Merge pull request #2716 from MicrosoftDocs/main

02/03/2025 PM Publishing

Author: v-alje

articles/ai-foundry/model-inference/includes/code-create-chat-client-entra.md

@@ -25,9 +25,10 @@ import os
 from azure.ai.inference import ChatCompletionsClient
 from azure.identity import DefaultAzureCredential
 
-model = ChatCompletionsClient(
+client = ChatCompletionsClient(
     endpoint="https://<resource>.services.ai.azure.com/models",
     credential=DefaultAzureCredential(),
+    credential_scopes=["https://cognitiveservices.azure.com/.default"],
     model="mistral-large-2407",
 )
 ```
@@ -47,10 +48,13 @@ import ModelClient from "@azure-rest/ai-inference";
 import { isUnexpected } from "@azure-rest/ai-inference";
 import { DefaultAzureCredential } from "@azure/identity";
 
+const clientOptions = { credentials: { "https://cognitiveservices.azure.com" } };
+
 const client = new ModelClient(
     "https://<resource>.services.ai.azure.com/models", 
     new DefaultAzureCredential(),
-    "mistral-large-2407"
+    "mistral-large-2407",
+    clientOptions,
 );
 ```
 
@@ -79,10 +83,16 @@ using Azure.AI.Inference;
 Then, you can use the package to consume the model. The following example shows how to create a client to consume chat completions with Entra ID:
 
 ```csharp
+var credential = new DefaultAzureCredential();
+AzureAIInferenceClientOptions clientOptions = new AzureAIInferenceClientOptions();
+BearerTokenAuthenticationPolicy tokenPolicy = new BearerTokenAuthenticationPolicy(credential, new string[] { "https://cognitiveservices.azure.com/.default" });
+clientOptions.AddPolicy(tokenPolicy, HttpPipelinePosition.PerRetry);
+
 ChatCompletionsClient client = new ChatCompletionsClient(
     new Uri("https://<resource>.services.ai.azure.com/models"),
-    new DefaultAzureCredential(includeInteractiveCredentials: true),
-    "mistral-large-2407"
+    credential,
+    "mistral-large-2407",
+    clientOptions.
 );
 ```
 
@@ -106,8 +116,9 @@ Add the package to your project:
 Then, you can use the package to consume the model. The following example shows how to create a client to consume chat completions:
 
 ```java
+TokenCredential defaultCredential = new DefaultAzureCredentialBuilder().build();
 ChatCompletionsClient client = new ChatCompletionsClientBuilder()
-    .credential(new DefaultAzureCredential()))
+    .credential(defaultCredential)
     .endpoint("https://<resource>.services.ai.azure.com/models")
     .model("mistral-large-2407")
     .buildClient();
@@ -127,6 +138,8 @@ Authorization: Bearer <bearer-token>
 Content-Type: application/json
 ```
 
+Tokens have to be issued with scope `https://cognitiveservices.azure.com/.default`.
+
 For testing purposes, the easiest way to get a valid token for your user account is to use the Azure CLI. In a console, run the following Azure CLI command:
 
 ```azurecli

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

@@ -100,8 +100,10 @@ Once you configured Microsoft Entra ID in your resource, you need to update your
 
 [!INCLUDE [about-credentials](about-credentials.md)]
 
+## Disable key-based authentication in the resource
 
+Disabling key-based authentication is advisable when you implemented Microsoft Entra ID and fully addressed compatibility or fallback concerns in all the applications that consume the service. You can achieve it by changing the property `disableLocalAuth`:
 
-## Disable key-based authentication in the resource
+__modules/ai-services-template.bicep__
 
-Disabling key-based authentication is advisable when you implemented Microsoft Entra ID and fully addressed compatibility or fallback concerns in all the applications that consume the service.
+:::code language="bicep" source="~/azureai-model-inference-bicep/infra/modules/ai-services-template.bicep" highlight="10-11,42":::

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

@@ -4,7 +4,7 @@ author: aahill
 ms.author: aahi
 ms.service: azure-ai-agent-service
 ms.topic: include
-ms.date: 01/28/2025
+ms.date: 02/03/2025
 ms.custom: devx-track-js
 ---
 
@@ -38,6 +38,12 @@ npm install @azure/ai-projects
 npm install @azure/identity
 ```
 
+Next, to authenticate your API requests and run the program, use the [az login](/cli/azure/authenticate-azure-cli-interactively) command to sign into your Azure subscription.
+
+```azurecli
+az login
+```
+
 Use the following code to create and run an agent. To run this code, you will need to create a connection string using information from your project. This string is in the format:
 
 `<HostName>;<AzureSubscriptionId>;<ResourceGroup>;<ProjectName>`
@@ -87,7 +93,7 @@ export async function main() {
   const codeInterpreterTool = ToolUtility.createCodeInterpreterTool();
 
   // Step 2 an agent
-  const agent = await client.agents.createAgent("gpt-35-turbo", {
+  const agent = await client.agents.createAgent("gpt-4o-mini", {
     name: "my-agent",
     instructions: "You are a helpful agent",
     tools: [codeInterpreterTool.definition],
@@ -143,7 +149,7 @@ export async function main() {
   // messages[0] is the most recent
   for (let i = messages.data.length - 1; i >= 0; i--) {
     const m = messages.data[i];
-    if (isOutputOfType<MessageTextContentOutput>(m.content[0], "text")) {
+    if (isOutputOfType(m.content[0], "text")) {
       const textContent = m.content[0];
       console.log(`${textContent.text.value}`);
       console.log(`---------------------------------`);

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

@@ -4,7 +4,7 @@ author: aahill
 ms.author: aahi
 ms.service: azure-ai-agent-service
 ms.topic: include
-ms.date: 01/28/2025
+ms.date: 02/03/2025
 ms.custom: devx-track-ts
 ---
 
@@ -39,6 +39,12 @@ npm install @azure/ai-projects
 npm install @azure/identity
 ```
 
+Next, to authenticate your API requests and run the program, use the [az login](/cli/azure/authenticate-azure-cli-interactively) command to sign into your Azure subscription.
+
+```azurecli
+az login
+```
+
 Use the following code to create and run an agent. To run this code, you will need to create a connection string using information from your project. This string is in the format:
 
 `<HostName>;<AzureSubscriptionId>;<ResourceGroup>;<ProjectName>`
@@ -93,7 +99,7 @@ export async function main(): Promise<void> {
   const codeInterpreterTool = ToolUtility.createCodeInterpreterTool();
 
   // Step 2: Create an agent
-  const agent = await client.agents.createAgent("gpt-35-turbo", {
+  const agent = await client.agents.createAgent("gpt-4o-mini", {
     name: "my-agent",
     instructions: "You are a helpful agent",
     tools: [codeInterpreterTool.definition],

articles/ai-services/computer-vision/spatial-analysis-container.md

@@ -159,9 +159,9 @@ Follow these steps to remotely connect from a Windows client.
 
 Follow these instructions if your host computer isn't an Azure Stack Edge device.
 
-#### Install NVIDIA CUDA Toolkit and Nvidia graphics drivers on the host computer
+#### Install NVIDIA CUDA Toolkit and NVIDIA graphics drivers on the host computer
 
-Use the following bash script to install the required Nvidia graphics drivers, and CUDA Toolkit.
+Use the following bash script to install the required NVIDIA graphics drivers, and CUDA Toolkit.
 
 ```bash
 wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-ubuntu1804.pin

articles/ai-services/content-safety/how-to/containers/install-run-container.md

@@ -86,7 +86,7 @@ Even with identical GPUs, performance can fluctuate based on the GPU load and th
 
 ## Install the NVIDIA container toolkit
 
-The `host` is the computer that runs the docker container. The host must support Nvidia container toolkit. Follow the below guidance to install the toolkit in your environment.
+The `host` is the computer that runs the docker container. The host must support NVIDIA container toolkit. Follow the below guidance to install the toolkit in your environment.
 
 [Install the NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
 

articles/ai-services/document-intelligence/train/custom-labels.md

@@ -41,7 +41,7 @@ A labeled dataset consists of several files:
 
 * We explore how to create a balanced data set and select the right documents to label. This process sets you on the path to higher quality models.
 
-> [!VIDEO https://www.microsoft.com/en-us/videoplayer/embed/RWWHru]
+> [!VIDEO 1190c010-ef3e-4cc6-8ffc-6d896fbb9711]
 
 ## Create a balanced dataset
 

articles/ai-services/language-service/concepts/model-lifecycle.md

@@ -41,8 +41,8 @@ Use the table below to find which model versions are supported by each feature:
 | Sentiment Analysis and opinion mining               | `latest*`                                      |                                             |
 | Language Detection                                  | `latest*`                                      |                                             |
 | Entity Linking                                      | `latest*`                                      |                                             |
-| Named Entity Recognition (NER)                      | `latest*`                                      | `2023-04-15-preview**`                      |
-| Personally Identifiable Information (PII) detection | `latest*`                                      | `2023-04-15-preview**`                      | 
+| Named Entity Recognition (NER)                      | `latest*`                                      | `2024-04-15-preview**`                      |
+| Personally Identifiable Information (PII) detection | `latest*`                                      | `2024-04-15-preview**`                      | 
 | PII detection for conversations                     | `latest*`                                      | `2024-11-01-preview**`                      |
 | Question answering                                  | `latest*`                                      |                                             |
 | Text Analytics for health                           | `latest*`                                      | `2022-08-15-preview`, `2023-01-01-preview**`|

articles/ai-services/language-service/summarization/how-to/use-containers.md

@@ -35,7 +35,7 @@ The following table describes the minimum and recommended specifications for the
 | Container Type             | Recommended number of CPU cores  | Recommended memory | Notes |
 |----------------------------|----------------------------------|--------------------|-------|
 | Summarization CPU container| 16                               | 48 GB              |       |
-| Summarization GPU container| 2                                | 24 GB              | Requires an Nvidia GPU that supports Cuda 11.8 with 16GB VRAM.|
+| Summarization GPU container| 2                                | 24 GB              | Requires an NVIDIA GPU that supports Cuda 11.8 with 16GB VRAM.|
 
 CPU core and memory correspond to the `--cpus` and `--memory` settings, which are used as part of the `docker run` command.
 

articles/ai-services/openai/how-to/code-interpreter.md

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 01/28/2025
+ms.date: 02/03/2025
 author: aahill
 ms.author: aahi
 recommendations: false
@@ -104,7 +104,12 @@ curl https://YOUR_RESOURCE_NAME.openai.azure.com/openai/assistants?api-version=2
     "tools": [
       { "type": "code_interpreter" }
     ],
-    "model": "gpt-4-1106-preview"
+    "model": "gpt-4-1106-preview",
+    "tool_resources": {
+      "code_interpreter": {
+        "file_ids": ["assistant-123abc456"]
+      }
+    }
   }'
 ```