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/cognitive-services/LUIS/luis-boundaries.md
+30-23Lines changed: 30 additions & 23 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,16 +1,8 @@
1
1
---
2
2
title: Limits - LUIS
3
-
titleSuffix: Azure Cognitive Services
4
3
description: This article contains the known limits of Azure Cognitive Services Language Understanding (LUIS). LUIS has several boundary areas. Model boundary controls intents, entities, and features in LUIS. Quota limits based on key type. Keyboard combination controls the LUIS website.
5
-
services: cognitive-services
6
-
author: diberry
7
-
manager: nitinme
8
-
ms.service: cognitive-services
9
-
ms.subservice: language-understanding
10
4
ms.topic: reference
11
-
ms.date: 11/07/2019
12
-
ms.author: diberry
13
-
ms.custom: seodec18
5
+
ms.date: 04/02/2020
14
6
---
15
7
# Boundaries for your LUIS model and keys
16
8
LUIS has several boundary areas. The first is the [model boundary](#model-boundaries), which controls intents, entities, and features in LUIS. The second area is [quota limits](#key-limits) based on key type. A third area of boundaries is the [keyboard combination](#keyboard-controls) for controlling the LUIS website. A fourth area is the [world region mapping](luis-reference-regions.md) between the LUIS authoring website and the LUIS [endpoint](luis-glossary.md#endpoint) APIs.
@@ -34,7 +26,7 @@ If your app exceeds the LUIS model limits and boundaries, consider using a [LUIS
34
26
|[Preview - Dynamic list entities](https://aka.ms/luis-api-v3-doc#dynamic-lists-passed-in-at-prediction-time)|2 lists of ~1k per query prediction endpoint request|
35
27
|[Patterns](luis-concept-patterns.md)|500 patterns per application.<br>Maximum length of pattern is 400 characters.<br>3 Pattern.any entities per pattern<br>Maximum of 2 nested optional texts in pattern|
36
28
|[Pattern.any](./luis-concept-entity-types.md)|100 per application, 3 pattern.any entities per pattern |
37
-
|[Phrase list][phrase-list]|500 phrase lists. 10 global phrase lists due to the model as a feature limit. Non-interchangeable phraselist has max of 5,000 phrases. Interchangeable Phraselist has max of 50,000 phrases. Maximum number of total phrases per application of 500,000 phrases.|
29
+
|[Phrase list][phrase-list]|500 phrase lists. 10 global phrase lists due to the model as a feature limit. Non-interchangeable phrase list has max of 5,000 phrases. Interchangeable phrase list has max of 50,000 phrases. Maximum number of total phrases per application of 500,000 phrases.|
38
30
|[Prebuilt entities](./luis-prebuilt-entities.md)| no limit|
39
31
|[Regular expression entities](./luis-concept-entity-types.md)|20 entities<br>500 character max. per regular expression entity pattern|
40
32
|[Roles](luis-concept-roles.md)|300 roles per application. 10 roles per entity|
@@ -71,26 +63,41 @@ Do not use the following characters in the following names.
71
63
|Intent, entity, and role names|`:`<br>`$` <br> `&`|
Language Understand has separate keys, one type for authoring, and one type for querying the prediction endpoint. To learn more about the differences between key types, see [Authoring and query prediction endpoint keys in LUIS](luis-concept-keys.md).
68
+
Language Understand has separate resources, one type for authoring, and one type for querying the prediction endpoint. To learn more about the differences between key types, see [Authoring and query prediction endpoint keys in LUIS](luis-concept-keys.md).
77
69
78
70
<aname="key-limits"></a>
79
71
80
-
##Resource key limits
72
+
### Authoring resource limits
81
73
82
-
The resource keys have different limits for authoring and endpoint. The LUIS prediction query endpoint key is only valid for endpoint queries.
74
+
Use the _kind_, `LUIS.Authoring`, when filtering resources in the Azure portal. LUIS limits 500 applications per Azure authoring resource.
83
75
84
-
* 500 applications per Azure authoring resource
76
+
|Authoring resource|Authoring TPS|
77
+
|--|--|
78
+
|Starter|1 million/month, 5/second|
79
+
|F0 - Free tier |1 million/month, 5/second|
80
+
81
+
* TPS = Transactions per second
82
+
83
+
[Learn more about pricing.][pricing]
84
+
85
+
### Query prediction resource limits
86
+
87
+
Use the _kind_, `LUIS`, when filtering resources in the Azure portal.The LUIS query prediction endpoint resource, used on the runtime, is only valid for endpoint queries.
88
+
89
+
|Query Prediction resource|Query TPS|
90
+
|--|--|
91
+
|F0 - Free tier |10 thousand/month, 5/second|
92
+
|S0 - Standard tier|50/second|
93
+
94
+
### Sentiment analysis
95
+
96
+
[Sentiment analysis integration](luis-how-to-publish-app.md#enable-sentiment-analysis), which provides sentiment information, is provided without requiring another Azure resource.
97
+
98
+
### Speech integration
85
99
86
-
|Key|Authoring|Endpoint|Purpose|
87
-
|--|--|--|--|
88
-
|Starter|1 million/month, 5/second|1 thousand/month, 5/second|Authoring your LUIS app|
89
-
|F0 - Free tier |1 million/month, 5/second|10 thousand/month, 5/second|Querying your LUIS endpoint|
90
-
|S0 - Basic tier|-|50/second|Querying your LUIS endpoint|
91
-
|S0 - Standard tier|-|50/second|Querying your LUIS endpoint|
92
-
|[Sentiment analysis integration](luis-how-to-publish-app.md#enable-sentiment-analysis)|-|-|Adding sentiment information including key phrase data extraction is provided without requiring another Azure resource. |
93
-
|[Speech integration](../speech-service/how-to-recognize-intents-from-speech-csharp.md)|-|1 thousand endpoint requests per unit cost|Convert spoken utterance to text utterance and return LUIS results|
100
+
[Speech integration](../speech-service/how-to-recognize-intents-from-speech-csharp.md) provides 1 thousand endpoint requests per unit cost.
0 commit comments