acrolinx

Author: PatrickFarley

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

@@ -30,7 +30,7 @@ The content safety container is available in public preview. Containers in previ
 
 To use the content safety containers in environments that are disconnected from the internet, you must submit a [request form](https://aka.ms/csdisconnectedcontainers) and wait for approval. For more information about applying and purchasing a commitment plan to use containers in disconnected environments, see [Use containers in disconnected environments](../../../../ai-services/containers/disconnected-containers.md) in the Azure AI services documentation.
 
-The request form takes information about you, your company, and the user scenario for which you'll use the container. Make sure you meet the following requirements:
+The request form takes information about you, your company, and the user scenario for which you use the container. Make sure you meet the following requirements:
 
 * On the form, you must use the email address associated with your Azure subscription ID.
 * The Azure resource you use to run the container must be created with the approved Azure subscription ID.

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

@@ -13,7 +13,7 @@ keywords: on-premises, Docker, container
 
 # Analyze image content with docker containers
 
-The analyze image container scans image for sexual content, violence, hate, and self harm with multi-severity levels. In this article, you learn how to download, install, and run a content safety to image container.
+The Analyze image container scans image for sexual content, violence, hate, and self harm with multi-severity levels. In this article, you learn how to download, install, and run a content safety to image container.
 
 For more information about prerequisites, validating that a container is running, running multiple containers on the same host, and running disconnected containers, see [Install and run content safety containers with Docker](container-install-run.md).
 

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

@@ -64,7 +64,7 @@ The minimum GPU requirement for these containers is NVIDIA's T4, however, we rec
 
 The table below presents the requests per second (RPS) and latency metrics obtained when the containers were tested on a single-node GPU configuration using NVIDIA's T4 and A100 GPUs.
 
-Note that even with identical GPUs, performance can fluctuate based on the GPU load and the specific configuration of the environment. The benchmark data we provide should be used as a reference point when considering the deployment of content safety containers in your environment. For the most accurate assessment, we recommend conducting tests within your specific environment.
+Even with identical GPUs, performance can fluctuate based on the GPU load and the specific configuration of the environment. The benchmark data we provide should be used as a reference point when considering the deployment of content safety containers in your environment. For the most accurate assessment, we recommend conducting tests within your specific environment.
 
 **[to-do] make below two table inline sections, one for text one for image.** 
 

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

@@ -1,5 +1,5 @@
 ---
-title: analyze text container - Azure AI content safety 
+title: Analyze text container - Azure AI content safety 
 titleSuffix: Azure AI services
 description: Install and run content safety analyze text containers with Docker to detect harmful content in text.
 author: 
@@ -13,7 +13,7 @@ keywords: on-premises, Docker, container
 
 # Analyze text content with Docker container 
 
-The analyze text container scans text generate by foundation model or human for sexual content, violence, hate, and self harm with multi-severity levels.	In this article, you learn how to download, install, and run a content safety analyze text container.
+The Analyze text container scans text generate by foundation model or human for sexual content, violence, hate, and self harm with multi-severity levels. In this article, you learn how to download, install, and run a content safety analyze text container.
 
 For more information about prerequisites, validating that a container is running, running multiple containers on the same host, and running disconnected containers, see [Install and run content safety containers with Docker](container-install-run.md).
 
@@ -82,7 +82,7 @@ docker run -e CUDA_ENABLED=false
 ```
 #### Run the container with blocklist
 
-The Analyze Text container supports the use of a [blocklist feature](./how-to/use-blocklist.md), which allows you to block custom terms. You, as the customer, have the ability to manage these blocklists by using CSV files. You have the flexibility to use multiple CSV files for multiple blocklists.
+The Analyze text container supports the use of a [blocklist feature](./how-to/use-blocklist.md), which allows you to block custom terms. You, as the customer, have the ability to manage these blocklists by using CSV files. You have the flexibility to use multiple CSV files for multiple blocklists.
 
 To run the container with a blocklist, use the following command:
 
@@ -92,7 +92,7 @@ docker run -e BLOCKLIST_DIR=/tmp/blocklist  -v {/path/on/host}:/tmp/blocklist
 
 In the command above, replace `{/path/on/host}` with the path to the blocklist folder on your host machine. This command mounts the blocklist directory from your host machine to the `BLOCKLIST_DIR=/tmp/blocklist` environment variable within the container.
 
-Note, the Analyze Text container uses an exact match method for the blocklist. All items in the blocklist will be converted to lowercase before the matching process. This means, for instance, if you have `Contoso` in your blocklist, both "Contoso" and "contoso" from your input will be considered a match.
+Note, the Analyze text container uses an exact match method for the blocklist. All items in the blocklist will be converted to lowercase before the matching process. This means, for instance, if you have `Contoso` in your blocklist, both "Contoso" and "contoso" from your input are considered a match.
 
 
 
@@ -156,7 +156,7 @@ sudo chown -R nonroot:nonroot <YOUR_LOCAL_MACHINE_PATH_1> <YOUR_LOCAL_MACHINE_PA
 ```
 #### Run the container with blocklist
 
-The Analyze Text container supports the use of a [blocklist feature](./how-to/use-blocklist.md), which allows you to block custom terms. You, as the customer, have the ability to manage these blocklists by using CSV files. You have the flexibility to use multiple CSV files for multiple blocklists.
+The Analyze text container supports the use of a [blocklist feature](./how-to/use-blocklist.md), which allows you to block custom terms. You, as the customer, have the ability to manage these blocklists by using CSV files. You have the flexibility to use multiple CSV files for multiple blocklists.
 
 To run the container with a blocklist, use the following command:
 
@@ -166,7 +166,7 @@ docker run -e BLOCKLIST_DIR=/tmp/blocklist  -v {/path/on/host}:/tmp/blocklist
 
 In the command above, replace `{/path/on/host}` with the path to the blocklist folder on your host machine. This command mounts the blocklist directory from your host machine to the `BLOCKLIST_DIR=/tmp/blocklist` environment variable within the container.
 
-Note, the Analyze Text container uses an exact match method for the blocklist. All items in the blocklist will be converted to lowercase before the matching process. This means, for instance, if you have `Contoso` in your blocklist, both "Contoso" and "contoso" from your input will be considered a match.
+Note, the Analyze text container uses an exact match method for the blocklist. All items in the blocklist are converted to lowercase before the matching process. This means, for instance, if you have `Contoso` in your blocklist, both "Contoso" and "contoso" from your input are considered a match.
 
 ---
 

articles/ai-services/content-safety/how-to/embedded-content-safety.md

@@ -2,8 +2,8 @@
 title: Embedded content safety - Azure AI Content Safety
 titleSuffix: Azure AI services
 description: Embedded content safety is designed for on-device scenarios where cloud connectivity is intermittent or unavailable.
-author: 
-manager:
+author: PatrickFarley
+manager: nitinme
 ms.service: azure-ai-content-safety
 ms.topic: how-to
 ms.date: 9/24/2024
@@ -82,10 +82,10 @@ Memory load – An embedded content safety text analysis process consumes about
 
 ### SDK parameters that can impact performance
 
-Below SDK parameters can impact the infernece time of the embedded content safety model. 
+Below SDK parameters can impact the inference time of the embedded content safety model. 
 
--  `gpuEnabled` Set as **true** to enable GPU, otherwise CPU will be used. Generally inference time will be shorter on GPU.
--  `numThreads` This parameter only works for CPU. It defines number of threads to be used in a multi-threaded environment. We support a maximum number of 4 threads.
+-  `gpuEnabled` Set as **true** to enable GPU, otherwise CPU is used. Generally inference time is shorter on GPU.
+-  `numThreads` This parameter only works for CPU. It defines number of threads to be used in a multi-threaded environment. We support a maximum number of four threads.
 
 See next section to for the performance benchmark data on popular PC CPUs and GPUs
 
@@ -96,7 +96,7 @@ See next section to for the performance benchmark data on popular PC CPUs and GP
 
 As stated above, there are multiple factors that impact the performance of embedded content safety model. We highly suggest you test it on your device and tweak the parameters to fit for your application's requirement. 
 
-We also conduct performance benchmark tests on various popular PC CPUs and GPUs. Please keep in mind that even with the same CPU, performance can vary depending on the CPU and memory load. The benchmark data provided should serve as a reference when considering if the embedded content safety can operate on your device. For optimal results, we advise testing on your intended device and in your specific application scenario.
+We also conduct performance benchmark tests on various popular PC CPUs and GPUs. Keep in mind that even with the same CPU, performance can vary depending on the CPU and memory load. The benchmark data provided should serve as a reference when considering if the embedded content safety can operate on your device. For optimal results, we advise testing on your intended device and in your specific application scenario.
 
 
 The [sample code](https://github.com/Azure/azure-ai-content-safety-sdk) includes code snippet to monitor performance metrics like memory, inference time.