You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-services/containers/disconnected-containers.md
+16-16Lines changed: 16 additions & 16 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -35,7 +35,7 @@ Containers enable you to run Azure AI services APIs in your own environment, and
35
35
Before attempting to run a Docker container in an offline environment, make sure you know the steps to successfully download and use the container. For example:
36
36
37
37
* Host computer requirements and recommendations.
38
-
* The Docker `pull` command you'll use to download the container.
38
+
* The Docker `pull` command you use to download the container.
39
39
* How to validate that a container is running.
40
40
* How to send queries to the container's endpoint, once it's running.
41
41
@@ -48,24 +48,24 @@ Fill out and submit the [request form](https://aka.ms/csdisconnectedcontainers)
48
48
Access is limited to customers that meet the following requirements:
49
49
50
50
* Your organization should be identified as strategic customer or partner with Microsoft.
51
-
* Disconnected containers are expected to run fully offline, hence your use cases must meet one of below or similar requirements:
52
-
*Environment or device(s) with zero connectivity to internet.
51
+
* Disconnected containers are expected to run fully offline, hence your use cases must meet one of these or similar requirements:
52
+
*Environments or devices with zero connectivity to internet.
53
53
* Remote location that occasionally has internet access.
54
54
* Organization under strict regulation of not sending any kind of data back to cloud.
55
-
* Application completed as instructed - Please pay close attention to guidance provided throughout the application to ensure you provide all the necessary information required for approval.
55
+
* Application completed as instructed - Pay close attention to guidance provided throughout the application to ensure you provide all the necessary information required for approval.
56
56
57
57
## Purchase a commitment tier pricing plan for disconnected containers
58
58
59
59
### Create a new resource
60
60
61
-
1. Sign in to the [Azure portal](https://portal.azure.com) and select **Create a new resource** for one of the applicable Azure AI services listed above.
61
+
1. Sign in to the [Azure portal](https://portal.azure.com) and select **Create a new resource** for one of the applicable Azure AI services listed.
62
62
63
63
2. Enter the applicable information to create your resource. Be sure to select **Commitment tier disconnected containers** as your pricing tier.
64
64
65
65
> [!NOTE]
66
66
>
67
-
> * You will only see the option to purchase a commitment tier if you have been approved by Microsoft.
68
-
> * Pricing details are for example only.
67
+
> * You only see the option to purchase a commitment tier if you have been approved by Microsoft.
68
+
> * Pricing details are only examples.
69
69
70
70
1. Select **Review + Create** at the bottom of the page. Review the information, and select **Create**.
71
71
@@ -94,7 +94,7 @@ See the following documentation for steps on downloading and configuring the con
94
94
*[Conversational Language Understanding (CLU)](../language-service/conversational-language-understanding/how-to/use-containers.md#run-the-container-disconnected-from-the-internet)
95
95
96
96
## Environment variable names in Kubernetes deployments
97
-
Some Azure AI Containers, for example Translator, require users to pass environmental variable names that include colons (`:`) when running the container. This will work fine when using Docker, but Kubernetes does not accept colons in environmental variable names.
97
+
Some Azure AI Containers, for example Translator, require users to pass environmental variable names that include colons (`:`) when running the container. This works fine when using Docker, but Kubernetes doesn't accept colons in environmental variable names.
98
98
To resolve this, you can replace colons with double underscore characters (`__`) when deploying to Kubernetes. See the following example of an acceptable format for environment variable names:
99
99
100
100
```Kubernetes
@@ -113,11 +113,11 @@ This example replaces the default format for the `Mounts:License` and `Mounts:Ou
113
113
114
114
## Usage records
115
115
116
-
When operating Docker containers in a disconnected environment, the container will write usage records to a volume where they're collected over time. You can also call a REST endpoint to generate a report about service usage.
116
+
When operating Docker containers in a disconnected environment, the container writes usage records to a volume where they're collected over time. You can also call a REST endpoint to generate a report about service usage.
117
117
118
118
### Arguments for storing logs
119
119
120
-
When run in a disconnected environment, an output mount must be available to the container to store usage logs. For example, you would include `-v /host/output:{OUTPUT_PATH}` and `Mounts:Output={OUTPUT_PATH}` in the example below, replacing `{OUTPUT_PATH}` with the path where the logs will be stored:
120
+
When run in a disconnected environment, an output mount must be available to the container to store usage logs. For example, you would include `-v /host/output:{OUTPUT_PATH}` and `Mounts:Output={OUTPUT_PATH}` in the example below, replacing `{OUTPUT_PATH}` with the path where the logs are stored:
121
121
122
122
```Docker
123
123
docker run -v /host/output:{OUTPUT_PATH} ... <image> ... Mounts:Output={OUTPUT_PATH}
@@ -129,13 +129,13 @@ The container provides two endpoints for returning records about its usage.
129
129
130
130
#### Get all records
131
131
132
-
The following endpoint will provide a report summarizing all of the usage collected in the mounted billing record directory.
132
+
The following endpoint provides a report summarizing all of the usage collected in the mounted billing record directory.
133
133
134
134
```http
135
135
https://<service>/records/usage-logs/
136
136
```
137
137
138
-
It will return JSON similar to the example below.
138
+
It returns JSON similar to the example below.
139
139
140
140
```json
141
141
{
@@ -152,13 +152,13 @@ It will return JSON similar to the example below.
152
152
153
153
#### Get records for a specific month
154
154
155
-
The following endpoint will provide a report summarizing usage over a specific month and year.
155
+
The following endpoint provides a report summarizing usage over a specific month and year.
it will return a JSON response similar to the example below:
161
+
It returns a JSON response similar to the example below:
162
162
163
163
```json
164
164
{
@@ -175,13 +175,13 @@ it will return a JSON response similar to the example below:
175
175
176
176
## Purchase a commitment plan to use containers in disconnected environments
177
177
178
-
Commitment plans for disconnected containers have a calendar year commitment period. When you purchase a plan, you'll be charged the full price immediately. During the commitment period, you can't change your commitment plan, however you can purchase additional unit(s) at a pro-rated price for the remaining days in the year. You have until midnight (UTC) on the last day of your commitment, to end a commitment plan.
178
+
Commitment plans for disconnected containers have a calendar year commitment period. When you purchase a plan, you are charged the full price immediately. During the commitment period, you can't change your commitment plan, however you can purchase more units at a pro-rated price for the remaining days in the year. You have until midnight (UTC) on the last day of your commitment, to end a commitment plan.
179
179
180
180
You can choose a different commitment plan in the **Commitment Tier pricing** settings of your resource.
181
181
182
182
## End a commitment plan
183
183
184
-
If you decide that you don't want to continue purchasing a commitment plan, you can set your resource's auto-renewal to **Do not auto-renew**. Your commitment plan will expire on the displayed commitment end date. After this date, you won't be charged for the commitment plan. You'll be able to continue using the Azure resource to make API calls, charged at pay-as-you-go pricing. You have until midnight (UTC) on the last day of the year to end a commitment plan for disconnected containers, and not be charged for the following year.
184
+
If you decide that you don't want to continue purchasing a commitment plan, you can set your resource's auto-renewal to **Do not auto-renew**. Your commitment plan expires on the displayed commitment end date. After this date, you won't be charged for the commitment plan. You are able to continue using the Azure resource to make API calls, charged at pay-as-you-go pricing. You have until midnight (UTC) on the last day of the year to end a commitment plan for disconnected containers, and not be charged for the following year.
# Install and run Conversational Language Understanding (CLU) containers
18
18
19
19
> [!NOTE]
20
-
> The data limits in a single synchronous API call for the CLU container are 5120 characters per document and up to 10 documents per call.
20
+
> The data limits in a single synchronous API call for the CLU container are 5,120 characters per document and up to 10 documents per call.
21
21
22
22
Containers enable you to host the CLU API on your own infrastructure. If you have security or data governance requirements that can't be fulfilled by calling CLU remotely, then containers might be a good option.
23
23
@@ -41,17 +41,17 @@ You must meet the following prerequisites before using CLU containers.
41
41
42
42
The following table describes the minimum and recommended specifications for the available container. Each CPU core must be at least 2.6 gigahertz (GHz) or faster.
43
43
44
-
It is recommended to have a CPU with AVX-512 instruction set, for the best experience (performance and accuracy).
44
+
It's recommended to have a CPU with AVX-512 instruction set, for the best experience (performance and accuracy).
CPU core and memory correspond to the `--cpus` and `--memory` settings, which are used as part of the `docker run` command.
51
51
52
52
## Export your Conversational Language Understanding model
53
53
54
-
Before you proceed with running the docker image, you will need to export your own trained model to expose it to your container. Use the following command to extract your model and replace the placeholders below with your own values:
54
+
Before you proceed with running the docker image, you need to export your own trained model to expose it to your container. Use the following command to extract your model and replace the placeholders below with your own values:
After creating the exported model in the section above, users will have to run the container in order to download the deployment package that was created specifically for their exported models.
89
+
After creating the exported model in the section above, users have to run the container in order to download the deployment package that was created specifically for their exported models.
| **{API_KEY}** | The key for your Language resource. You can find it on your resource's **Key and endpoint** page, on the Azure portal. | xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx |
94
94
|**{ENDPOINT_URI}**| The endpoint for accessing the API. You can find it on your resource's **Key and endpoint** page, on the Azure portal. |`https://<your-custom-subdomain>.cognitiveservices.azure.com`|
95
95
|**{IMAGE_TAG}**| The image tag representing the language of the container you want to run. Make sure this matches the `docker pull` command you used. | latest |
96
96
|**{LOCAL_CLU_PORT}**| Port number assigned for the container in local machine. | 5000 |
97
-
|**{LOCAL_MODEL_DIRECTORY}**| Absolute directory in host machine where exported models will be saved in. |`C:\usr\local\myDeploymentPackage`|
97
+
|**{LOCAL_MODEL_DIRECTORY}**| Absolute directory in host machine where exported models are be saved in. |`C:\usr\local\myDeploymentPackage`|
98
98
|**{PROJECT_NAME}**| Name of the project that the exported model belongs to | myProject |
99
99
|**{EXPORTED_MODEL_NAME}**| Exported model to be downloaded | myExportedModel |
100
100
@@ -115,7 +115,7 @@ Repeat those steps to download as many models as you'd like to test. They can be
115
115
116
116
## Run the container with `docker run`
117
117
118
-
Once the container is on the host computer, use the [docker run](https://docs.docker.com/engine/reference/commandline/run/) command to run the containers. The container will continue to run until you stop it. Replace the placeholders below with your own values:
118
+
Once the container is on the host computer, use the [docker run](https://docs.docker.com/engine/reference/commandline/run/) command to run the containers. The container continues to run until you stop it. Replace the placeholders below with your own values:
119
119
120
120
121
121
> [!IMPORTANT]
@@ -131,7 +131,7 @@ To run the CLU container, execute the following `docker run` command. Replace th
131
131
|**{IMAGE_TAG}**| The image tag representing the language of the container you want to run. Make sure this matches the `docker pull` command you used. |`latest`|
132
132
|**{LOCAL_CLU_PORT}**|Port number assigned for the container in local machine. |5000 |
133
133
|**{LOCAL_NER_PORT}**|Port number of the NER container. See Run NER Container section below. |5001 (Has to be different that the above port number) |
134
-
|**{LOCAL_LOGGING_DIRECTORY}**|Absolute directory in host machine where that logs will be saved in. |`C:\usr\local\mylogs`|
134
+
|**{LOCAL_LOGGING_DIRECTORY}**|Absolute directory in host machine where that logs are saved in. |`C:\usr\local\mylogs`|
135
135
|**{LOCAL_MODEL_DIRECTORY}**|Absolute directory in host machine where exported models are saved in. |`C:\usr\local\myDeploymentPackage`|
136
136
137
137
```bash
@@ -152,9 +152,9 @@ This command:
152
152
[!INCLUDE [Running multiple containers on the same host](../../../includes/cognitive-services-containers-run-multiple-same-host.md)]
153
153
154
154
## Running NER Container
155
-
CLU relies on NER to handle prebuilt entities. The CLU container will work properly without NER if users decide not to integrate it. NER billing is disabled when it’s used through CLU, no extra charges are generated unless a call is made directly to NER’s container.
155
+
CLU relies on NER to handle prebuilt entities. The CLU container works properly without NER if users decide not to integrate it. NER billing is disabled when it’s used through CLU, no extra charges are generated unless a call is made directly to NER’s container.
156
156
157
-
To set NER up in CLU container
157
+
To set up NER in CLU container
158
158
- Follow the [NER container documentation](../../named-entity-recognition/how-to/use-containers.md).
159
159
- When running CLU container, make sure to set the parameter `Ner_Url `so that `Ner_Url=http://host.docker.internal:{LOCAL_NER_PORT}`
160
160
@@ -202,7 +202,7 @@ In this article, you learned concepts and workflow for downloading, installing,
202
202
* You must specify billing information when instantiating a container.
203
203
204
204
> [!IMPORTANT]
205
-
> Azure AI containers are not licensed to run without being connected to Azure for metering. Customers need to enable the containers to communicate billing information with the metering service at all times. Azure AI containers do not send customer data (e.g. text that is being analyzed) to Microsoft.
205
+
> Azure AI containers aren't licensed to run without being connected to Azure for metering. Customers need to enable the containers to communicate billing information with the metering service at all times. Azure AI containers don't send customer data (for example, text that is being analyzed) to Microsoft.
0 commit comments