Samples for the Language Understanding Intelligent Service (LUIS)

License: MIT License

C# 31.68% HTML 12.13% JavaScript 25.39% Go 3.47% Java 7.80% PHP 2.95% Python 4.12% Ruby 2.02% Dockerfile 2.81% Batchfile 7.38% ASP.NET 0.02% Shell 0.23%

cognitive-services-language-understanding's Introduction

page_type

languages

products

description

urlFragment

sample

csharp

javascript

html

java

python

azure

LUIS allows your application to understand what a person wants in their own words.

cognitive-services-language-understanding

Language Understanding (LUIS) Samples

Welcome to the Language Understanding (LUIS) samples repository. LUIS allows your application to understand what a person wants in their own words. LUIS uses machine learning to allow developers to build applications that can receive user input in natural language and extract meaning from it.

Create your Azure LUIS service

Use the Deploy to Azure button to quickly create an Azure LUIS service. You get one free LUIS service per account. The free service has a sku of F0. The basic tier has a sku of S0.

Examples by language

Example	CSharp	Java	Node.js	Javascript	Python	JSON	GO
Create and customize a LUIS app (Authoring)	✔
Predict user utterances (Runtime)	REST, SDK	REST	REST		REST		REST
Build app programmatically	REST, SDK		✔
Upload utterances from query log			✔
Upload utterances from exported app			✔
Quickstarts: Change model
Quickstarts: Analyze text
Azure function to LUIS endpoint	✔
Backup all apps in Subscription			✔
Add list entity			✔
*Notes app sample	✔
App model definition - Bookflight						✔
App model definition - Colors						✔
App model definition - IoT						✔
Phrase lists						✔
Bing Spell Check				✔
Azure function with application insights	✔
Download query log asynchronously			✔
Get region from app ID and subscription key	✔		✔
*Bot Integration sample - hotel finder	✔		✔
Bot Integration sample - HomeAutomation	✔		✔
Bot Integration sample - HomeAutomation & Application Insights	✔		✔
Bot Integration sample - Study Bot - Csharp, Node	✔		✔

* = example demonstrates complete cycle: create, train, publish, query

Examples by usage

Example	Demonstrates
Create and customize a LUIS app (Authoring)	Uses the LUIS SDK to create then customize an app
Predict user utterances (Runtime)	Uses the LUIS SDK to show utterance relevancy and intent scores
Build app programmatically	Authoring API
Upload utterances from query log	Authoring API
Upload utterances from exported app	Authoring API
Add an utterance to app model	Authoring API
Send utterance to endpoint	Endpoint API, Public app
Azure function to LUIS endpoint	Endpoint API
Backup all apps in Subscription	Authoring API
Notes app sample	Create-Train-Publish-Query, Prebuilt domain
App model definition - Bookflight	Hierarchical entity, Composite entity, List entity, datetimeV2 prebuilt entity, number prebuilt entity, upload labeled utterance
App model definition - Colors	Phrase list feature
App model definition - IoT	Prebuilt domain
Phrase lists	Phrase list feature, Hierarchical entity, datetimeV2 prebuilt entity, number prebuilt entity
Bing Spell Check	Public App
Azure function with application insights	Azure function, Application Insights
Add list entity	List entity, train, query
Download query log asynchronously	Authoring API
Bot Integration sample - hotel finder	Bot Framework SDK, Create-Train-Publish-Query
Bot Integration sample - HomeAutomation	Web app bot
Bot Integration sample - HomeAutomation & Application Insights	Web app bot, Application Insights
Bot Integration sample - Study Bot - Csharp, Node	Web app bot that integrates LUIS, QnA Maker, Bing Spell Check, and Speech Service

Interactive app

Ask LUIS to turn on the lights in this interactive demonstration.

Healthbot

Tell the Contoso Health bot where you are injured and the bot will recommend remedies.

Intelligent Kiosk

The open-source Intelligent Kiosk Sample version is a collection of apps showcasing workflows and experiences built on top of the Microsoft Cognitive Services. Most of the experiences are hands-free and autonomous, using the human faces in front of a web camera as the main form of input (thus the word "kiosk" in the name).

Install the currently supported Intelligent Kiosk as a Windows 10 app and try out the various apps inside the kiosk, including apps with LUIS.

References

LUIS Docs
FAQs, Regions, limits, Supported languages

APIs

last updated Oct 2019

Rest API ref docs

Version	Type	By route
V3 stable	Prediction
V3 preview	Authoring	Routes
V2 stable	Prediction
V2 stable	Authoring	Routes

SDKs

last updated Feb 13, 2019

Language	Package Manager	Samples	Reference Documentation
C#	NuGet - authoring NuGet - runtime	Samples	Docs
Go	SDK - authoring SDK - runtime	-	Docs
Java	Maven - authoring Maven - runtime	Samples	Docs
Javascript	NPM - authoring NPM - runtime	Samples
Python	PIP	Samples	Docs

Azure REST API

Azure CLI

Cognitive Services

Azure RM Powershell

Cognitive Services

Common HTTP response codes

Http codes

Bots

Bot Framework
BotBuilder v4, Nodejs, .Net. Coming soon: Python & Java
BotBuilder v4 LUIS libraries: Nodejs NPM package, .Net NuGet package
Bot Builder Samples
Bot Builder Tools

Related Services

Dependencies

Recognizers-Text for prebuilt entities

Azure status

Regional availability: LUIS is part of the AI and Machine Learning section.

Videos

updated Dec 15, 2018

Containers

Video demonstration of LUIS container.

//BUILD 2018

LUIS with Bot framework Blog

blog.botframework.com

Courses including LUIS

Mixed reality: MR and Azure 303: Natural language understanding

Related Microsoft Projects

Prebuilt entity recognizer
Azure Code Samples for LUIS
Universal Language Intelligence Service - Nodejs: A wrapper for the Microsoft LUIS cognitive that provides universal language support (after training) using the Bing Translate API
Microsoft Cognitive Services control for Microsoft Bot Builder - C# & Nodejs: The cognitive services control makes consuming different Microsoft Cognitive Services easy for bots developed using Microsoft Bot Builder SDK. The control is available for C# and Node.js SDKs.
Activate Azure with Intelligent Apps - C#: Fabrikam Investment Bank Customer Service uses LUIS
LUIS Console Application Sample - C#
Adaptive Cards
Octobot from the Sandbox
Microsoft Health Bot

Searching docs

Azure RSS for 'LUIS'

Community Projects

If you find an open-source project or sample using LUIS, submit a PR for the community-projects.md file.

Prediction Routes v3 Stable

/apps/{appId}/slots/{slotName}/predict [get,post]
/apps/{appId}/versions/{versionId}/predict [get,post]

Authoring Routes v3 Preview

/apps/ [post,get]
/apps/assistants [get]
/apps/cultures [get]
/apps/customprebuiltdomains [get,post]
/apps/customprebuiltdomains/{culture} [get]
/apps/domains [get]
/apps/import [post]
/apps/usagescenarios [get]
/apps/{appId} [get,put,delete]
/apps/{appId}/azureaccounts [post,get,delete]
/apps/{appId}/endpoints [get]
/apps/{appId}/permissions [get,post,delete,put]
/apps/{appId}/publish [post]
/apps/{appId}/publishsettings [get,put]
/apps/{appId}/querylogs [get]
/apps/{appId}/settings [get,put]
/apps/{appId}/versions [get]
/apps/{appId}/versions/import [post]
/apps/{appId}/versions/{versionId}/ [get,put,delete]
/apps/{appId}/versions/{versionId}/clone [post]
/apps/{appId}/versions/{versionId}/closedlists [get,post]
/apps/{appId}/versions/{versionId}/closedlists/{clEntityId} [get,put,patch,delete]
/apps/{appId}/versions/{versionId}/closedlists/{clEntityId}/sublists [post]
/apps/{appId}/versions/{versionId}/closedlists/{clEntityId}/sublists/{subListId} [delete,put]
/apps/{appId}/versions/{versionId}/closedlists/{entityId}/roles [get,post]
/apps/{appId}/versions/{versionId}/closedlists/{entityId}/roles/{roleId} [get,put,delete]
/apps/{appId}/versions/{versionId}/compositeentities [get]
/apps/{appId}/versions/{versionId}/compositeentities/{cEntityId} [get,put,delete]
/apps/{appId}/versions/{versionId}/compositeentities/{cEntityId}/children [post]
/apps/{appId}/versions/{versionId}/compositeentities/{cEntityId}/children/{cChildId} [delete]
/apps/{appId}/versions/{versionId}/compositeentities/{cEntityId}/roles [get,post]
/apps/{appId}/versions/{versionId}/compositeentities/{cEntityId}/roles/{roleId} [get,put,delete]
/apps/{appId}/versions/{versionId}/customprebuiltdomains [post]
/apps/{appId}/versions/{versionId}/customprebuiltdomains/{domainName} [delete]
/apps/{appId}/versions/{versionId}/customprebuiltentities [post,get]
/apps/{appId}/versions/{versionId}/customprebuiltentities/{entityId}/roles [get,post]
/apps/{appId}/versions/{versionId}/customprebuiltentities/{entityId}/roles/{roleId} [get,put,delete]
/apps/{appId}/versions/{versionId}/customprebuiltintents [post,get]
/apps/{appId}/versions/{versionId}/customprebuiltmodels [get]
/apps/{appId}/versions/{versionId}/entities [post,get]
/apps/{appId}/versions/{versionId}/entities/{entityId} [get,delete,patch]
/apps/{appId}/versions/{versionId}/entities/{entityId}/children [post]
/apps/{appId}/versions/{versionId}/entities/{entityId}/roles [get,post]
/apps/{appId}/versions/{versionId}/entities/{entityId}/roles/{roleId} [get,put,delete]
/apps/{appId}/versions/{versionId}/entities/{entityId}/suggest [get]
/apps/{appId}/versions/{versionId}/example [post]
/apps/{appId}/versions/{versionId}/examples [post,get]
/apps/{appId}/versions/{versionId}/examples/{exampleId} [delete]
/apps/{appId}/versions/{versionId}/export [get]
/apps/{appId}/versions/{versionId}/features [get]
/apps/{appId}/versions/{versionId}/hierarchicalentities [get]
/apps/{appId}/versions/{versionId}/hierarchicalentities/{hEntityId} [get,patch,delete]
/apps/{appId}/versions/{versionId}/hierarchicalentities/{hEntityId}/children/{hChildId} [get,patch,delete]
/apps/{appId}/versions/{versionId}/hierarchicalentities/{hEntityId}/roles [get,post]
/apps/{appId}/versions/{versionId}/hierarchicalentities/{hEntityId}/roles/{roleId} [get,put,delete]
/apps/{appId}/versions/{versionId}/intents [post,get]
/apps/{appId}/versions/{versionId}/intents/{intentId} [get,put,delete]
/apps/{appId}/versions/{versionId}/intents/{intentId}/patternrules [get]
/apps/{appId}/versions/{versionId}/intents/{intentId}/suggest [get]
/apps/{appId}/versions/{versionId}/listprebuilts [get]
/apps/{appId}/versions/{versionId}/models [get]
/apps/{appId}/versions/{versionId}/models/{modelId}/examples [get]
/apps/{appId}/versions/{versionId}/patternanyentities [get,post]
/apps/{appId}/versions/{versionId}/patternanyentities/{entityId} [get,put,delete]
/apps/{appId}/versions/{versionId}/patternanyentities/{entityId}/explicitlist [get,post]
/apps/{appId}/versions/{versionId}/patternanyentities/{entityId}/explicitlist/{itemId} [get,put,delete]
/apps/{appId}/versions/{versionId}/patternanyentities/{entityId}/roles [get,post]
/apps/{appId}/versions/{versionId}/patternanyentities/{entityId}/roles/{roleId} [get,put,delete]
/apps/{appId}/versions/{versionId}/patternrule [post]
/apps/{appId}/versions/{versionId}/patternrules [get,put,post,delete]
/apps/{appId}/versions/{versionId}/patternrules/{patternId} [put,delete]
/apps/{appId}/versions/{versionId}/patterns [post,get]
/apps/{appId}/versions/{versionId}/patterns/{patternId} [get,put,delete]
/apps/{appId}/versions/{versionId}/phraselists [post,get]
/apps/{appId}/versions/{versionId}/phraselists/{phraselistId} [get,put,delete]
/apps/{appId}/versions/{versionId}/prebuilts [post,get]
/apps/{appId}/versions/{versionId}/prebuilts/{entityId}/roles [get,post]
/apps/{appId}/versions/{versionId}/prebuilts/{entityId}/roles/{roleId} [get,put,delete]
/apps/{appId}/versions/{versionId}/prebuilts/{prebuiltId} [get,delete]
/apps/{appId}/versions/{versionId}/regexentities [get,post]
/apps/{appId}/versions/{versionId}/regexentities/{entityId}/roles [get,post]
/apps/{appId}/versions/{versionId}/regexentities/{entityId}/roles/{roleId} [get,put,delete]
/apps/{appId}/versions/{versionId}/regexentities/{regexEntityId} [get,put,delete]
/apps/{appId}/versions/{versionId}/settings [get,put]
/apps/{appId}/versions/{versionId}/suggest [delete]
/apps/{appId}/versions/{versionId}/train [post,get]
/azureaccounts [get]
/package/{appId}/slot/{slotName}/gzip [get]
/package/{appId}/versions/{versionId}/gzip [get]

Authoring Routes v2 Stable

/apps/ [post,get]
/apps/assistants [get]
/apps/cultures [get]
/apps/customprebuiltdomains [post,get]
/apps/customprebuiltdomains/{culture} [get]
/apps/domains [get]
/apps/import [post]
/apps/usagescenarios [get]
/apps/{appId} [delete,get,put]
/apps/{appId}/azureaccounts [post,get,delete]
/apps/{appId}/endpoints [get]
/apps/{appId}/permissions [post,get,delete,put]
/apps/{appId}/publish [post]
/apps/{appId}/publishsettings [get,put]
/apps/{appId}/querylogs/ [get]
/apps/{appId}/querylogsasync/ [get,post]
/apps/{appId}/settings [get,put]
/apps/{appId}/versions [get]
/apps/{appId}/versions/import [post]
/apps/{appId}/versions/{versionId}/ [delete,get,put]
/apps/{appId}/versions/{versionId}/assignedkey [put,get]
/apps/{appId}/versions/{versionId}/clone [post]
/apps/{appId}/versions/{versionId}/closedlists [post,get]
/apps/{appId}/versions/{versionId}/closedlists/{clEntityId} [delete,get,patch,put]
/apps/{appId}/versions/{versionId}/closedlists/{clEntityId}/sublists [post]
/apps/{appId}/versions/{versionId}/closedlists/{clEntityId}/sublists/{subListId} [delete,put]
/apps/{appId}/versions/{versionId}/closedlists/{entityId}/roles [post,get]
/apps/{appId}/versions/{versionId}/closedlists/{entityId}/roles/{roleId} [delete,get,put]
/apps/{appId}/versions/{versionId}/compositeentities [post,get]
/apps/{appId}/versions/{versionId}/compositeentities/{cEntityId} [delete,get,put]
/apps/{appId}/versions/{versionId}/compositeentities/{cEntityId}/children [post]
/apps/{appId}/versions/{versionId}/compositeentities/{cEntityId}/children/{cChildId} [delete]
/apps/{appId}/versions/{versionId}/compositeentities/{cEntityId}/roles [post,get]
/apps/{appId}/versions/{versionId}/compositeentities/{cEntityId}/roles/{roleId} [delete,get,put]
/apps/{appId}/versions/{versionId}/customprebuiltdomains [post]
/apps/{appId}/versions/{versionId}/customprebuiltdomains/{domainName} [delete]
/apps/{appId}/versions/{versionId}/customprebuiltentities [post,get]
/apps/{appId}/versions/{versionId}/customprebuiltentities/{entityId}/roles [post,get]
/apps/{appId}/versions/{versionId}/customprebuiltentities/{entityId}/roles/{roleId} [delete,get,put]
/apps/{appId}/versions/{versionId}/customprebuiltintents [post,get]
/apps/{appId}/versions/{versionId}/customprebuiltmodels [get]
/apps/{appId}/versions/{versionId}/entities [post,get]
/apps/{appId}/versions/{versionId}/entities/{entityId} [delete,get,put]
/apps/{appId}/versions/{versionId}/entities/{entityId}/roles [post,get]
/apps/{appId}/versions/{versionId}/entities/{entityId}/roles/{roleId} [delete,get,put]
/apps/{appId}/versions/{versionId}/entities/{entityId}/suggest [get]
/apps/{appId}/versions/{versionId}/example [post]
/apps/{appId}/versions/{versionId}/examples [post,get]
/apps/{appId}/versions/{versionId}/examples/{exampleId} [delete]
/apps/{appId}/versions/{versionId}/export [get]
/apps/{appId}/versions/{versionId}/externalKeys [get,put]
/apps/{appId}/versions/{versionId}/externalKeys/{keyType} [delete]
/apps/{appId}/versions/{versionId}/features [get]
/apps/{appId}/versions/{versionId}/hierarchicalentities [post,get]
/apps/{appId}/versions/{versionId}/hierarchicalentities/{hEntityId} [delete,get,put]
/apps/{appId}/versions/{versionId}/hierarchicalentities/{hEntityId}/children [post]
/apps/{appId}/versions/{versionId}/hierarchicalentities/{hEntityId}/children/{hChildId} [delete,get,put]
/apps/{appId}/versions/{versionId}/hierarchicalentities/{hEntityId}/roles [post,get]
/apps/{appId}/versions/{versionId}/hierarchicalentities/{hEntityId}/roles/{roleId} [delete,get,put]
/apps/{appId}/versions/{versionId}/intents [post,get]
/apps/{appId}/versions/{versionId}/intents/{intentId} [delete,get,put]
/apps/{appId}/versions/{versionId}/intents/{intentId}/patternrules [get]
/apps/{appId}/versions/{versionId}/intents/{intentId}/suggest [get]
/apps/{appId}/versions/{versionId}/listprebuilts [get]
/apps/{appId}/versions/{versionId}/models [get]
/apps/{appId}/versions/{versionId}/patternanyentities [post,get]
/apps/{appId}/versions/{versionId}/patternanyentities/{entityId} [delete,get,put]
/apps/{appId}/versions/{versionId}/patternanyentities/{entityId}/explicitlist [post,get]
/apps/{appId}/versions/{versionId}/patternanyentities/{entityId}/explicitlist/{itemId} [delete,get,put]
/apps/{appId}/versions/{versionId}/patternanyentities/{entityId}/roles [post,get]
/apps/{appId}/versions/{versionId}/patternanyentities/{entityId}/roles/{roleId} [delete,get,put]
/apps/{appId}/versions/{versionId}/patternrule [post]
/apps/{appId}/versions/{versionId}/patternrules [post,delete,get,put]
/apps/{appId}/versions/{versionId}/patternrules/{patternId} [delete,put]
/apps/{appId}/versions/{versionId}/patterns [post,get]
/apps/{appId}/versions/{versionId}/patterns/{patternId} [delete,get,put]
/apps/{appId}/versions/{versionId}/phraselists [post,get]
/apps/{appId}/versions/{versionId}/phraselists/{phraselistId} [delete,get,put]
/apps/{appId}/versions/{versionId}/prebuilts [post,get]
/apps/{appId}/versions/{versionId}/prebuilts/{entityId}/roles [post,get]
/apps/{appId}/versions/{versionId}/prebuilts/{entityId}/roles/{roleId} [delete,get,put]
/apps/{appId}/versions/{versionId}/prebuilts/{prebuiltId} [delete,get]
/apps/{appId}/versions/{versionId}/regexentities [post,get]
/apps/{appId}/versions/{versionId}/regexentities/{entityId}/roles [post,get]
/apps/{appId}/versions/{versionId}/regexentities/{entityId}/roles/{roleId} [delete,get,put]
/apps/{appId}/versions/{versionId}/regexentities/{regexEntityId} [delete,get,put]
/apps/{appId}/versions/{versionId}/settings [get,put]
/apps/{appId}/versions/{versionId}/suggest [delete]
/apps/{appId}/versions/{versionId}/train [get,post]
/azureaccounts [get]
/externalKeys [post,get]
/externalKeys/{externalKeyValue} [delete]
/package/{appId}/slot/{slotName}/gzip [get]
/package/{appId}/versions/{versionId}/gzip [get]
/programmatickey [put]
/subscriptions [post,get,put]
/subscriptions/{subscriptionKey} [delete]

Route map generated with swagger-tools.

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.microsoft.com.

When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information, see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

cognitive-services-language-understanding's People

Contributors

Stargazers

Watchers

Forkers

eaglezzb gauravanandreviewer vishalnagarar barrabyte rekha-balan vivekbrahmadandi johnancelet ai-natural-language-processing-lab rmundhe nicolehaugen wjones30309 zitas samirshaik sumanthpopuri ritekr winstonchang mykolapavlenko elygod chocho13 danielichida josedbaez zayantharani baopanda joangenis devongoldsmith hopeminchen praneet22 pravinacg vishnuvimala bubpa victorhkng ufukhurriyetoglu jimmyganesh meicen-tw bochaton nadiamkh divysin wolkerzheng fjcastilloc link2rn briansalato nazaranalytics gunagg iamsapple ajaypaulfrancis clopezam ypgakhar69 yonet willgab tianliang0038 ebluejade ievangelist siddhantmd jgouda amrattia mewa1024 m1050735 jingyidu dachinzo emanafi marvinboris xchancex splumber bennyhou sarvang008 prskriti andyarroyo5 ta-matsuura datacon10 agustingarcia210988 emmagarland srinidhianantharamu alishahusain attackgithub mrpuel yingjiangjiao chrstphrmack rosaistdiebeste radparde11 trammai chaitanyamadala-isd raphaelsegalla dragoscostin jyotsnaravi amritlalsahu5 stormywine aayushibeniwal johnau4 ericli-5230 skydev2020 samzhang01 aditya2008 xctpro fsexchangerrates ironcev-forks sravyanu-kore lucvo dip10du anandabasak glaucia86

cognitive-services-language-understanding's Issues

LUIS SDK azure vs container implementation

Is your feature request related to a problem? Please describe.
When using the container version, you need to access web service. SDK Abstraction don't work as sdk URLs differ in webservice endpoints...
Azure-Samples/cognitive-services-speech-sdk#424 (comment)

The problem here is that prediction results are not the same...

Exemple in code :
Task pred;

            if (_config.UseLocalServices)
            {
                pred = GetPredictionFromEndpointAsync(_config.LuisAPIKey, _config.LuisContainerUrl, _config.LuisAppId, _config.LuisSlotName, question.ToLowerInvariant());
            }
            else
            {
                IList<DynamicList> dynamicLists = _luisFeedDynamicListService.LuisEntries.Select(e => new DynamicList(e.Key, RequestListExtensions.FromLuisEntries(e.Value))).ToList();
                var predictionRequest = new PredictionRequest(question.ToLowerInvariant(), null, null, dynamicLists);
               
                pred = _luisClient.Prediction.GetSlotPredictionAsync(
                   Guid.Parse(_config.LuisAppId),
                   slotName: _config.LuisSlotName,
                   predictionRequest,
                   verbose: true,
                   showAllIntents: true,
                   log: true);
            }

Describe the solution you'd like
The proper solution would be to change only the enpoint like this:
Version Azure
_luisClient = new LUISRuntimeClient(new ApiKeyServiceClientCredentials(_config.LuisAPIKey))
{
Endpoint = _config.LuisHostRegion
};

Version container
_luisClient = new LUISRuntimeClient(new MockCredentials())
{
Endpoint = "http://localhost:5010"
};

How can you have exactly the same result from webservice ?

LUIS Authoring - New Phrase Lists are applied, but don't appear on screen (non-Global Phrase Lists)

Please provide us with the following information:

This issue is for a: (mark with an `x`)

- [x] bug report -> please search issues before submitting
- [ ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

Create a LUIS application on luis.ai with at least 100 Intents and 100 Features (non-Global Phrase Lists) on luis.ai website
Create a new Phrase List (non-Global)
Notice that the Phrase List appears on the list correctly
Refresh the page
Notice that the new Phrase List is not appearing anymore

Any log messages given by the failure

No logging messages, but 429 erros on the console all the time.

Expected/desired behavior

Since the Phrase List limit for Luis is 500, I should be able to create them normally. It's good to point out that the JSON file shows the Phrase Lists applied correctly to the intent, but it doesn't show on the screen. That blocks me from being able to work on the Luis app properly using the web version (luis.ai).

OS and Version?

Windows, MacOs

Versions

10 Pro, Mojave 10.14.6

Mention any other details that might be useful

Luis apps with a smaller number of intents and phrase lists will work normally. With larger apps, it seems it bugs somehow. Just by training the app will give me 429 errors on the console, which seems weird.

Thanks! We'll be in touch soon.

Review Endpoint Utterances- Cannot find an unlabeled query with the given text

Please provide us with the following information:

This issue is for a: (mark with an `x`)

- [ ] bug report -> please search issues before submitting
- [ ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

go to review endpoint utterances
try to accept or delete any utterance
displays error

Any log messages given by the failure

Uncaught (in promise) 400: BadArgument: Cannot find an unlabeled query with the given text.
at Object.handle (https://www.luis.ai/app.314c72959f3f3643f950.js:1:28902)
at Object.handle (https://www.luis.ai/app.314c72959f3f3643f950.js:1:28679)
at https://www.luis.ai/app.314c72959f3f3643f950.js:1:30640
at Generator.next ()
at https://www.luis.ai/vendors.314c72959f3f3643f950.js:31:1430
at new Promise ()
at l (https://www.luis.ai/vendors.314c72959f3f3643f950.js:31:1204)
at https://www.luis.ai/app.314c72959f3f3643f950.js:1:30581

Expected/desired behavior

Delete or accept the endpoint utterance at Review

OS and Version?

Windows 10.

Versions

Mention any other details that might be useful

Thanks! We'll be in touch soon.

LuisGen cannot create a C# class when json has sub entities.

Minimal steps to reproduce

Create Sub Entity Under Entity

Publish the LUIS App, Export the .json file
Use Luis gen to create a C# class using LUISGen {Your export json file} -cs {your C# file name}
You get below error.

Any log messages given by the failure

Unhandled Exception: System.ArgumentException: Can not convert Object to String. at Newtonsoft.Json.Linq.JToken.op_Explicit(JToken value) at System.Dynamic.UpdateDelegates.UpdateAndExecute1[T0,TRet](CallSite site, T0 arg0) at CallSite.Target(Closure , CallSite , Object ) at LUISGen.Utils.EntityApply(JObject entity, Action1 action) in D:\a\1\s\packages\LUISGen\src\Utils.cs:line 94
at System.Dynamic.UpdateDelegates.UpdateAndExecuteVoid5[T0,T1,T2,T3,T4](CallSite site, T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4)
at LUISGen.CSharp.Entities(Object app, Writer w) in D:\a\1\s\packages\LUISGen\src\CSharp.cs:line 161
at System.Dynamic.UpdateDelegates.UpdateAndExecuteVoid3[T0,T1,T2](CallSite site, T0 arg0, T1 arg1, T2 arg2)
at LUISGen.CSharp.Generate(String description, Object app, String className, String space, String outPath) in D:\a\1\s\packages\LUISGen\src\CSharp.cs:line 289
at System.Dynamic.UpdateDelegates.UpdateAndExecuteVoid6[T0,T1,T2,T3,T4,T5](CallSite site, T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4, T5 arg5)
at LUISGen.Program.Main(String[] args) in D:\a\1\s\packages\LUISGen\src\Program.cs:line 182`

Expected/desired behavior

The command must create a C# LUIS Recognizer class.

Versions

Microsoft.Bot.Builder.AI.Luis 4.11.1
Microsoft.Bot.Builder 4.11.1

I keep getting this error after deploying a trained model: Badrequest Corresponding activity ID

Please provide us with the following information:

This issue is for a: (mark with an `x`)

- [x ] bug report -> please search issues before submitting
- [ ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

Use the sample output run the endpoint
Here is the sample curl

curl -X POST "https://westus2.api.cognitive.microsoft.com/language/:analyze-conversations?projectName=OptumTestIVR&deploymentName=production&api-version=2021-11-01-preview" -H "Ocp-Apim-Subscription-Key: xxxxxxxxxx"  -H "Apim-Request-Id: xxxxxxxxxx" -H "Content-Type: application/json" -d "{\"verbose\":true,\"query\":\"YOUR_QUERY_HERE\",\"language\":\"QUERY_LANGUAGE_HERE\"}"

Technically I don't know what language is supposed to be or Query_language. I don't know if that is causing the error.

Any log messages given by the failure

the issue seems to be the language param. I don't know what else to put besides english or eng

{
    "error": {
        "code": "BadRequest",
        "message": "One or more errors occurred. Corresponding activity ID: ab2dc68a-d5c0-49f9-b621-c97a1f1ccb21.",
        "innerError": {
            "message": "Failed to call the Conversation project OptumTestIVR and deployment production.."
        }
    }
}

Expected/desired behavior

for it to work

OS and Version?

Windows 7, 8 or 10. Linux (which distribution). macOS (Yosemite? El Capitan? Sierra?)

Versions

Mention any other details that might be useful

Thanks! We'll be in touch soon.

Update sample to Bot Framework V4

Update sample of bot-integration-samples/hotel-finder to use Bot Framework V4. This repo is linked to from a primary documentation source so not appropriate to still be exclusively using an old version, especially given how much things have changed.

Broken links in "Examples by language" and "Examples by usage"

Several of the links in the live version of the landing page seem to be broken.

To reproduce:

Go to https://docs.microsoft.com/en-us/samples/azure-samples/cognitive-services-language-understanding/cognitive-services-language-understanding/
Select a link in the tables titled "Examples by language" or "Examples by usage". For example, the link labeled "Quickstarts: Change model".

Most of the links in those tables currently lead to 404 errors.

utternace normalisation c#

Are there any examples on how to turn on utterance normalisation in C# like on https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-utterance .
I am trying to do it in an Micorosoft chatbot using Azure bot services sdk v4.

Need deeper entity extraction information for list keys

Please provide us with the following information:

This issue is for a: (mark with an `x`)

- [ ] bug report -> please search issues before submitting
- [x ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

Run endpoint

Any log messages given by the failure

Expected/desired behavior

The output of the transaction as an example does not give the full entity information:
The different entities are within the category of AffirmENT but I can't resolve to them directly per the LIST. This is very different than LUIS.
A list key property would be ideal.

{
    "query": "no",
    "prediction": {
        "topIntent": "Affirmation_Prompt",
        "projectKind": "conversation",
        "intents": [
            {
                "category": "Affirmation_Prompt",
                "confidenceScore": 1
            }
        ],
        "entities": [
            {
                "category": "AffirmENT",
                "text": "no",
                "offset": 0,
                "length": 2,
                "confidenceScore": 1
            }
        ]
    }
}

OS and Version?

Windows 7, 8 or 10. Linux (which distribution). macOS (Yosemite? El Capitan? Sierra?)

Versions

Mention any other details that might be useful

Thanks! We'll be in touch soon.

Incorrect JSON Response

Please provide us with the following information:

We are extracting datetimev2 entities via LUIS api using prebuilt model. In the json response, we are not able to deserialiize it due to additional values being returned. For eg: "10D" is added without the correct format of the json response body.

This issue is for a: (mark with an `x`)

- [x] bug report -> please search issues before submitting
- [ ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

Submitted line - to extract datetimev2 entities
Mannauðslausnir - RMKT,$63.87,From Feb 28, 2021, 12:00 AM to Mar 21, 2021, 2:15 PM,2021 - Mannauðslausnir - RMKT - RMKT - 10D,6,858 Impressions,$63.87,2020 - AutoBoost - Post Engagement,$155.13,From Feb 28, 2021, 12:00 AM to Mar 21, 2021, 2:15 PM,2020 - AutoBoost - Post Engagement - IS,4,095 Impressions,$12.76,2020 - AutoBoost - Post Engagement - IS,8,270 Impressions,$24.13,2020 - AutoBoost - Post Engagement - IS,8,008 Impressions,$21.98,2020 - AutoBoost - Post Engagement - IS,6,277 Impressions

The json response for datetimev2 we got
[{ 'type': 'datetimerange', 'values': [{ 'timex': '(2021-02-28T00:00,2021-03-21T14:15,PT518H)', 'resolution': [{ 'start': '2021-02-28 00:00:00', 'end': '2021-03-21 14:15:00' }] }] }, '10D', { 'type': 'datetimerange', 'values': [{ 'timex': '(2021-02-28T00:00,2021-03-21T14:15,PT518H)', 'resolution': [{ 'start': '2021-02-28 00:00:00', 'end': '2021-03-21 14:15:00' }] }] } ]

Any log messages given by the failure

Expected/desired behavior

JSON response with correct format.

OS and Version?

Windows 7, 8 or 10. Linux (which distribution). macOS (Yosemite? El Capitan? Sierra?)

Versions

Microsoft.Azure.CognitiveServices.Language.LUIS.Runtime V3.0.0 nuget

Mention any other details that might be useful

Thanks! We'll be in touch soon.

Is bing spell check for integration with luis helpful with the dispatch pattern and is it useful or harmful to entity assurance?

An article here gave some caution to using the Bing spellchecker api for washing all of your user utterances into your bot channel.

Link to article here

Point being the entity could become unravled when the spellchecker is turned on? So if you have an obscure word style entity starblazingIT this might be reconstructed to star blazing IT. Thus harming the entity.

With that said the article was written in 2016 so perhaps this concern has been addressed but I can't find any documentation on it.

The documentation I did find on it gave an outlet for ignoring spelling mistakes and simply label utterances and the LUIS would learn proper spelling as well as typos... That is a loaded statement. What does that mean exactly and is luis really learning proper spelling or just adding the bad spellings in there as an alternative answer?

Because if that is the case then one would have to watch misspelled utterances and add in variations all of the time. Or would Luis overtime training learn that a particular word can have variations and be misspelled and to add that in with the correct intent model of utterances?

Here is a link to the article and quote below:

Ignore spelling mistakes
If you don't want to use the Bing Spell Check API v7 service, you can label utterances that have spelling mistakes so that LUIS can learn proper spelling as well as typos. This option requires more labeling effort than using a spell checker.

Overall what is the best practice of word misspelling correction for your luis chatbot application?

No LUIS authoring region within Canada

This issue is for a: Feature Request

- [ ] bug report -> please search issues before submitting
- [x] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Feature request description

Would it be possible to add a LUIS Authoring Environment in region within Canada.

Minimal steps to reproduce

The following documentation page shows no LUIS authoring environment hosted within Canada.

The westus is recommended for Canada, however that is not within Canada.

https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-reference-regions#feedback

Any log messages given by the failure

Not applicable

Expected/desired behavior

We should be able to select a LUIS authoring environment hosted within Canada.

OS and Version?

Not applicable

Mention any other details that might be useful

This is a major blocker for our product.

Regulatory requirements dictate that must host our product entirely within Canada.

During the pilot / prototype stage we're fine for testing within westus but this is a blocker for production launch.

Please advise.

Batch Transcription integration with LUIS

I have a requirement to do integration between the batch transcription and LUIS wherein I will pass the full transcriptions as such to LUIS and get the intent of the audio.

As far as I know we can pass the data for intent analysis to LUIS as a query which accepts only 500 characters.

So here comes the question is it possible to pass the full transcription from speech to text batch transcription API to LUIS for intent analysis or we have to feed the data in chunks to LUIS ?

If we feed the data in chunks how we will get the overall intent of the audio?

Please suggest on the best possible way to achieve this.

LUIS Programmatic APIs v2.0 returns error

This issue is for a: (mark with an `x`)

- [X] bug report -> please search issues before submitting
- [ ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

https://westus.dev.cognitive.microsoft.com/docs/services/5890b47c39e2bb17b84a55ff/operations/5be313cec181ae720aa2b26c/console
Entering the right credentials to retrieve info of our registered applications

Any log messages given by the failure

{
"error": {
"code": "BadArgument",
"message": "The source completed without providing data to receive."
}
}

OS and Version?

Windows 10

Versions

Mention any other details that might be useful

I need help of LUIS API Team to solve this problem, I'm trying to use Bot Composer to publish an update with LUIS Service, but it fails, the reason: API of LUIS v2 and v3.0 preview.

Only the first name is picked up when utterance containing multiple personName is given

This issue is for a: (mark with an `x`)

- [x] bug report -> please search issues before submitting
- [ ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

Add personName as an Entity
Use the utterance "Create a meeting with John and Ben"
Use the utterance "Create a meeting with Ben and John"

Any log messages given by the failure

Expected/desired behavior

Expected both to give personName Ben and Jhon

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.

azure-samples / cognitive-services-language-understanding Goto Github PK

cognitive-services-language-understanding's Introduction

Language Understanding (LUIS) Samples

Create your Azure LUIS service

Examples by language

Examples by usage

Interactive app

Healthbot

Intelligent Kiosk

References

APIs

SDKs

Azure REST API

Azure CLI

Azure RM Powershell

Common HTTP response codes

Bots

Related Services

Dependencies

Azure status

Videos

Containers

//BUILD 2018

Other videos

LUIS with Bot framework Blog

Courses including LUIS

Related Microsoft Projects

Searching docs

Community Projects

Prediction Routes v3 Stable

Authoring Routes v3 Preview

Authoring Routes v2 Stable

Contributing

cognitive-services-language-understanding's People

Contributors

Stargazers

Watchers

Forkers

cognitive-services-language-understanding's Issues

Please provide us with the following information:

This issue is for a: (mark with an x)

Minimal steps to reproduce

Any log messages given by the failure

Expected/desired behavior

OS and Version?

Versions

Mention any other details that might be useful

Please provide us with the following information:

This issue is for a: (mark with an x)

Minimal steps to reproduce

Any log messages given by the failure

Expected/desired behavior

OS and Version?

Versions

Mention any other details that might be useful

Minimal steps to reproduce

Any log messages given by the failure

Expected/desired behavior

Versions

Please provide us with the following information:

This issue is for a: (mark with an x)

Minimal steps to reproduce

Any log messages given by the failure

Expected/desired behavior

OS and Version?

Versions

Mention any other details that might be useful

Please provide us with the following information:

This issue is for a: (mark with an x)

Minimal steps to reproduce

Any log messages given by the failure

Expected/desired behavior

OS and Version?

Versions

Mention any other details that might be useful

This issue is for a: (mark with an x)

Minimal steps to reproduce

Any log messages given by the failure

Expected/desired behavior

OS and Version?

This issue is for a: (mark with an `x`)

This issue is for a: (mark with an `x`)

This issue is for a: (mark with an `x`)

This issue is for a: (mark with an `x`)

This issue is for a: (mark with an `x`)

This issue is for a: (mark with an `x`)

This issue is for a: (mark with an `x`)