Merge pull request #1857 from MicrosoftDocs/main

Taojunshen · web-flow · commit d62332b95706 · 2024-12-06T07:00:58.000+08:00
12/5/2024 PM Publish
diff --git a/articles/ai-services/openai/concepts/models.md b/articles/ai-services/openai/concepts/models.md
@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn about the different model capabilities that are available with Azure OpenAI.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 10/25/2024
+ms.date: 12/05/2024
 ms.custom: references_regions, build-2023, build-2023-dataai, refefences_regions
 manager: nitinme
 author: mrbullwinkle #ChrisHMSFT
@@ -388,7 +388,13 @@ All deployments can perform the exact same inference operations, however the bil
 
 ### Data zone standard model availability
 
-[!INCLUDE [Global batch](../includes/model-matrix/datazone-standard.md)]
+[!INCLUDE [Data zone standard](../includes/model-matrix/datazone-standard.md)]
+
+# [Data Zone Provisioned Managed](#tab/datazone-provisioned-managed)
+
+### Data zone provisioned managed model availability
+
+[!INCLUDE [Global data zone provisioned managed](../includes/model-matrix/datazone-provisioned-managed.md)]
 
 # [Standard](#tab/standard)
 
diff --git a/articles/ai-services/openai/includes/model-matrix/datazone-provisioned-managed.md b/articles/ai-services/openai/includes/model-matrix/datazone-provisioned-managed.md
@@ -0,0 +1,16 @@
+---
+title: Data zone provisioned managed  model availability
+titleSuffix: Azure OpenAI Service
+description: Regional availability for data zone provisioned managed models
+manager: nitinme
+ms.service: azure-ai-openai
+ms.topic: include
+ms.date: 12/05/2024
+---
+
+| **Region**   | **gpt-4o**, **2024-05-13**   | **gpt-4o**, **2024-08-06**   | **gpt-4o-mini**, **2024-07-18**   |
+|:-----------------|:--------------------------:|:--------------------------:|:-------------------------------:|
+| eastus2          | ✅                       | ✅                       | ✅                            |
+| spaincentral     | ✅                       | ✅                       | ✅                            |
+| westeurope       | ✅                       | ✅                       | ✅                            |
+| westus3          | ✅                       | ✅                       | ✅                            |
diff --git a/articles/ai-studio/concepts/rbac-ai-studio.md b/articles/ai-studio/concepts/rbac-ai-studio.md
@@ -9,7 +9,7 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: conceptual
-ms.date: 9/12/2024
+ms.date: 12/05/2024
 ms.reviewer: deeikele
 ms.author: larryfr
 author: Blackmist
diff --git a/articles/ai-studio/how-to/configure-private-link.md b/articles/ai-studio/how-to/configure-private-link.md
@@ -6,7 +6,7 @@ manager: scottpolly
 ms.service: azure-ai-studio
 ms.custom: ignite-2023, devx-track-azurecli, build-2024, ignite-2024
 ms.topic: how-to
-ms.date: 5/21/2024
+ms.date: 12/05/2024
 ms.reviewer: meerakurup
 ms.author: larryfr
 author: Blackmist
diff --git a/articles/ai-studio/how-to/develop/connections-add-sdk.md b/articles/ai-studio/how-to/develop/connections-add-sdk.md
@@ -8,7 +8,7 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: how-to
-ms.date: 9/12/2024
+ms.date: 12/05/2024
 ms.reviewer: dantaylo
 ms.author: larryfr
 author: Blackmist
diff --git a/articles/ai-studio/how-to/develop/simulator-interaction-data.md b/articles/ai-studio/how-to/develop/simulator-interaction-data.md
@@ -54,7 +54,6 @@ You can generate query response pairs from a text blob like the following Wikipe
 
 ```python
 import asyncio
-from simulator import Simulator
 from azure.identity import DefaultAzureCredential
 import wikipedia
 import os
@@ -161,7 +160,11 @@ The callback function above processes each message generated by the simulator.
 With the simulator initialized, you can now run it to generate synthetic conversations based on the provided text.
 
 ```python
-    simulator = Simulator(azure_ai_project=azure_ai_project)
+    model_config = {
+        "azure_endpoint": "<your_azure_endpoint>",
+        "azure_deployment": "<deployment_name>"
+    }
+    simulator = Simulator(model_config=model_config)
     
     outputs = await simulator(
         target=callback,
diff --git a/articles/ai-studio/how-to/disaster-recovery.md b/articles/ai-studio/how-to/disaster-recovery.md
@@ -10,7 +10,7 @@ ms.topic: how-to
 ms.author: larryfr
 author: Blackmist
 ms.reviewer: andyaviles
-ms.date: 5/21/2024
+ms.date: 12/05/2024
 ---
 
 # Customer enabled disaster recovery
diff --git a/articles/ai-studio/how-to/fine-tune-phi-3.md b/articles/ai-studio/how-to/fine-tune-phi-3.md
@@ -7,6 +7,8 @@ ms.service: azure-ai-studio
 ms.custom:
 ms.topic: how-to
 ms.date: 7/16/2024
+ms.author: ssalgado
+author: ssalgadodev
 ---
 
 # Fine-tune Phi-3 models in Azure AI Foundry portal
diff --git a/articles/ai-studio/includes/dependent-resources.md b/articles/ai-studio/includes/dependent-resources.md
@@ -6,7 +6,7 @@ ms.reviewer: larryfr
 ms.author: larryfr
 ms.service: azure-ai-studio
 ms.topic: include
-ms.date: 5/21/2024
+ms.date: 12/05/2024
 ms.custom: include, build-2024
 ---
 
diff --git a/articles/ai-studio/includes/resource-provider-kinds.md b/articles/ai-studio/includes/resource-provider-kinds.md
@@ -6,7 +6,7 @@ ms.reviewer: larryfr
 ms.author: larryfr
 ms.service: azure-ai-studio
 ms.topic: include
-ms.date: 5/21/2024
+ms.date: 12/05/2024
 ms.custom: include, build-2024
 ---
 
diff --git a/articles/machine-learning/how-to-use-batch-model-openai-embeddings.md b/articles/machine-learning/how-to-use-batch-model-openai-embeddings.md
@@ -1,7 +1,7 @@
 ---
-title: 'Run OpenAI models in batch endpoints'
+title: 'Run Azure OpenAI models in batch endpoints'
 titleSuffix: Azure Machine Learning
-description: In this article, learn how to use batch endpoints with OpenAI models.
+description: In this article, learn how to use batch endpoints with Azure OpenAI models.
 services: machine-learning
 ms.service: azure-machine-learning
 ms.subservice: inferencing
@@ -13,15 +13,15 @@ ms.date: 11/04/2023
 ms.custom: how-to, devplatv2, update-code
 ---
 
-# Run OpenAI models in batch endpoints to compute embeddings
+# Run Azure OpenAI models in batch endpoints to compute embeddings
 
 [!INCLUDE [cli v2](includes/machine-learning-dev-v2.md)]
 
-Batch Endpoints can deploy models to run inference over large amounts of data, including OpenAI models. In this example, you learn how to create a batch endpoint to deploy ADA-002 model from OpenAI to compute embeddings at scale but you can use the same approach for completions and chat completions models. It uses Microsoft Entra authentication to grant access to the Azure OpenAI resource.
+Batch Endpoints can deploy models to run inference over large amounts of data, including Azure OpenAI models. In this example, you learn how to create a batch endpoint to deploy `text-embedding-ada-002` model from Azure OpenAI to compute embeddings at scale but you can use the same approach for completions and chat completions models. It uses Microsoft Entra authentication to grant access to the Azure OpenAI resource.
 
 ## About this example
 
-In this example, we're going to compute embeddings over a dataset using ADA-002 model from OpenAI. We will register the particular model in MLflow format using the OpenAI flavor which has support to orchestrate all the calls to the OpenAI service at scale.
+In this example, we're going to compute embeddings over a dataset using `text-embedding-ada-002` model via the Azure OpenAI Service. We will register the particular model in MLflow format using the Azure OpenAI flavor which has support to orchestrate all the calls to the Azure OpenAI Service at scale.
 
 [!INCLUDE [machine-learning-batch-clone](includes/azureml-batch-clone-samples.md)]
 
@@ -40,13 +40,13 @@ You can follow along this sample in the following notebooks. In the cloned repos
 [!INCLUDE [machine-learning-batch-prereqs](includes/azureml-batch-prereqs.md)]
 
 
-### Ensure you have an OpenAI deployment
+### Ensure you have an Azure OpenAI deployment
 
-The example shows how to run OpenAI models hosted in Azure OpenAI Service. To begin, you need an OpenAI resource correctly deployed in Azure and a deployment for the model you want to use. To deploy an OpenAI model in Azure OpenAI Service, see [Focus on Azure OpenAI Service](../ai-studio/azure-openai-in-ai-studio.md#focus-on-azure-openai-service).
+The example shows how to run OpenAI models hosted in Azure OpenAI Service. To begin, you need an Azure OpenAI resource correctly deployed in Azure and a deployment for the model you want to use. To deploy an Azure OpenAI model in Azure OpenAI Service, see [Focus on Azure OpenAI Service](../ai-studio/azure-openai-in-ai-studio.md#focus-on-azure-openai-service).
 
-:::image type="content" source="./media/how-to-use-batch-model-openai-embeddings/aoai-deployments.png" alt-text="A screenshot of the Azure OpenAI studio within Azure AI Foundry, showing the model deployments available in a particular Azure OpenAI Service resource." lightbox="media/how-to-use-batch-model-openai-embeddings/aoai-deployments.png":::
+:::image type="content" source="./media/how-to-use-batch-model-openai-embeddings/aoai-deployments.png" alt-text="A screenshot of the Azure OpenAI Service page within Azure AI Foundry, showing the model deployments available in a particular Azure OpenAI Service resource." lightbox="media/how-to-use-batch-model-openai-embeddings/aoai-deployments.png":::
 
-The previous image shows the Azure OpenAI Service resource to which the model is deployed. Note the name of this resource, as you later use it to construct the URL of the resource. Save the URL for later use in the tutorial.
+The previous image is an example that shows a deployed Azure OpenAI model and the Azure OpenAI Service resource to which it is deployed. Note the name of the resource used for your model deployment, as you use it later to construct the URL of the resource. 
 
 # [Azure CLI](#tab/cli)
 
@@ -125,14 +125,14 @@ You can get an access key and configure the batch deployment to use the access k
 ---
 
 
-### Register the OpenAI model
+### Register the Azure OpenAI model
 
-Model deployments in batch endpoints can only deploy registered models. You can use MLflow models with the flavor OpenAI to create a model in your workspace referencing a deployment in Azure OpenAI.
+Model deployments in batch endpoints can only deploy registered models. You can use MLflow models with the Azure OpenAI flavor to create a model in your workspace referencing a deployment in Azure OpenAI.
 
-1. Create an MLflow model in the workspace's models registry pointing to your OpenAI deployment with the model you want to use. Use MLflow SDK to create the model:
+1. Create an MLflow model in the workspace's models registry pointing to your Azure OpenAI deployment with the model you want to use. Use the MLflow SDK to create the model:
 
     > [!TIP]
-    > In the cloned repository in the folder **model** you already have an MLflow model to generate embeddings based on ADA-002 model in case you want to skip this step.
+    > In the cloned repository in the **model** folder, you already have an MLflow model to generate embeddings based on `text-embedding-ada-002` model in case you want to skip this step.
 
     ```python
     import mlflow
@@ -159,7 +159,7 @@ Model deployments in batch endpoints can only deploy registered models. You can
     [!notebook-python[] (~/azureml-examples-main/sdk/python/endpoints/batch/deploy-models/openai-embeddings/deploy-and-test.ipynb?name=register_model)]
 
 
-## Create a deployment for an OpenAI model
+## Create a deployment for an Azure OpenAI model
 
 1. First, let's create the endpoint that hosts the model. Decide on the name of the endpoint:
 
@@ -220,7 +220,7 @@ Model deployments in batch endpoints can only deploy registered models. You can
 
     > [!div class="checklist"]
     > * Allow the endpoint to read multiple data types, including `csv`, `tsv`, `parquet`, `json`, `jsonl`, `arrow`, and `txt`.
-    > * Add some validations to ensure the MLflow model used has an OpenAI flavor on it.
+    > * Add some validations to ensure the MLflow model used has an Azure OpenAI flavor on it.
     > * Format the output in `jsonl` format.
     > * Add an environment variable `AZUREML_BI_TEXT_COLUMN` to control (optionally) which input field you want to generate embeddings for.
 
@@ -233,22 +233,22 @@ Model deployments in batch endpoints can only deploy registered models. You can
 
     :::code language="python" source="~/azureml-examples-main/cli/endpoints/batch/deploy-models/openai-embeddings/code/batch_driver.py" :::
 
-1. One the scoring script is created, it's time to create a batch deployment for it. We use environment variables to configure the OpenAI deployment. Particularly we use the following keys:
+1. One the scoring script is created, it's time to create a batch deployment for it. We use environment variables to configure the Azure OpenAI deployment. Particularly we use the following keys:
 
     * `OPENAI_API_BASE` is the URL of the Azure OpenAI resource to use.
     * `OPENAI_API_VERSION` is the version of the API you plan to use.
     * `OPENAI_API_TYPE` is the type of API and authentication you want to use.
 
     # [Microsoft Entra authentication](#tab/ad)
 
-    The environment variable `OPENAI_API_TYPE="azure_ad"` instructs OpenAI to use Active Directory authentication and hence no key is required to invoke the OpenAI deployment. The identity of the cluster is used instead.
+    The environment variable `OPENAI_API_TYPE="azure_ad"` instructs the Azure OpenAI Service to use Microsoft Entra authentication and hence no key is required to invoke the Azure OpenAI deployment. The identity of the cluster is used instead.
     
     # [Access keys](#tab/keys)
 
     To use access keys instead of Microsoft Entra authentication, we need the following environment variables:
 
     * Use `OPENAI_API_TYPE="azure"`
-    * Use `OPENAI_API_KEY="<YOUR_AZURE_OPENAI_KEY>"`
+    * Use `AZURE_OPENAI_API_KEY="<YOUR_AZURE_OPENAI_KEY>"`
 
 1. Once we decided on the authentication and the environment variables, we can use them in the deployment. The following example shows how to use Microsoft Entra authentication particularly:
 
@@ -259,14 +259,14 @@ Model deployments in batch endpoints can only deploy registered models. You can
     :::code language="yaml" source="~/azureml-examples-main/cli/endpoints/batch/deploy-models/openai-embeddings/deployment.yml" highlight="26-28":::
 
     > [!TIP]
-    > Notice the `environment_variables` section where we indicate the configuration for the OpenAI deployment. The value for `OPENAI_API_BASE` will be set later in the creation command so you don't have to edit the YAML configuration file.
+    > Notice the `environment_variables` section where we indicate the configuration for the Azure OpenAI deployment. The value for `OPENAI_API_BASE` will be set later in the creation command so you don't have to edit the YAML configuration file.
 
     # [Python](#tab/python)
 
     [!notebook-python[] (~/azureml-examples-main/sdk/python/endpoints/batch/deploy-models/openai-embeddings/deploy-and-test.ipynb?name=configure_deployment)]
     
     > [!TIP]
-    > Notice the `environment_variables` section where we indicate the configuration for the OpenAI deployment.
+    > Notice the `environment_variables` section where we indicate the configuration for the Azure OpenAI deployment.
 
 1. Now, let's create the deployment.
 
diff --git a/articles/machine-learning/toc.yml b/articles/machine-learning/toc.yml
@@ -1008,7 +1008,7 @@ items:
               href: how-to-image-processing-batch.md
             - name: Deploy language models with batch model deployments
               href: how-to-nlp-processing-batch.md
-            - name: Run OpenAI models in batch endpoints to compute embeddings
+            - name: Run Azure OpenAI models in batch endpoints to compute embeddings
               href: how-to-use-batch-model-openai-embeddings.md
         - name: Deploy pipeline components
           items:
diff --git a/articles/search/search-security-network-security-perimeter.md b/articles/search/search-security-network-security-perimeter.md
@@ -9,17 +9,16 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2024
 ms.topic: how-to
-ms.date: 10/23/2024
+ms.date: 12/05/2024
 ---
 
 # Add a search service to a network security perimeter
 
 > [!IMPORTANT]
-> Azure AI Search support for network security perimeter is in public preview under supplemental terms of use. It's available in [regions providing the feature](/azure/private-link/network-security-perimeter-concepts).
+> Azure AI Search support for network security perimeter is in public preview under [supplemental terms of use](https://azure.microsoft.com/support/legal/preview-supplemental-terms/). It's available in [regions providing the feature](/azure/private-link/network-security-perimeter-concepts).
 > This preview version is provided without a service level agreement, and it's not recommended for production workloads. Certain features might not be supported or might have constrained capabilities.
-> For more information, see [Supplemental Terms of Use for Microsoft Azure Previews](https://azure.microsoft.com/support/legal/preview-supplemental-terms/).
 >
-> Be sure to review the [limitations and considerations](#limitations-and-considerations) section before you start.
+>  Review the [limitations and considerations](#limitations-and-considerations) section before you start.
 
 This article explains how to join an Azure AI Search service to a [network security perimeter](/azure/private-link/network-security-perimeter-concepts) to control network access to your search service. By joining a network security perimeter, you can:
 
@@ -35,6 +34,8 @@ You can add a search service to a network security perimeter in the Azure portal
 
 * Supported indexer data sources are currently limited to [Azure Blob Storage](search-howto-indexing-azure-blob-storage.md), [Azure Cosmos DB for NoSQL](./search-howto-index-cosmosdb.md), and [Azure SQL Database](search-how-to-index-sql-database.md).
 
+* Currently, within the perimeter, indexer connections to Azure PaaS for data retrieval is the primary use case. For outbound skills-driven API calls to Azure AI services, Azure OpenAI, or the Azure AI Foundry model catalog, or for inbound calls from the Azure AI Foundry for "chat with your data" scenarios you must [configure inbound and outbound rules](#add-an-inbound-access-rule) to allow the requests through the perimeter. If you require private connections for [structure-aware chunking](search-how-to-semantic-chunking.md) and vectorization, you should [create a shared private link](search-indexer-howto-access-private.md) and a private network.
+
 ## Prerequisites
 
 * An existing network security perimeter. You can [create one to associate with your search service](/azure/private-link/create-network-security-perimeter-portal).
@@ -47,7 +48,7 @@ Azure Network Security Perimeter allows administrators to define a logical netwo
 
 You can add Azure AI Search to a network security perimeter so that all indexing and query requests occur within the security boundary.
 
-1. In the Azure portal, create or find the network security perimeter service for your subscription.
+1. In the Azure portal, find the network security perimeter service for your subscription.
 
 1. Select **Resources** from the left-hand menu.
 
diff --git a/articles/search/vector-search-ranking.md b/articles/search/vector-search-ranking.md
@@ -9,12 +9,12 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: concept-article
-ms.date: 09/19/2024
+ms.date: 12/05/2024
 ---
 
 # Relevance in vector search
 
-During vector query execution, the search engine looks for similar vectors to find the best candidates to return in search results. Depending on how you indexed the vector content, the search for relevant matches is either exhaustive, or constrained to near neighbors for faster processing. Once candidates are found, similarity metrics are used to score each result based on the strength of the match. 
+During vector query execution, the search engine looks for similar vectors to find the best candidates to return in search results. Depending on how you indexed the vector content, the search for relevant matches is either exhaustive, or constrained to nearest neighbors for faster processing. Once candidates are found, similarity metrics are used to score each result based on the strength of the match. 
 
 This article explains the algorithms used to find relevant matches and the similarity metrics used for scoring. It also offers tips for improving relevance if search results don't meet expectations.
 
@@ -90,6 +90,9 @@ The algorithm finds candidate vectors to evaluate similarity. To perform this ta
 | `dotProduct` | This metric measures both the length of each pair of two vectors, and the angle between them. Mathematically, it calculates the products of vectors' magnitudes and the angle between them. For normalized vectors, this is identical to `cosine` similarity, but slightly more performant. |
 | `euclidean` | (also known as `l2 norm`) This metric measures the length of the vector difference between two vectors. Mathematically, it calculates the Euclidean distance between two vectors, which is the l2-norm of the difference of the two vectors. |
 
+> [!NOTE]
+> If you run two or more vector queries in parallel, or if you do a hybrid search that combines vector and text queries in the same request, [Reciprocal Rank Fusion (RRF)](hybrid-search-ranking.md) is used for scoring the final search results.
+
 ## Scores in a vector search results
 
 Scores are calculated and assigned to each match, with the highest matches returned as `k` results. The **`@search.score`** property contains the score. The following table shows the range within which a score will fall.
