Merge pull request #112903 from diberry/diberry/0427-qna-fresh-april

[Cogsvcs] Qna Maker - freshness

Author: GitHubber17

articles/cognitive-services/QnAMaker/Quickstarts/get-answer-from-knowledge-base-using-url-tool.md

@@ -9,7 +9,7 @@ ms.service: cognitive-services
 ms.subservice: qna-maker
 zone_pivot_groups: URL-test-interface
 ms.topic: quickstart
-ms.date: 02/08/2020
+ms.date: 04/27/2020
 ms.author: diberry
 #Customer intent: As an knowledge base manager new to the QnA Maker service, I want to get an answer from a published knowledge base using a URL tool such as Postman or cURL.
 ---

articles/cognitive-services/QnAMaker/Quickstarts/quickstart-sdk.md

@@ -2,7 +2,7 @@
 title: "Quickstart: Use SDK to create and manage knowledge base - QnA Maker"
 description: This quickstart shows you how to create and manage your knowledge base using the client SDK.
 ms.topic: quickstart
-ms.date: 01/13/2020
+ms.date: 04/27/2020
 zone_pivot_groups: programming-languages-set-six
 ---
 

articles/cognitive-services/QnAMaker/includes/quickstart-sdk-csharp.md

@@ -2,14 +2,16 @@
 title: "Quickstart: QnA Maker client library for .NET"
 description: This quickstart shows how to get started with the QnA Maker client library for .NET. Follow these steps to install the package and try out the example code for basic tasks.  QnA Maker enables you to power a question-and-answer service from your semi-structured content like FAQ documents, URLs, and product manuals.
 ms.topic: quickstart
-ms.date: 01/13/2020
+ms.date: 04/27/2020
 ---
 Use the QnA Maker client library for .NET to:
 
 * Create a knowledge base
-* Manage a knowledge base
+* Update a knowledge base
 * Publish a knowledge base
-* Generate an answer from the knowledge base
+* Get published endpoint key
+* Wait for long-running task
+* Delete knowledge base
 
 [Reference documentation](https://docs.microsoft.com/dotnet/api/microsoft.azure.cognitiveservices.knowledge.qnamaker?view=azure-dotnet) | [Library source code](https://github.com/Azure/azure-sdk-for-net/tree/master/sdk/cognitiveservices/Knowledge.QnAMaker) | [Package (NuGet)](https://www.nuget.org/packages/Microsoft.Azure.CognitiveServices.Knowledge.QnAMaker/) | [C# Samples](https://github.com/Azure-Samples/cognitive-services-qnamaker-csharp)
 
@@ -18,15 +20,18 @@ Use the QnA Maker client library for .NET to:
 ## Prerequisites
 
 * Azure subscription - [Create one for free](https://azure.microsoft.com/free/)
-* The current version of [.NET Core](https://dotnet.microsoft.com/download/dotnet-core).
+* The [Visual Studio IDE](https://visualstudio.microsoft.com/vs/) or current version of [.NET Core](https://dotnet.microsoft.com/download/dotnet-core).
+* Once you have your Azure subscription, create a [QnA Maker resource](https://ms.portal.azure.com/#create/Microsoft.CognitiveServicesQnAMaker) in the Azure portal to get your authoring key and endpoint. After it deploys, select **Go to resource**.
+    * You will need the key and endpoint from the resource you create to connect your application to the QnA Maker API. You'll paste your key and endpoint into the code below later in the quickstart.
+    * You can use the free pricing tier (`F0`) to try the service, and upgrade later to a paid tier for production.
 
 ## Setting up
 
 ### Create a QnA Maker Azure resource
 
 Azure Cognitive Services are represented by Azure resources that you subscribe to. Create a resource for QnA Maker using the [Azure portal](https://docs.microsoft.com/azure/cognitive-services/cognitive-services-apis-create-account) or [Azure CLI](https://docs.microsoft.com/azure/cognitive-services/cognitive-services-apis-create-account-cli) on your local machine.
 
-After getting a key and endpoint for your resource, [create environment variables](https://docs.microsoft.com/azure/cognitive-services/cognitive-services-apis-create-account#configure-an-environment-variable-for-authentication) for the key, named `QNAMAKER_SUBSCRIPTION_KEY`. The resource name is used as part of the endpoint URL.
+After getting a key and endpoint for your resource, [create an environment variable](https://docs.microsoft.com/azure/cognitive-services/cognitive-services-apis-create-account#configure-an-environment-variable-for-authentication) for the key, named `QNAMAKER_SUBSCRIPTION_KEY`. The resource name is used as custom subdomain of the endpoint URL.
 
 ### Create a new C# application
 
@@ -115,7 +120,7 @@ In the **main** method, create a variable for your resource's authentication pul
 
 Create a [QnAMakerRuntimeClient](https://docs.microsoft.com/dotnet/api/microsoft.azure.cognitiveservices.knowledge.qnamaker.qnamakerruntimeclient?view=azure-dotnet) to query the knowledge base to generate an answer or train from active learning.
 
-[!code-csharp[Authenticate the runtime](~/samples-qnamaker-csharp/documentation-samples/quickstarts/Knowledgebase_Quickstart/Program.cs?name=EndpointKey)]
+[!code-csharp[Authenticate the runtime](~/samples-qnamaker-csharp/documentation-samples/quickstarts/Knowledgebase_Quickstart/Program.cs?name=EndpointKey&highlight=3)]
 
 ## Create a knowledge base
 
@@ -129,7 +134,7 @@ Call the [CreateAsync](https://docs.microsoft.com/dotnet/api/microsoft.azure.cog
 
 The final line of the following code returns the knowledge base ID from the response from MonitorOoperation.
 
-[!code-csharp[Create a knowledge base](~/samples-qnamaker-csharp/documentation-samples/quickstarts/Knowledgebase_Quickstart/Program.cs?name=CreateKB&highlight=29,30)]
+[!code-csharp[Create a knowledge base](~/samples-qnamaker-csharp/documentation-samples/quickstarts/Knowledgebase_Quickstart/Program.cs?name=CreateKB&highlight=30)]
 
 Make sure the include the [`MonitorOperation`](#get-status-of-an-operation) function, referenced in the above code, in order to successfully create a knowledge base.
 

articles/cognitive-services/QnAMaker/includes/quickstart-sdk-nodejs.md

@@ -2,7 +2,7 @@
 title: "Quickstart: QnA Maker client library for Node.js"
 description: This quickstart shows how to get started with the QnA Maker client library for Node.js.
 ms.topic: quickstart
-ms.date: 01/13/2020
+ms.date: 04/27/2020
 ---
 Use the QnA Maker client library for Node.js to:
 
@@ -21,6 +21,9 @@ Use the QnA Maker client library for Node.js to:
 
 * Azure subscription - [Create one for free](https://azure.microsoft.com/free/)
 * The current version of [Node.js](https://nodejs.org).
+* Once you have your Azure subscription, create a [QnA Maker resource](https://ms.portal.azure.com/#create/Microsoft.CognitiveServicesQnAMaker) in the Azure portal to get your authoring key and endpoint. After it deploys, select **Go to resource**.
+    * You will need the key and endpoint from the resource you create to connect your application to the QnA Maker API. You'll paste your key and endpoint into the code below later in the quickstart.
+    * You can use the free pricing tier (`F0`) to try the service, and upgrade later to a paid tier for production.
 
 ## Setting up
 
@@ -126,7 +129,7 @@ Make sure the include the [`wait_for_operation`](#get-status-of-an-operation) fu
 
 ## Publish a knowledge base
 
-Publish the knowledge base using the [publish](https://docs.microsoft.com/javascript/api/@azure/cognitiveservices-qnamaker/knowledgebase?view=azure-node-latest#publish-string--msrest-requestoptionsbase-) method. This takes the current saved and trained model, referenced by the knowledge base ID, and publishes that at an endpoint. Check the HTTP response code to validate publish succeeded.
+Publish the knowledge base using the [publish](https://docs.microsoft.com/javascript/api/@azure/cognitiveservices-qnamaker/knowledgebase?view=azure-node-latest#publish-string--msrest-requestoptionsbase-) method. This takes the current saved and trained model, referenced by the knowledge base ID, and publishes that at an endpoint. Check the HTTP response code to validate that the publish succeeded.
 
 [!code-javascript[Publish a knowledge base](~/cognitive-services-quickstart-code/javascript/QnAMaker/sdk/qnamaker_quickstart.js?name=publishKnowledgeBase&highlight=3)]
 

articles/cognitive-services/QnAMaker/includes/quickstart-sdk-python.md

@@ -1,9 +1,17 @@
-
+---
+title: "Quickstart: QnA Maker client library for Python"
+description: This quickstart shows how to get started with the QnA Maker client library for Python.
+ms.topic: include
+ms.date: 04/27/2020
+---
 Use the QnA Maker client library for python to:
 
 * Create a knowledge base
-* Manage a knowledge base
+* Update a knowledge base
 * Publish a knowledge base
+* Get published endpoint key
+* Wait for long-running task
+* Delete knowledge base
 
 [Reference documentation](https://docs.microsoft.com/python/api/azure-cognitiveservices-knowledge-qnamaker/azure.cognitiveservices.knowledge.qnamaker?view=azure-python) | [Library source code](https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/cognitiveservices/azure-cognitiveservices-knowledge-qnamaker) | [Package (pypi)](https://pypi.org/project/azure-cognitiveservices-knowledge-qnamaker/) | [Python samples](https://github.com/Azure-Samples/cognitive-services-qnamaker-python/blob/master/documentation-samples/quickstarts/knowledgebase_quickstart/knowledgebase_quickstart.py)
 
@@ -13,6 +21,9 @@ Use the QnA Maker client library for python to:
 
 * Azure subscription - [Create one for free](https://azure.microsoft.com/free/)
 * [Python 3.x](https://www.python.org/)
+* Once you have your Azure subscription, create a [QnA Maker resource](https://ms.portal.azure.com/#create/Microsoft.CognitiveServicesQnAMaker) in the Azure portal to get your authoring key and endpoint. After it deploys, select **Go to resource**.
+    * You will need the key and endpoint from the resource you create to connect your application to the QnA Maker API. You'll paste your key and endpoint into the code below later in the quickstart.
+    * You can use the free pricing tier (`F0`) to try the service, and upgrade later to a paid tier for production.
 
 ## Setting up
 

articles/cognitive-services/QnAMaker/includes/quickstart-test-tool-curl.md

@@ -8,7 +8,7 @@ ms.service: cognitive-services
 ms.subservice: luis
 ms.topic: include
 ms.custom: include file
-ms.date: 02/08/2020
+ms.date: 04/27/2020
 ms.author: diberry
 ---
 
@@ -291,120 +291,7 @@ The JSON response uses the same schema as the published knowledge base query.
 
     Because the question of `Thank you` exactly matched a Chit-chat question, QnA Maker is completely confident with the score of 100. QnA Maker also returned all the related questions, as well as the metadata property containing the Chit-chat metadata tag information.
 
-## Use cURL with threshold and default answer
-
-You can request a minimum threshold for the answer. If the threshold is not met, the default answer is returned.
-
-1. Use the following cURL command, replacing with your own resource name, knowledge base ID, and endpoint key, to ask for an answer to `size` with a threshold of 80% or better. The knowledge base should not find that answer because the question's score is 71%, and instead return the default answer you provided when you created the knowledge base.
-
-    ```bash
-    curl -X POST https://replace-with-your-resource-name.azurewebsites.net/qnamaker/knowledgebases/replace-with-your-knowledge-base-id/generateAnswer -H "Authorization: EndpointKey replace-with-your-endpoint-key" -H "Content-type: application/json" -d "{'question':'size', 'scoreThreshold':80.00}"
-    ```
-
-1. Run the cURL command and receive the JSON response, including the score and answer.
-
-    ```json
-    {
-        "answers": [
-            {
-                "questions": [],
-                "answer": "No good match found in KB.",
-                "score": 0.0,
-                "id": -1,
-                "source": null,
-                "metadata": []
-            }
-        ],
-        "debugInfo": null,
-        "activeLearningEnabled": true
-    }
-    ```
-
-    QnA Maker returned a score of `0`, which means no confidence. It also returned the default answer.
-
-    ```json
-    {
-      "answers": [
-          {
-              "questions": [
-                  "I thank you",
-                  "Oh, thank you",
-                  "My sincere thanks",
-                  "My humblest thanks to you",
-                  "Marvelous, thanks",
-                  "Marvelous, thank you kindly",
-                  "Marvelous, thank you",
-                  "Many thanks to you",
-                  "Many thanks",
-                  "Kthx",
-                  "I'm grateful, thanks",
-                  "Ahh, thanks",
-                  "I'm grateful for that, thank you",
-                  "Perfecto, thanks",
-                  "I appreciate you",
-                  "I appreciate that",
-                  "I appreciate it",
-                  "I am very thankful for that",
-                  "How kind, thank you",
-                  "Great, thanks",
-                  "Great, thank you",
-                  "Gracias",
-                  "Gotcha, thanks",
-                  "Gotcha, thank you",
-                  "Awesome thanks!",
-                  "I'm grateful for that, thank you kindly",
-                  "thank you pal",
-                  "Wonderful, thank you!",
-                  "Wonderful, thank you very much",
-                  "Why thank you",
-                  "Thx",
-                  "Thnx",
-                  "That's very kind",
-                  "That's great, thanks",
-                  "That is lovely, thanks",
-                  "That is awesome, thanks!",
-                  "Thanks bot",
-                  "Thanks a lot",
-                  "Okay, thanks!",
-                  "Thank you so much",
-                  "Perfect, thanks",
-                  "Thank you my friend",
-                  "Thank you kindly",
-                  "Thank you for that",
-                  "Thank you bot",
-                  "Thank you",
-                  "Right on, thanks very much",
-                  "Right on, thanks a lot",
-                  "Radical, thanks",
-                  "Rad, thanks",
-                  "Rad thank you",
-                  "Wonderful, thanks!",
-                  "Thanks"
-              ],
-              "answer": "You're welcome.",
-              "score": 100.0,
-              "id": 75,
-              "source": "qna_chitchat_Professional.tsv",
-              "metadata": [
-                  {
-                      "name": "editorial",
-                      "value": "chitchat"
-                  }
-              ],
-              "context": {
-                  "isContextOnly": false,
-                  "prompts": []
-              }
-          }
-      ],
-      "debugInfo": null,
-      "activeLearningEnabled": true
-    }
-    ```
-
-    Because the question of `Thank you` exactly matched a Chit-chat question, QnA Maker is completely confident with the score of 100. QnA Maker also returned all the related questions, as well as the metadata property containing the Chit-chat metadata tag information.
-
-## Use cURL with threshold and default answer
+## Use threshold and default answer
 
 You can request a minimum threshold for the answer. If the threshold is not met, the default answer is returned.
 

articles/cognitive-services/QnAMaker/includes/quickstart-test-tool-postman.md

@@ -8,7 +8,7 @@ ms.service: cognitive-services
 ms.subservice: luis
 ms.topic: include
 ms.custom: include file
-ms.date: 02/08/2020
+ms.date: 04/27/2020
 ms.author: diberry
 ---
 
@@ -35,7 +35,7 @@ Use this procedure to configure Postman, then read each subsequent section to co
     |Name|Setting|Purpose and value|
     |--|--|--|
     |`POST`| `/knowledgebases/replace-with-your-knowledge-base-id/generateAnswer`|This is the HTTP method and route for the URL.|
-    |`Host`|`https://diberry-qna-s0-s.azurewebsites.net/qnamaker`|This is the host of the URL. Concatenate the Host and Post values to get the complete generateAnswer URL.|
+    |`Host`|`https://YOUR-RESOURCE_NAME.azurewebsites.net/qnamaker`|This is the host of the URL. Concatenate the Host and Post values to get the complete generateAnswer URL.|
     |`Authorization`|`EndpointKey xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx`|The header value for to authorize your request to Azure. |
     |`Content-type`|`application/json`|The header value for your content.|
     ||`{"question":"<Your question>"}`|The body of the POST request as a JSON object. This value will change in each following section depending on what the query is meant to do.|