Merge pull request #2199 from MicrosoftDocs/main

1/8/2025 11:00 AM IST Publish

Author: PhilKang0704

articles/ai-services/agents/overview.md

@@ -65,7 +65,7 @@ What originally took hundreds of lines of code can now be done in just a few wit
 
 ### Comparing Azure agents and Azure OpenAI assistants
 
-Both services enable you to build agents using the same API and SDKs, but if you have additional enterprise requirements, you may want to consider using Azure AI Agent Service. Azure AI Agent Service provides all the capabilities of assistants in addition to:
+Both services enable you to build agents using the same API and SDKs, but if you have additional enterprise requirements, you might want to consider using Azure AI Agent Service. Azure AI Agent Service provides all the capabilities of assistants in addition to:
 
 **Flexible model selection** - Create agents that use Azure OpenAI models, or others such as Llama 3, Mistral and Cohere. Choose the most suitable model to meet your business needs.
 

articles/ai-services/agents/quotas-limits.md

@@ -21,7 +21,7 @@ The following sections provide you with a guide to the default quotas and limits
 
 | Limit Name | Limit Value |
 |--|--|
-| Max files per agent/thread | 10,000 when using the API or Azure AI Foundry portal. 20 when using Azure OpenAI Studio.|
+| Max files per agent/thread | 10,000 when using the API or Azure AI Foundry portal. In Azure OpenAI Studio the limit was 20.|
 | Max file size for agents & fine-tuning | 512 MB |
 | Max size for all uploaded files for agents |100 GB |  
 | agents token limit | 2,000,000 token limit |

articles/ai-services/anomaly-detector/concepts/best-practices-multivariate.md

@@ -185,7 +185,7 @@ to determine whether data at `2021-01-02T00:01:00Z` is anomalous. It moves on in
 
 Normally we recommend you to use  `severity` as the filter to sift out 'anomalies' that aren't so important to your business. Depending on your scenario and data pattern, those anomalies that are less important often have relatively lower `severity` values or standalone (discontinuous) high `severity` values like random spikes.
 
-In cases where you've found a need of more sophisticated rules than thresholds against `severity` or duration of continuous high `severity` values, you may want to use `score` to build more powerful filters. Understanding how MVAD is using `score` to determine anomalies may help:
+In cases where you've found a need of more sophisticated rules than thresholds against `severity` or duration of continuous high `severity` values, you might want to use `score` to build more powerful filters. Understanding how MVAD is using `score` to determine anomalies may help:
 
 We consider whether a data point is anomalous from both global and local perspective. If `score` at a timestamp is higher than a certain threshold, then the timestamp is marked as an anomaly. If `score` is lower than the threshold but is relatively higher in a segment, it's also marked as an anomaly.
 

articles/ai-services/computer-vision/how-to/background-removal.md

@@ -77,7 +77,7 @@ Authentication is done by adding the HTTP request header **Ocp-Apim-Subscription
 
 ## Select the image to analyze
 
-The code in this guide uses remote images referenced by URL. You may want to try different images on your own to see the full capability of the Image Analysis features.
+The code in this guide uses remote images referenced by URL. You might want to try different images on your own to see the full capability of the Image Analysis features.
 
 <!--
 #### [C#](#tab/csharp)

articles/ai-services/computer-vision/how-to/specify-recognition-model.md

@@ -126,7 +126,7 @@ If you'd like to compare the performances of different recognition models on you
 1. Train your **PersonGroup**s using the [Train Person Group] API.
 1. Test with [Identify From Person Group] on all four **PersonGroup**s and compare the results.
 
-If you normally specify a confidence threshold (a value between zero and one that determines how confident the model must be to identify a face), you may need to use different thresholds for different models. A threshold for one model isn't meant to be shared to another and won't necessarily produce the same results.
+If you normally specify a confidence threshold (a value between zero and one that determines how confident the model must be to identify a face), you might need to use different thresholds for different models. A threshold for one model isn't meant to be shared to another and won't necessarily produce the same results.
 
 ## Next steps
 

articles/ai-services/computer-vision/includes/environment-variables.md

@@ -30,7 +30,7 @@ setx VISION_KEY <your_key>
 setx VISION_ENDPOINT <your_endpoint>
 ```
 
-After you add the environment variables, you may need to restart any running programs that will read the environment variables, including the console window.
+After you add the environment variables, you might need to restart any running programs that will read the environment variables, including the console window.
 
 #### [Linux](#tab/linux)
 

articles/ai-services/computer-vision/includes/face-environment-variables.md

@@ -27,7 +27,7 @@ setx FACE_APIKEY <your_key>
 setx FACE_ENDPOINT <your_endpoint>
 ```
 
-After you add the environment variables, you may need to restart any running programs that will read the environment variables, including the console window.
+After you add the environment variables, you might need to restart any running programs that will read the environment variables, including the console window.
 
 #### [Linux](#tab/linux)
 

articles/ai-services/computer-vision/includes/how-to-guides/analyze-image-40-rest.md

@@ -28,7 +28,7 @@ Authentication is done by adding the HTTP request header **Ocp-Apim-Subscription
 
 ## Select the image to analyze
 
-The code in this guide uses remote images referenced by URL. You may want to try different images on your own to see the full capability of the Image Analysis features.
+The code in this guide uses remote images referenced by URL. You might want to try different images on your own to see the full capability of the Image Analysis features.
 
 ### Image URL
 When analyzing a remote image, you specify the image's URL by formatting the request body like this: `{"url":"https://learn.microsoft.com/azure/cognitive-services/computer-vision/images/windows-kitchen.jpg"}`. The **Content-Type** should be `application/json`.

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

@@ -1023,7 +1023,7 @@ Output of this operation depends on configured `events`, for example if there's
 
 ## Use the output generated by the container
 
-You may want to integrate Spatial Analysis detection or events into your application. Here are a few approaches to consider: 
+You might want to integrate Spatial Analysis detection or events into your application. Here are a few approaches to consider: 
 
 * Use the Azure Event Hubs SDK for your chosen programming language to connect to the Azure IoT Hub endpoint and receive the events. For more information, see [Read device-to-cloud messages from the built-in endpoint](/azure/iot-hub/iot-hub-devguide-messages-read-builtin). 
 * Set up **Message Routing** on your Azure IoT Hub to send the events to other endpoints or save the events to your data storage. For more information, see [IoT Hub Message Routing](/azure/iot-hub/iot-hub-devguide-messages-d2c). 

articles/ai-services/computer-vision/tutorials/build-enrollment-app.md

@@ -69,7 +69,7 @@ The sample app is written using JavaScript and the React Native framework. It ca
 
 Now that you've set up the sample app, you can tailor it to your own needs.
 
-For example, you may want to add situation-specific information on your consent page:
+For example, you might want to add situation-specific information on your consent page:
 
 > [!div class="mx-imgBorder"]
 > ![app consent page](../media/enrollment-app/1-consent-1.jpg)