
 | Name | Type | Description | Required | Default |
 |------|------|-------------|----------|---------|
 | image | file | The input image to edit. Must be a valid image URL or base64-encoded image. | Yes |  |
@@ -1364,10 +1369,8 @@ Generates an image based on an input image and text prompt instructions. Require
 | quality | string | The quality of the image that will be generated. Values are 'low', 'medium', 'high' | No | high |
 | response_format | [imagesResponseFormat](#imagesresponseformat) | The format in which the generated images are returned. | No | url |
 | size | [imageSize](#imagesize) | The size of the generated images. | No | 1024x1024 |
-| style | [imageStyle](#imagestyle) | The style of the generated images. | No | vivid |
 | user | string | A unique identifier representing your end-user, which can help to monitor and detect abuse. | No |  |
 | output_format | [imageOutputFormat](#imageoutputformat) | The format in which the generated images are returned. | No | PNG |
-| output_compression | integer | The compression level (on a scale of 0-100) of the generated images. GPT-image-1 | No | 0 |
 
 
 ### Responses
@@ -6121,13 +6124,24 @@ Speech request.
 | speed | number | The speed of the synthesized audio. Select a value from `0.25` to `4.0`. `1.0` is the default. | No | 1.0 |
 | voice | enum | The voice to use for speech synthesis.<br>Possible values: `alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer` | Yes |  |
 
+### imageBackground
+
+The desired appearance of the background of the image.
+
+| Property | Value |
+|----------|-------|
+| **Description** | The desired appearance of the background of the image. |
+| **Type** | string |
+| **Default** | auto |
+| **Values** | `transparent`</br>`opaque`</br>`auto`|
+
 ### imageOutputFormat
 
-The requested output format for the generated image.
+The format in which the generated images are returned.
 
 | Property | Value |
 |----------|-------|
-| **Description** | The requested output format for the generated image. |
+| **Description** | The format in which the generated images are returned. |
 | **Type** | string |
 | **Default** | PNG |
 | **Values** | `PNG`<br>`JPEG` |
@@ -6154,6 +6168,19 @@ The format in which the generated images are returned.
 | **Default** | url |
 | **Values** | `url`<br>`b64_json` |
 
+### imageSafety
+
+The safety setting of the image generation process.
+
+| Property | Value |
+|----------|-------|
+| **Description** | The safety setting of the image generation process. |
+| **Type** | string |
+| **Default** | auto |
+| **Values** | `strict`</br>`auto`|
+
+
+
 ### imageSize
 
 The size of the generated images.
@@ -6163,7 +6190,7 @@ The size of the generated images.
 | **Description** | The size of the generated images. |
 | **Type** | string |
 | **Default** | 1024x1024 |
-| **Values** | `256x256`<br>`512x512`<br>`1792x1024`<br>`1024x1792`<br>`1024x1024` |
+| **Values** | `256x256`, `512x512`, `1792x1024`, `1024x1792`, `1024x1024` (for DALL-E)</br>`1024x1024`, `1024x1536`, `1536x1024` (for GPT-image-1) |
 
 ### imageStyle
 
@@ -6185,10 +6212,13 @@ The style of the generated images.
 | quality | [imageQuality](#imagequality) | The quality of the image that will be generated. | No | standard (for DALL-E)</br>high (for GPT-image-1) |
 | response_format | [imagesResponseFormat](#imagesresponseformat) | The format in which the generated images are returned. | No | url |
 | size | [imageSize](#imagesize) | The size of the generated images. | No | 1024x1024 |
-| style | [imageStyle](#imagestyle) | The style of the generated images. | No | vivid |
+| style | [imageStyle](#imagestyle) | The style of the generated images. (DALL-E 3 only)| No | vivid |
 | user | string | A unique identifier representing your end-user, which can help to monitor and detect abuse. | No |  |
-| output_format | string | The format in which the generated images are returned. GPT-image-1 models only. | No | PNG |
-| output_compression | integer | The compression level (on a scale of 0-100) of the generated images. GPT-image-1 | No | 0 |
+| output_format | [imageOutputFormat](#imageoutputformat) | The format in which the generated images are returned. (GPT-image-1 only) | No | PNG |
+| safety | [imageSafety](#imagesafety) | The safety setting of the image generation process. (GPT-image-1 only) | No | auto |
+ | No | auto |
+| background | [imageBackground](#imagebackground) | The desired appearance of the background of the image. (GPT-image-1 only) | No | auto |
+| compression_level | integer | The compression level (on a scale of 0-100) of the generated images. (GPT-image-1 only) | No | 0 |
 
 ### imageEditsRequest
 
@@ -6202,10 +6232,9 @@ The style of the generated images.
 | quality | string | The quality of the image that will be generated. Values are 'low', 'medium', 'high' | No | high |
 | response_format | [imagesResponseFormat](#imagesresponseformat) | The format in which the generated images are returned. | No | url |
 | size | [imageSize](#imagesize) | The size of the generated images. | No | 1024x1024 |
-| style | [imageStyle](#imagestyle) | The style of the generated images. | No | vivid |
 | user | string | A unique identifier representing your end-user, which can help to monitor and detect abuse. | No |  |
 | output_format | [imageOutputFormat](#imageoutputformat) | The format in which the generated images are returned. | No | PNG |
-| output_compression | integer | The compression level (on a scale of 0-100) of the generated images. GPT-image-1 | No | 0 |
+