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
# Migrate from QnA Maker to custom question answering
13
13
14
-
**Purpose of this document:** This article aims to provide information that can be used to successfully migrate applications that use QnA Maker to custom question answering. Using this article, we hope customers will gain clarity on the following:
14
+
**Purpose of this document:** This article aims to provide information that can be used to successfully migrate applications that use QnA Maker to custom question answering. Using this article, we hope customers gain clarity on the following:
15
15
16
16
- Comparison of features across QnA Maker and custom question answering
> Custom question Answering, a feature of Azure AI Language was introduced in November 2021 with several new capabilities including enhanced relevance using a deep learning ranker, precise answers, and end-to-end region support. Each custom question answering project is equivalent to a knowledge base in QnA Maker. Resource level settings such as Role-based access control (RBAC) are not migrated to the new resource. These resource level settings would have to be reconfigured for the language resource post migration:
26
+
> Custom question Answering, a feature of Azure AI Language was introduced in November 2021 with several new capabilities including enhanced relevance using a deep learning ranker, precise answers, and end-to-end region support. Each custom question answering project is equivalent to a knowledge base in QnA Maker. Resource level settings such as Role-based access control (RBAC) aren't migrated to the new resource. These resource level settings would have to be reconfigured for the language resource post migration:
27
27
>
28
28
> - Automatic RBAC to Language project (not resource)
29
29
> - Automatic enabling of analytics.
@@ -37,15 +37,15 @@ In addition to a new set of features, custom question answering provides many te
|State of the art transformer-based models|➖|✔️|Turing based models that enable search of QnA at web scale.|
40
-
|Pre-built capability|➖|✔️|Using this capability one can leverage the power of custom question answering without having to ingest content and manage resources.|
40
+
|Prebuilt capability|➖|✔️|Using this capability one can use the power of custom question answering without having to ingest content and manage resources.|
41
41
|Precise answering|➖|✔️|Custom question answering supports precise answering with the help of SOTA models.|
42
42
|Smart URL Refresh|➖|✔️|Custom question answering provides a means to refresh ingested content from public sources with a single click.|
43
43
|Q&A over knowledge base (hierarchical extraction)|✔️|✔️||
44
44
|Active learning|✔️|✔️|Custom question answering has an improved active learning model.|
45
45
|Alternate Questions|✔️|✔️|The improved models in custom question answering reduce the need to add alternate questions.|
46
46
|Synonyms|✔️|✔️||
47
47
|Metadata|✔️|✔️||
48
-
|Question Generation (private preview)|➖|✔️|This new feature will allow generation of questions over text.|
48
+
|Question Generation (private preview)|➖|✔️|This new feature allows generation of questions over text.|
49
49
|Support for unstructured documents|➖|✔️|Users can now ingest unstructured documents as input sources and query the content for responses|
50
50
|.NET SDK|✔️|✔️||
51
51
|API|✔️|✔️||
@@ -54,7 +54,7 @@ In addition to a new set of features, custom question answering provides many te
54
54
55
55
## Pricing
56
56
57
-
When you're looking at migrating to custom question answering, please consider the following:
57
+
When you're looking at migrating to custom question answering, consider the following:
@@ -65,7 +65,7 @@ When you're looking at migrating to custom question answering, please consider t
65
65
66
66
- Users may select a higher tier with higher capacity, which will impact overall price they pay. It doesn’t impact the price on language component of custom question answering.
67
67
68
-
-“Text Records” in custom question answering features refers to the query submitted by the user to the runtime, and it's a concept common to all features within Language service. Sometimes a query may have more text records when the query length is higher.
68
+
-"Text Records" in custom question answering features refers to the query submitted by the user to the runtime, and it's a concept common to all features within Language service. Sometimes a query may have more text records when the query length is higher.
69
69
70
70
**Example price estimations**
71
71
@@ -84,7 +84,7 @@ The [Azure pricing calculator](https://azure.microsoft.com/pricing/calculator/)
84
84
85
85
## Simplified Provisioning and Development Experience
86
86
87
-
With the Language service, QnA Maker customers now benefit from a single service that provides Text Analytics, LUIS and custom question answering as features of the language resource. The Language service provides:
87
+
With the Language service, QnA Maker customers now benefit from a single service that provides Text Analytics, LUIS, and custom question answering as features of the language resource. The Language service provides:
88
88
89
89
- One Language resource to access all above capabilities
90
90
- A single pane of authoring experience across capabilities
@@ -93,13 +93,13 @@ With the Language service, QnA Maker customers now benefit from a single service
93
93
94
94
## Migration Phases
95
95
96
-
If you or your organization have applications in development or production that use QnA Maker, you should update them to use custom question answering as soon as possible. See the following links for available APIs, SDKs, Bot SDKs and code samples.
96
+
If you or your organization have applications in development or production that use QnA Maker, you should update them to use custom question answering as soon as possible. See the following links for available APIs, SDKs, Bot SDKs, and code samples.
97
97
98
98
Following are the broad migration phases to consider:
99
99
100
100

101
101
102
-
Additional links which can help you're given below:
@@ -110,10 +110,10 @@ Additional links which can help you're given below:
110
110
This topic compares two hypothetical scenarios when migrating from QnA Maker to custom question answering. These scenarios can help you to determine the right set of migration steps to execute for the given scenario.
111
111
112
112
> [!NOTE]
113
-
> An attempt has been made to ensure these scenarios are representative of real customer migrations, however, individual customer scenarios will of course differ. Also, this article doesn't include pricing details. Visit the [pricing](https://azure.microsoft.com/pricing/details/cognitive-services/language-service/) page for more information.
113
+
> An attempt has been made to ensure these scenarios are representative of real customer migrations, however, individual customer scenarios differ. Also, this article doesn't include pricing details. Visit the [pricing](https://azure.microsoft.com/pricing/details/cognitive-services/language-service/) page for more information.
114
114
115
115
> [!IMPORTANT]
116
-
> Each custom question answering project is equivalent to a knowledge base in QnA Maker. Resource level settings such as Role-based access control (RBAC) are not migrated to the new resource. These resource level settings would have to be reconfigured for the language resource post migration. You'll also need to [re-enable analytics](analytics.md) for the language resource.
116
+
> Each custom question answering project is equivalent to a knowledge base in QnA Maker. Resource level settings such as Role-based access control (RBAC) aren't migrated to the new resource. These resource level settings would have to be reconfigured for the language resource post migration. You'll also need to [re-enable analytics](analytics.md) for the language resource.
117
117
118
118
### Migration scenario 1: No custom authoring portal
119
119
@@ -139,11 +139,11 @@ Here are some [detailed steps](migrate-qnamaker.md) on migration scenario 1.
139
139
140
140
### Migration scenario 2
141
141
142
-
In this migration scenario, the customer may have created their own authoring frontend leveraging the QnA Maker authoring APIs or QnA Maker SDKs.
142
+
In this migration scenario, the customer may have created their own authoring frontend using the QnA Maker authoring APIs or QnA Maker SDKs.
143
143
144
144
They should perform these steps required for migration of SDKs:
145
145
146
-
This [SDK Migration Guide](https://github.com/Azure/azure-sdk-for-net/blob/Azure.AI.Language.QuestionAnswering_1.1.0-beta.1/sdk/cognitivelanguage/Azure.AI.Language.QuestionAnswering/MigrationGuide.md) is intended to assist in the migration to the new custom question answering client library, [Azure.AI.Language.QuestionAnswering](https://www.nuget.org/packages/Azure.AI.Language.QuestionAnswering), from the old one, [Microsoft.Azure.CognitiveServices.Knowledge.QnAMaker](https://www.nuget.org/packages/Microsoft.Azure.CognitiveServices.Knowledge.QnAMaker). It will focus on side-by-side comparisons for similar operations between the two packages.
146
+
This [SDK Migration Guide](https://github.com/Azure/azure-sdk-for-net/blob/Azure.AI.Language.QuestionAnswering_1.1.0-beta.1/sdk/cognitivelanguage/Azure.AI.Language.QuestionAnswering/MigrationGuide.md) is intended to help the migration to the new custom question answering client library, [Azure.AI.Language.QuestionAnswering](https://www.nuget.org/packages/Azure.AI.Language.QuestionAnswering), from the old one, [Microsoft.Azure.CognitiveServices.Knowledge.QnAMaker](https://www.nuget.org/packages/Microsoft.Azure.CognitiveServices.Knowledge.QnAMaker). It will focus on side-by-side comparisons for similar operations between the two packages.
147
147
148
148
They should perform the steps required for migration of Knowledge bases to the new Project within Language resource.
149
149
@@ -165,12 +165,12 @@ Here you can find some code samples: [Sample 1](https://github.com/microsoft/Bot
165
165
166
166
Here are [detailed steps on migration scenario 2](https://github.com/Azure/azure-sdk-for-net/blob/Azure.AI.Language.QuestionAnswering_1.1.0-beta.1/sdk/cognitivelanguage/Azure.AI.Language.QuestionAnswering/MigrationGuide.md)
167
167
168
-
Learn more about the [pre-built API](../../../QnAMaker/How-To/using-prebuilt-api.md)
168
+
Learn more about the [prebuilt API](../../../QnAMaker/How-To/using-prebuilt-api.md)
169
169
170
170
Learn more about the [custom question answering Get Answers REST API](/rest/api/questionanswering/question-answering/get-answers)
171
171
172
172
## Migration steps
173
173
174
-
Please note that some of these steps are needed depending on the customers existing architecture. Kindly look at migration phases given above for getting more clarity on which steps are needed by you for migration.
174
+
Note that some of these steps are needed depending on the customers existing architecture. Kindly look at migration phases given above for getting more clarity on which steps are needed by you for migration.
175
175
176
176

Copy file name to clipboardExpand all lines: articles/ai-services/language-service/text-analytics-for-health/how-to/call-api.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -36,12 +36,12 @@ The Text Analytics for health supports English in addition to multiple languages
36
36
37
37
## Submitting data
38
38
39
-
To send an API request, you will need your Language resource endpoint and key.
39
+
To send an API request, you need your Language resource endpoint and key.
40
40
41
41
> [!NOTE]
42
-
> You can find the key and endpoint for your Language resource on the Azure portal. They will be located on the resource's **Key and endpoint** page, under **resource management**.
42
+
> You can find the key and endpoint for your Language resource on the Azure portal. They are located on the resource's **Key and endpoint** page, under **resource management**.
43
43
44
-
Analysis is performed upon receipt of the request. If you send a request using the REST API or client library, the results will be returned asynchronously. If you're using the Docker container, they will be returned synchronously.
44
+
Analysis is performed upon receipt of the request. If you send a request using the REST API or client library, the results are returned asynchronously. If you're using the Docker container, they are returned synchronously.
0 commit comments