Appendices

NLP integration

In this item, you will learn how to integrate a bot to a cognitive engine. A cognitive engine, or Natural Language Processing (NLP) software interpret what a user is saying to a bot. To integrate any of the following NLP engines, just follow the step by step:

NTT DATA Clever

NTT DATA Clever comes integrated as default. Clever is a NTT DATA proprietary Natural Language Processing engine. If you are using another NLP and wants to integrate your bot to clever again, just select Clever on the NLP menu.

IBM Watson Assistant

Watson Assistant is a service package offered by IBM. Among them, there is a question-answering software that applies natural language processing, information retrieval, knowledge representation, automated reasoning and machine learning technologies to answer questions posed in natural language.

Watson on eva

1. ​

2. Log in with your IBM id.

3. Click on "skills" on the upper left corner.

4. Go to skills, then click “create skill” to create a bot on Watson.

5. If you have existing skills, select one, then click on the menu on the upper right corner of the selected skill card.

Watson skills

1. Click on “view API details”

2. If you are using a newer account, copy the links and

codes after Assistant URL and Api Key insert them on eva. Remember to switch to the newer version in eva.

1. If you are using an older account, copy the links and codes after v1 Workspace URL, Username and

Password and insert them on eva. Remember to switch to the older version in eva.

Google Dialogflow

Google Dialogflow is a human-computer interaction framework that works on natural language.

Dialog on eva

1. ​

2. Then click on “go to console”.

3. Click on settings on the upper left corner (the cogwheel icon - see image).

Dialogflow settings

1. Click the link right after “Project ID”.

Project ID

1. You will be taken to a page in the Google Cloud Platform.

2. Once in the Google Cloud Platform, click on the link below “e- mail”.

Important: Remember to charge your agent permission or else your intents won’t work.

Go to IAM in the upper left corner of the menu.

IAM

Once there, click on the edit icon (pencil) on the right of the agent named as Dialogflow Integrations.

Agents list

Now, select “Dialogflow” and then “Dialogflow API Admin”.

Permissions

1. Once you changed your agent permission, go to “service accounts” and then click on the menu on the right of the agent you want to use.

*If you don’t have a Service Account, click on “Create Service Account” and create one.

Agent selection

1. Click on “create key” and select JSON.

2. Save the JSON file on your computer. Upload this file when creating a Dialogflow BOT in eva to complete the integration.

Microsoft Luis

Language Understanding (LUIS) is a cloud-based API service that applies custom machine-learning intelligence to a user's conversational, natural language text to predict overall meaning, and pull out relevant, detailed information.

To integrate LUIS to eva, you have to have an active Azure account with created resources.

Luis on eva

1. ​

2. Login with your Microsoft account.

3. Create an app or click on an existing one.

4. Click on “manage”.

Endpoints on Azure

1. Then click on “Azure Resources” at the left.

Azure resources

1. Copy the example query, located on the botton of the screen.

Example Query

1. Then, click on authoring resource and copy the primary key. and paste it on eva.

Authoring resource

1. Paste the Example Query on eva and replace the subscription key (the code between subscription-key={code} and &verbose) for the primary key you just copied on Authoring Resource.

Example Query with replaced subscription key

Chatbase integration(Deprecated)

Sign in.

Go to “my bots” on the right upper corner.

Chatbase website

Add a new bot.

If you already have bots, go to the next page.

Fill the required fields.

Click on “next”.

Copy the generated API.

Insert in the required field.

Chatbase API screen

If you already have a bot, just copy the API and insert in eva.

Microsoft QnA Maker

QnA Maker is a cloud-based Natural Language Processing (NLP) service that creates a conversational layer over data. It can be used to find the most appropriate answer for any given natural language input.

QnA Maker on eva

1. ​

2. Login.

3. Click on "My Knowledge Bases".

*If you already have knowledge bases, skip to the next page.

1. Click “create a knowledge base”.

• You must have an active Azure account.

1. Fill the required fields and click “create”.

Knowledge base creation

1. Select a knowledge base.

Knowledge base selection

1. Click on “settings”.

Knowledge base settings

1. Then go to “postman”, on the bottom of the page, and copy the code.

Chatbase Using system entities in Luis

eva supports Luis version 2. When using the datetimeV2 system entity in Luis, you can use subcategories, such:

• • date

  • time

  • datetime

  • daterange

  • timerange

  • datetimerange

Those subcategories should be added after a dot (.).

So, if you are using the date subcategory, the entity name should be builtin.datetimeV2.date

Where builtin.datetimeV2 is the system entity name and date is the subcategory.

For further information, check https://docs.microsoft.com/en- us/azure/cognitive-services/luis/luis-reference-prebuilt- datetimev2?tabs=1-3%2C2-1%2C3-1%2C4-1%2C5-1%2C6-​

​1#subtypes-of-datetimev2​

​