Skip to content

Commit 18e86fe

Browse files
authored
Merge pull request #258531 from jboback/Language-day-1
Ignite 2023 day 1 additions for Language
2 parents 3bb5929 + f8871cd commit 18e86fe

10 files changed

Lines changed: 214 additions & 142 deletions

File tree

articles/ai-services/cognitive-services-container-support.md

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -53,9 +53,10 @@ Azure AI containers provide the following set of Docker containers, each of whic
5353
| [Language service][ta-containers-language] | **Text Language Detection** ([image](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/language/about)) | For up to 120 languages, detects which language the input text is written in and report a single language code for every document submitted on the request. The language code is paired with a score indicating the strength of the score. | Generally available. <br> This container can also [run in disconnected environments](containers/disconnected-containers.md). |
5454
| [Language service][ta-containers-sentiment] | **Sentiment Analysis** ([image](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/sentiment/about)) | Analyzes raw text for clues about positive or negative sentiment. This version of sentiment analysis returns sentiment labels (for example *positive* or *negative*) for each document and sentence within it. | Generally available. <br> This container can also [run in disconnected environments](containers/disconnected-containers.md). |
5555
| [Language service][ta-containers-health] | **Text Analytics for health** ([image](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/healthcare/about))| Extract and label medical information from unstructured clinical text. | Generally available |
56+
| [Language service][ta-containers-ner] | **Named Entity Recognition** ([image](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/ner/about))| Extract named entities from text. | Generally available. <br>This container can also [run in disconnected environments](containers/disconnected-containers.md). |
5657
| [Language service][ta-containers-cner] | **Custom Named Entity Recognition** ([image](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/customner/about))| Extract named entities from text, using a custom model you create using your data. | Preview |
57-
| [Language service][ta-containers-summarization] | **Summarization** ([image](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/summarization/about))| Summarize text from various sources. | Preview. <br>This container can also [run in disconnected environments](containers/disconnected-containers.md). |
58-
| [Translator][tr-containers] | **Translator** ([image](https://mcr.microsoft.com/product/azure-cognitive-services/translator/text-translation/about))| Translate text in several languages and dialects. | Generally available. Gated - [request access](https://aka.ms/csgate-translator). <br>This container can also [run in disconnected environments](containers/disconnected-containers.md). |
58+
| [Language service][ta-containers-summarization] | **Summarization** ([image](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/summarization/about))| Summarize text from various sources. | Public preview. <br>This container can also [run in disconnected environments](containers/disconnected-containers.md). |
59+
| [Translator][tr-containers] | **Translator** ([image](https://mcr.microsoft.com/product/azure-cognitive-services/translator/text-translation/about))| Translate text in several languages and dialects. | Generally available. Gated - [request access](https://aka.ms/csgate-translator). <br>This container can also [run in disconnected environments](containers/disconnected-containers.md). |
5960

6061
### Speech containers
6162

@@ -116,7 +117,6 @@ Install and explore the functionality provided by containers in Azure AI service
116117
* [Speech Service API containers][sp-containers]
117118
* [Language service containers][ta-containers]
118119
* [Translator containers][tr-containers]
119-
* [Summarization containers][su-containers]
120120

121121
<!--* [Personalizer containers](https://go.microsoft.com/fwlink/?linkid=2083928&clcid=0x409)
122122
-->
@@ -138,5 +138,6 @@ Install and explore the functionality provided by containers in Azure AI service
138138
[ta-containers-health]: language-service/text-analytics-for-health/how-to/use-containers.md
139139
[ta-containers-cner]: language-service/custom-named-entity-recognition/how-to/use-containers.md
140140
[ta-containers-summarization]: language-service/summarization/how-to/use-containers.md
141+
[ta-containers-ner]: language-service/named-entity-recognition/how-to/use-containers.md
141142
[tr-containers]: translator/containers/translator-how-to-install-container.md
142143
[request-access]: https://aka.ms/csgate

articles/ai-services/language-service/named-entity-recognition/how-to-call.md

Lines changed: 6 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,7 @@ ms.custom: language-service-ner, ignite-fall-2021
1313
---
1414

1515

16-
# How to use Named Entity Recognition(NER)
16+
# How to use Named Entity Recognition (NER)
1717

1818
The NER feature can evaluate unstructured text, and extract named entities from text in several predefined categories, for example: person, location, event, product, and organization.
1919

@@ -23,11 +23,6 @@ The NER feature can evaluate unstructured text, and extract named entities from
2323

2424
## Determine how to process the data (optional)
2525

26-
### Specify the NER model
27-
28-
By default, this feature uses the latest available AI model on your text. You can also configure your API requests to use a specific [model version](../concepts/model-lifecycle.md).
29-
30-
3126
### Input languages
3227

3328
When you submit documents to be processed, you can specify which of [the supported languages](language-support.md) they're written in. if you don't specify a language, key phrase extraction defaults to English. The API may return offsets in the response to support different [multilingual and emoji encodings](../concepts/multilingual-emoji-support.md).
@@ -92,7 +87,7 @@ The above examples would return entities falling under the `Location` entity typ
9287

9388
```
9489

95-
This method returns all `Location` entities only falling under the `GPE` tag and ignore any other entity falling under the `Location` type that is tagged with any other entity tag such as `Structural` or `Geological` tagged `Location` entities. We could also further drill-down on our results by using the `excludeList` parameter. `GPE` tagged entities could be tagged with the following tags: `City`, `State`, `CountryRegion`, `Continent`. We could, for example, exclude `Continent` and `CountryRegion` tags for our example:
90+
This method returns all `Location` entities only falling under the `GPE` tag and ignore any other entity falling under the `Location` type that is tagged with any other entity tag such as `Structural` or `Geological` tagged `Location` entities. We could also further drill down on our results by using the `excludeList` parameter. `GPE` tagged entities could be tagged with the following tags: `City`, `State`, `CountryRegion`, `Continent`. We could, for example, exclude `Continent` and `CountryRegion` tags for our example:
9691

9792
```bash
9893

@@ -113,6 +108,10 @@ This method returns all `Location` entities only falling under the `GPE` tag and
113108

114109
Using these parameters we can successfully filter on only `Location` entity types, since the `GPE` entity tag included in the `includeList` parameter, falls under the `Location` type. We then filter on only Geopolitical entities and exclude any entities tagged with `Continent` or `CountryRegion` tags.
115110

111+
## Specify the NER model
112+
113+
By default, this feature uses the latest available AI model on your text. You can also configure your API requests to use a specific [model version](../concepts/model-lifecycle.md).
114+
116115
## Service and data limits
117116

118117
[!INCLUDE [service limits article](../includes/service-limits-link.md)]

articles/ai-services/language-service/named-entity-recognition/how-to/use-containers.md

Lines changed: 18 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -28,48 +28,43 @@ You must meet the following prerequisites before using Named Entity Recognition
2828
* [Docker](https://docs.docker.com/) installed on a host computer. Docker must be configured to allow the containers to connect with and send billing data to Azure.
2929
* On Windows, Docker must also be configured to support Linux containers.
3030
* You should have a basic understanding of [Docker concepts](https://docs.docker.com/get-started/overview/).
31-
* A <a href="https://portal.azure.com/#create/Microsoft.CognitiveServicesTextAnalytics" title="Create a Language resource" target="_blank">Language resource </a> with the free (F0) or standard (S) [pricing tier](https://azure.microsoft.com/pricing/details/cognitive-services/text-analytics/).
31+
* A <a href="https://portal.azure.com/#create/Microsoft.CognitiveServicesTextAnalytics" title="Create a Language resource" target="_blank">Language resource </a>
3232

3333
[!INCLUDE [Gathering required parameters](../../../containers/includes/container-gathering-required-parameters.md)]
3434

3535
## Host computer requirements and recommendations
3636

3737
[!INCLUDE [Host Computer requirements](../../../../../includes/cognitive-services-containers-host-computer.md)]
3838

39-
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. The allowable Transactions Per Second (TPS) are also listed.
39+
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.
4040

41-
| | Minimum host specs | Recommended host specs | Minimum TPS | Maximum TPS |
42-
|--------------------------------|------------------------|------------------------|-------------|-------------|
43-
| **Named Entity Recognition** | 1 core, 2GB memory | 4 cores, 8GB memory | 15 | 30 |
41+
It is recommended to have a CPU with AVX-512 instruction set, for the best experience (performance and accuracy).
42+
43+
| | Minimum host specs | Recommended host specs |
44+
|--------------------------------|------------------------|------------------------|
45+
| **Named Entity Recognition** | 1 core, 2GB memory | 4 cores, 8GB memory |
4446

4547
CPU core and memory correspond to the `--cpus` and `--memory` settings, which are used as part of the `docker run` command.
4648

4749
## Get the container image with `docker pull`
4850

49-
The Named Entity Recognition container image can be found on the `mcr.microsoft.com` container registry syndicate. It resides within the `azure-cognitive-services/textanalytics/` repository and is named `sentiment`. The fully qualified container image name is, `mcr.microsoft.com/azure-cognitive-services/textanalytics/ner`
51+
The Named Entity Recognition container image can be found on the `mcr.microsoft.com` container registry syndicate. It resides within the `azure-cognitive-services/textanalytics/` repository and is named `ner`. The fully qualified container image name is, `mcr.microsoft.com/azure-cognitive-services/textanalytics/ner`
5052

51-
To use the latest version of the container, you can use the `latest` tag, which is for english. You can also find a full list of containers for supported languages using the [tags on the MCR](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/sentiment/tags).
53+
To use the latest version of the container, you can use the `latest` tag, which is for English. You can also find a full list of containers for supported languages using the [tags on the MCR](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/ner/tags).
5254

53-
The Named Entity Recognition container v3 container is available in several languages. To download the container for the English container, use the command below.
55+
The latest Named Entity Recognition container is available in several languages. To download the container for the English container, use the command below.
5456

5557
```
56-
docker pull mcr.microsoft.com/azure-cognitive-services/textanalytics/sentiment:3.0-en
58+
docker pull mcr.microsoft.com/azure-cognitive-services/textanalytics/ner:latest
5759
```
5860

5961
[!INCLUDE [Tip for using docker list](../../../../../includes/cognitive-services-containers-docker-list-tip.md)]
6062

61-
## Download the Named Entity Recognition container models
62-
63-
A pre-requisite for running the Named Entity Recognition container is to download the models first. This can be done by running one of the following commands using a CPU container image as an example.
64-
65-
It's not recommended to download models for all skills inside the same HOST_MODELS_Path, as the container loads all models inside the HOST_MODELS_PATH. Doing so would use a large amount of memory. It's recommended to only download the model for the skill you need in a particular HOST_MODELS_PATH.
66-
67-
In order to ensure compatibility between models and the container, re-download the utilized models whenever you create a container using a new image version. When using a disconnected container, the license should be downloaded again after downloading the models.
68-
6963
## Run the container with `docker run`
7064

7165
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:
72-
<!--
66+
67+
7368
> [!IMPORTANT]
7469
> * 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.
7570
> * 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).
@@ -80,16 +75,15 @@ To run the Named Entity Recognition container, execute the following `docker run
8075
|-------------|-------|---|
8176
| **{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`|
8277
| **{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` |
83-
| **{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. | `3.0-en` |
78+
| **{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` |
8479

8580
```bash
8681
docker run --rm -it -p 5000:5000 --memory 8g --cpus 1 \
87-
mcr.microsoft.com/azure-cognitive-services/textanalytics/sentiment:{IMAGE_TAG} \
82+
mcr.microsoft.com/azure-cognitive-services/textanalytics/ner:{IMAGE_TAG} \
8883
Eula=accept \
8984
Billing={ENDPOINT_URI} \
9085
ApiKey={API_KEY}
9186
```
92-
-->
9387

9488
This command:
9589

@@ -106,10 +100,12 @@ The container provides REST-based query prediction endpoint APIs.
106100

107101
Use the host, `http://localhost:5000`, for container APIs.
108102

109-
<!-- ## Validate container is running -->
103+
<!-- ## Validate container is running -->
110104

111105
[!INCLUDE [Container's API documentation](../../../../../includes/cognitive-services-containers-api-documentation.md)]
112106

107+
For information on how to call NER see [our guide](../how-to-call.md).
108+
113109
## Run the container disconnected from the internet
114110

115111
[!INCLUDE [configure-disconnected-container](../../../containers/includes/configure-disconnected-container.md)]

0 commit comments

Comments
 (0)