Merge pull request #2083 from MicrosoftDocs/main

12/19/2024 AM Publish

Author: Taojunshen

articles/ai-services/agents/how-to/tools/function-calling.md

@@ -133,6 +133,8 @@ ToolOutput GetResolvedToolOutput(RequiredToolCall toolCall)
 
 In the sample below we create a client and define a `toolset` which will be used to process the functions defined in `user_functions`.
 
+`toolset`: When using the toolset parameter, you provide not only the function definitions and descriptions but also their implementations. The SDK will execute these functions within create_and_run_process or streaming. These functions will be invoked based on their definitions.
+
 ```python
 import os
 from azure.ai.projects import AIProjectClient

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

@@ -70,7 +70,10 @@ with AIProjectClient.from_connection_string(
 ) as project_client:
 
     # Explicit type hinting for IntelliSense
-    client: AzureOpenAI = project_client.inference.get_azure_openai_client()
+    client: AzureOpenAI = project_client.inference.get_azure_openai_client(
+        # The latest API version is 2024-10-01-preview
+        api_version = os.environ.get("AZURE_OPENAI_API_VERSION"),
+    )
 
     with client:
         agent = client.beta.assistants.create(

articles/ai-services/computer-vision/category-taxonomy.md

@@ -4,6 +4,7 @@ titleSuffix: Azure AI services
 description: Get the 86 categories of taxonomy for the Azure AI Vision API in Azure AI services.
 #services: cognitive-services
 author: PatrickFarley
+ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.author: pafarley
 manager: nitinme
 ms.service: azure-ai-vision

articles/ai-services/computer-vision/computer-vision-how-to-install-containers.md

@@ -8,6 +8,7 @@ manager: nitinme
 ms.service: azure-ai-vision
 ms.topic: how-to
 ms.date: 06/26/2024
+ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.author: pafarley
 keywords: on-premises, OCR, Docker, container
 ---
@@ -101,7 +102,7 @@ Once the container is on the [host computer](#host-computer-requirements), use t
 
 Use the [docker run](https://docs.docker.com/engine/reference/commandline/run/) command to run the container. Refer to [gather required parameters](#gather-required-parameters) for details on how to get the `{ENDPOINT_URI}` and `{API_KEY}` values.
 
-[Examples](computer-vision-resource-container-config.md#example-docker-run-commands) of the `docker run` command are available.
+[Examples](computer-vision-resource-container-config.md#example-docker-commands) of the `docker run` command are available.
 
 ```bash
 docker run --rm -it -p 5000:5000 --memory 16g --cpus 8 \
@@ -129,7 +130,7 @@ mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2022-04-30
 ```
 
 
-More [examples](./computer-vision-resource-container-config.md#example-docker-run-commands) of the `docker run` command are available. 
+More [examples](./computer-vision-resource-container-config.md#example-docker-commands) of the `docker run` command are available. 
 
 > [!IMPORTANT]
 > The `Eula`, `Billing`, and `ApiKey` options must be specified to run the container; otherwise, the container won't start.  For more information, see [Billing](#billing).

articles/ai-services/computer-vision/computer-vision-resource-container-config.md

@@ -1,19 +1,20 @@
 ---
-title: Configure Read OCR containers - Azure AI Vision
+title: Configure Read containers - Azure AI Vision
 titleSuffix: Azure AI services
-description: This article shows you how to configure both required and optional settings for Read OCR containers in Azure AI Vision.
+description: This article shows you how to configure both required and optional settings for Read optical character recognition (OCR) containers in Azure AI Vision.
 #services: cognitive-services
 author: aahill
 manager: nitinme
 ms.service: azure-ai-vision
 ms.topic: how-to
 ms.date: 01/19/2024
+ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.author: aahi
 ---
 
 # Configure Read OCR Docker containers
 
-You can configure the Azure AI Vision Read OCR container's runtime environment by using the `docker run` command arguments. This container has several required settings, along with a few optional settings. Several [examples](#example-docker-run-commands) of the command are available. The container-specific settings are the billing settings. 
+You can configure the Azure AI Vision Read OCR container's runtime environment by using the `docker run` command arguments. This container has some required settings, along with a few optional settings. Several [examples](#example-docker-commands) of the command are available. The container-specific settings are the billing settings. 
 
 ## Configuration settings
 
@@ -26,18 +27,18 @@ The container also has the following container-specific configuration settings:
 
 |Required|Setting|Purpose|
 |--|--|--|
-|No|ReadEngineConfig:ResultExpirationPeriod| v2.0 containers only. Result expiration period in hours. The default is 48 hours. The setting specifies when the system should clear recognition results. For example, if `resultExpirationPeriod=1`, the system clears the recognition result 1 hour after the process. If `resultExpirationPeriod=0`, the system clears the recognition result after the result is retrieved.|
-|No|Cache:Redis| v2.0 containers only. Enables Redis storage for storing results. A cache is *required* if multiple read OCR containers are placed behind a load balancer.|
-|No|Queue:RabbitMQ|v2.0 containers only. Enables RabbitMQ for dispatching tasks. The setting is useful when multiple read OCR containers are placed behind a load balancer.|
-|No|Queue:Azure:QueueVisibilityTimeoutInMilliseconds | v3.x containers only. The time for a message to be invisible when another worker is processing it. |
-|No|Storage::DocumentStore::MongoDB|v2.0 containers only. Enables MongoDB for permanent result storage. |
-|No|Storage:ObjectStore:AzureBlob:ConnectionString| v3.x containers only. Azure blob storage connection string. |
-|No|Storage:TimeToLiveInDays| v3.x containers only. Result expiration period in days. The setting specifies when the system should clear recognition results. The default is 2 days, which means any result live for longer than that period is not guaranteed to be successfully retrieved. The value is integer and it must be between 1 day to 7 days.|
-|No|StorageTimeToLiveInMinutes| v3.2-model-2021-09-30-preview and new containers. Result expiration period in minutes. The setting specifies when the system should clear recognition results. The default is 2 days (2880 minutes), which means any result live for longer than that period is not guaranteed to be successfully retrieved. The value is integer and it must be between 60 minutes to 7 days (10080 minutes).|
-|No|Task:MaxRunningTimeSpanInMinutes| v3.x containers only. Maximum running time for a single request. The default is 60 minutes. |
-|No|EnableSyncNTPServer| v3.x containers only, except for v3.2-model-2021-09-30-preview and newer containers. Enables the NTP server synchronization mechanism, which ensures synchronization between the system time and expected task runtime. Note that this requires external network traffic. The default is `true`. |
-|No|NTPServerAddress| v3.x containers only, except for v3.2-model-2021-09-30-preview and newer containers. NTP server for the time sync-up. The default is `time.windows.com`. |
-|No|Mounts:Shared| v3.x containers only. Local folder for storing recognition result. The default is `/share`. For running container without using Azure blob storage, we recommend mounting a volume to this folder to ensure you have enough space for the recognition results. |
+|No|`ReadEngineConfig:ResultExpirationPeriod`| v2.0 containers only. Result expiration period in hours. The default is 48 hours. The setting specifies when the system should clear recognition results. For example, if `resultExpirationPeriod=1`, the system clears the recognition result 1 hour after the process. If `resultExpirationPeriod=0`, the system clears the recognition result after the result is retrieved.|
+|No|`Cache:Redis`| v2.0 containers only. Enables Redis storage for storing results. A cache is *required* if multiple read OCR containers are placed behind a load balancer.|
+|No|`Queue:RabbitMQ`|v2.0 containers only. Enables RabbitMQ for dispatching tasks. The setting is useful when multiple read OCR containers are placed behind a load balancer.|
+|No|`Queue:Azure:QueueVisibilityTimeoutInMilliseconds` | v3.x containers only. The time for a message to be invisible when another worker is processing it. |
+|No|`Storage::DocumentStore::MongoDB`|v2.0 containers only. Enables MongoDB for permanent result storage. |
+|No|`Storage:ObjectStore:AzureBlob:ConnectionString`| v3.x containers only. Azure blob storage connection string. |
+|No|`Storage:TimeToLiveInDays`| v3.x containers only. Result expiration period in days. The setting specifies when the system should clear recognition results. The default is two days, which means any result that's live for longer than that period isn't guaranteed to be successfully retrieved. The value is integer and it must be between one day to seven days.|
+|No|`StorageTimeToLiveInMinutes`| v3.2-model-2021-09-30-preview and new containers. Result expiration period in minutes. The setting specifies when the system should clear recognition results. The default is two days (2,880 minutes), which means any result that's live for longer than that period isn't guaranteed to be successfully retrieved. The value is integer and it must be between 60 minutes to seven days (10080 minutes).|
+|No|`Task:MaxRunningTimeSpanInMinutes`| v3.x containers only. Maximum running time for a single request. The default is 60 minutes. |
+|No|`EnableSyncNTPServer`| v3.x containers only, except for v3.2-model-2021-09-30-preview and newer containers. Enables the NTP server synchronization mechanism, which ensures synchronization between the system time and expected task runtime. Note that this requires external network traffic. The default is `true`. |
+|No|`NTPServerAddress`| v3.x containers only, except for v3.2-model-2021-09-30-preview and newer containers. NTP server for the time sync-up. The default is `time.windows.com`. |
+|No|`Mounts:Shared`| v3.x containers only. Local folder for storing recognition result. The default is `/share`. For running container without using Azure blob storage, we recommend mounting a volume to this folder to ensure you have enough space for the recognition results. |
 
 ## ApiKey configuration setting
 
@@ -65,7 +66,7 @@ Remember to add the `vision/<version>` routing to the endpoint URI as shown in t
 |--|------|-----------|-------------|
 |Yes| `Billing` | String | Billing endpoint URI<br><br>Example:<br>`Billing=https://westcentralus.api.cognitive.microsoft.com/vision/v3.2` |
 
-## Eula setting
+## EULA setting
 
 [!INCLUDE [Container shared configuration eula settings](../includes/cognitive-services-containers-configuration-shared-settings-eula.md)]
 
@@ -87,19 +88,19 @@ Use bind mounts to read and write data to and from the container. You can specif
 
 The Azure AI Vision containers don't use input or output mounts to store training or service data. 
 
-The exact syntax of the host mount location varies depending on the host operating system. Additionally, the [host computer](computer-vision-how-to-install-containers.md#host-computer-requirements)'s mount location may not be accessible due to a conflict between permissions used by the Docker service account and the host mount location permissions. 
+The exact syntax of the host mount location varies depending on the host operating system. Additionally, the [host computer](computer-vision-how-to-install-containers.md#host-computer-requirements)'s mount location might not be accessible due to a conflict between permissions used by the Docker service account and the host mount location permissions. 
 
 |Optional| Name | Data type | Description |
 |-------|------|-----------|-------------|
-|Not allowed| `Input` | String | Azure AI Vision containers do not use this.|
+|Not allowed| `Input` | String | Azure AI Vision containers don't use this field.|
 |Optional| `Output` | String | The target of the output mount. The default value is `/output`. This is the location of the logs. This includes container logs. <br><br>Example:<br>`--mount type=bind,src=c:\output,target=/output`|
 
-## Example docker run commands
+## Example docker commands
 
 The following examples use the configuration settings to illustrate how to write and use `docker run` commands.  Once running, the container continues to run until you [stop](computer-vision-how-to-install-containers.md#stop-the-container) it.
 
 * **Line-continuation character**: The Docker commands in the following sections use the back slash, `\`, as a line continuation character. Replace or remove this based on your host operating system's requirements. 
-* **Argument order**: Do not change the order of the arguments unless you are very familiar with Docker containers.
+* **Argument order**: Do not change the order of the arguments unless you're familiar with Docker containers.
 
 Replace {_argument_name_} with your own values:
 

articles/ai-services/computer-vision/concept-background-removal.md

@@ -9,6 +9,7 @@ manager: nitinme
 ms.service: azure-ai-vision
 ms.topic: conceptual
 ms.date: 01/19/2024
+ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.author: pafarley
 ---
 

articles/ai-services/computer-vision/concept-categorizing-images.md

@@ -9,6 +9,7 @@ manager: nitinme
 ms.service: azure-ai-vision
 ms.topic: conceptual
 ms.date: 01/19/2024
+ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.author: pafarley
 ---
 

articles/ai-services/computer-vision/concept-describe-images-40.md

@@ -9,6 +9,7 @@ manager: nitinme
 ms.service: azure-ai-vision
 ms.topic: conceptual
 ms.date: 09/25/2024
+ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.author: pafarley
 ---
 

articles/ai-services/computer-vision/concept-describing-images.md

@@ -9,6 +9,7 @@ manager: nitinme
 ms.service: azure-ai-vision
 ms.topic: conceptual
 ms.date: 09/25/2024
+ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.author: pafarley
 ---
 

articles/ai-services/computer-vision/concept-detecting-adult-content.md

@@ -9,6 +9,7 @@ manager: nitinme
 ms.service: azure-ai-vision
 ms.topic: conceptual
 ms.date: 01/19/2024
+ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.author: pafarley
 ---