Merge pull request #2044 from MicrosoftDocs/main

12/17/2024 PM Publish

Author: Taojunshen

articles/ai-services/agents/how-to/use-your-own-resources.md

@@ -7,8 +7,8 @@ manager: nitinme
 ms.service: azure
 ms.topic: how-to
 ms.date: 12/11/2024
-author: aahill
-ms.author: aahi
+author: fosteramanda
+ms.author: fosteramanda
 ms.custom: azure-ai-agents
 ---
 
@@ -27,9 +27,9 @@ To use your own resources, you can edit the parameters in the provided deploymen
 
 **Standard Setup**: Agents use customer-owned, single-tenant search and storage resources. With this setup, you have full control and visibility over these resources, but you incur costs based on your usage. You can use your own AI services account, storage account, and/or Azure AI Search resource with this option. 
 
-## Basic agent setup: use an existing AI Services resource 
+## Basic agent setup: use an existing AI Services/Azure OpenAI resource 
 
-Replace the parameter value for `aiServiceAccountResourceId` with the full arm resource ID of the AI Services account you want to use.
+Replace the parameter value for `aiServiceAccountResourceId` with the full arm resource ID of the AI Services/Azure OpenAI resource you want to use.
 
 1. To get the AI Services account resource ID, sign in to the Azure CLI and select the subscription with your AI Services account:
 
@@ -44,18 +44,25 @@ Replace the parameter value for `aiServiceAccountResourceId` with the full arm r
 
     ```
     aiServiceAccountResourceId:/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{serviceName}
+
+    [Azure OpenAI Only] aiServiceKind: AzureOpenAI
     ```
 
-## Standard agent setup: use an existing AI Services, storage, and/or Azure AI Search resource 
+    If you want to use an existing Azure OpenAI resource, you will need to update the `aiServiceAccountResourceId` and the `aiServiceKind` parameters in the parameter file. The aiServiceKind parameter should be set to AzureOpenAI.
+
+
+## Standard agent setup: use an existing AI Services/Azure OpenAI, storage, and/or Azure AI Search resource 
 
 Use an existing AI Search, storage account, and/or Azure AI Search resource by providing the full arm resource ID in the standard agent template file.
 
-Use an existing AI Services resource:
+Use an existing AI Services/Azure OpenAI resource:
 1. Follow the steps in basic agent setup to get the AI Services account resource ID.
 2. In the standard agent template file, replace the following placeholders:
     
     ```
     aiServiceAccountResourceId:/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{serviceName}
+    
+    [Azure OpenAI Only] aiServiceKind: AzureOpenAI
     ```
 
 ### Use an existing storage account

articles/ai-services/agents/includes/bicep-setup.md

@@ -1,7 +1,7 @@
 ---
 manager: nitinme
-author: aahill
-ms.author: aahi
+author: fosteramanda
+ms.author: fosteramanda
 ms.service: azure
 ms.topic: include
 ms.date: 11/13/2024
@@ -47,10 +47,28 @@ By default, the deployment template is configured with the following values:
 >
 > The templates only support deployment of OpenAI models. See which OpenAI models are supported in the [Azure AI Agent Service model support](../concepts/model-region-support.md) documentation.
 
+
+### [Optional] Use your own resources during agent setup
+
+> [!NOTE]
+> If you use an existing AI Services or Azure OpenAI resource, no model will be deployed. You can deploy a model to the resource after the agent setup is complete. 
+
+Use an existing AI Services, Azure OpenAI, AI Search, and/or Azure Blob Storage resource by providing the full arm resource ID in the parameters file:
+
+- `aiServiceAccountResourceId`
+- `aiSearchServiceResourceId`
+- `aiStorageAccountResourceId`
+
+
+If you want to use an existing Azure OpenAI resource, you need to update the `aiServiceAccountResourceId` and the `aiServiceKind` parameters in the parameter file. The `aiServiceKind` parameter should be set to `AzureOpenAI`. 
+
+For more information, see [how to use your own resources](../how-to/use-your-own-resources.md).
+
+
 ## Basic agent setup resource architecture
 :::image type="content" source="../media/quickstart/basic-agent-setup-resources.png" alt-text="An architecture diagram for basic agent setup." lightbox="../media/quickstart/basic-agent-setup-resources.png":::
 
-Resources for the AI hub, AI project, and AI Services are created for you. A storage account is created because it's a required resource for hubs, but this storage account is not used by agents. The AI Services account is connected to your project/hub and a gpt-4o-mini model is deployed in the eastus region. A Microsoft-managed key vault, storage account, and search resource is used by default.
+Resources for the AI hub, AI project, and AI Services are created for you. A storage account is created because it's a required resource for hubs, but this storage account isn't used by agents. The AI Services account is connected to your project/hub and a gpt-4o-mini model is deployed in the eastus region. A Microsoft-managed key vault, storage account, and search resource is used by default.
 
 ## Standard agent setup resource architecture
 :::image type="content" source="../media/quickstart/standard-agent-setup-resources.png" alt-text="An architecture diagram for standard agent setup." lightbox="../media/quickstart/standard-agent-setup-resources.png":::

articles/ai-services/agents/includes/file-search/deep-dive.md

@@ -7,16 +7,6 @@ ms.topic: include
 ms.date: 12/10/2024
 ---
 ## Creating vector stores and adding files 
-
-You can create a vector store and add files to it in a single API call:
-
-```python
-vector_store = project_client.agents.create_vector_store_file_batch_and_poll(
-  name="my_vector_store",
-  file_ids=['file_path_1', 'file_path_2', 'file_path_3', 'file_path_4', 'file_path_5']
-)
-```
-
 Adding files to vector stores is an async operation. To ensure the operation is complete, we recommend that you use the 'create and poll' helpers in our official SDKs. If you're not using the SDKs, you can retrieve the `vector_store` object and monitor its `file_counts` property to see the result of the file ingestion operation.
 
 Files can also be added to a vector store after it's created by creating vector store files.
@@ -40,7 +30,7 @@ Alternatively, you can add several files to a vector store by creating batches o
 ```python
 batch = project_client.agents.create_vector_store_file_batch_and_poll(
   vector_store_id=vector_store.id,
-  file_ids=['file_1', 'file_2', 'file_3', 'file_4', 'file_5']
+  file_ids=[file_1.id, file_2.id, file_3.id, file_4.id, file_5.id]
 )
 ```
 
@@ -83,7 +73,7 @@ To help you manage the costs associated with these vector_store objects, we adde
 ```python
 vector_store = project_client.agents.create_vector_store_and_poll(
   name="Product Documentation",
-  file_ids=['file_1', 'file_2', 'file_3', 'file_4', 'file_5'],
+  file_ids=[file_1.id],
   expires_after={
       "anchor": "last_active_at",
       "days": 7

articles/ai-services/agents/includes/quickstart-python-openai.md

@@ -13,8 +13,9 @@ ms.date: 11/13/2024
 ## Prerequisites
 
 * An Azure subscription - [Create one for free](https://azure.microsoft.com/free/cognitive-services).
-* [Python 3.13 or later](https://www.python.org/)
+* [Python 3.8 or later](https://www.python.org/)
 * Make sure you have the **Azure AI Developer** [RBAC role](../../../ai-studio/concepts/rbac-ai-studio.md) assigned at the appropriate level.
+* You may also require the **Cognitive Services OpenAI User** assigned to use the Azure AI Services resource.
 * Install [the Azure CLI and the machine learning extension](/azure/machine-learning/how-to-configure-cli). If you have the CLI already installed, make sure it's updated to the latest version.
 
 [!INCLUDE [bicep-setup](bicep-setup.md)]
@@ -96,4 +97,4 @@ with AIProjectClient.from_connection_string(
 
         messages = client.beta.threads.messages.list(thread_id=thread.id)
         print(f"Messages: {messages}")
-```
+```

articles/ai-services/agents/includes/quickstart-python.md

@@ -13,7 +13,7 @@ ms.date: 11/13/2024
 ## Prerequisites
 
 * An Azure subscription - [Create one for free](https://azure.microsoft.com/free/cognitive-services).
-* [Python 3.13 or later](https://www.python.org/)
+* [Python 3.8 or later](https://www.python.org/)
 * Make sure you have the **Azure AI Developer** [RBAC role](../../../ai-studio/concepts/rbac-ai-studio.md) assigned at the appropriate level.
 * Install [the Azure CLI and the machine learning extension](/azure/machine-learning/how-to-configure-cli). If you have the CLI already installed, make sure it's updated to the latest version.
 
@@ -137,4 +137,4 @@ with project_client:
     # Delete the agent once done
     project_client.agents.delete_agent(agent.id)
     print("Deleted agent")
-```
+```