Watson Assistant Chatbot for SAP Cloud Platform

This Node.js app demonstrates how easily a chatbot can be built that is running on the SAP Cloud Platform and that is leveraging the Watson Assistant service on the IBM Cloud.

The assistant-simple was slightly modified so the Node.js app is deployed on the SCP. There's also a demo of the original app - apps on SCP trial accounts are stopped after a certain time. Please note that both animations in this repo are still from the orginal IBM Cloud repo. This one shows the dialog.

As both, IBM Cloud and SAP Cloud platform, have Cloud Foundry runtimes it was possible to deploy the assistant on the SAP Cloud Platform.

The solution demonstrates how simple it is to deploy Cloud Foundry applications on different platforms and how to consume services from other platforms via a REST API.

Please note this app uses the Watson Assistant V2 API. To access a version of the V1 app, you can go to v1.4.1.

If you need more information about the V1 API, you can go to the Watson Assistant V1 API page.

Prerequisites

It is assumed that you have an account on the SAP Cloud Platform and downloaded the Cloud Foundry Command Line Interface.

1. Sign up for an IBM Cloud account.
2. Download the IBM Cloud CLI.
3. Create an instance of the Watson Assistant service and get your credentials:
   • Go to the Watson Assistant page in the IBM Cloud Catalog.
   • Log in to your IBM Cloud account.
   • Click Create.
   • Click Show to view the service credentials.
   • Copy the apikey value, or copy the username and password values if your service instance doesn't provide an apikey.
   • Copy the url value.

Configuring the application

1. In your IBM Cloud console, open the Watson Assistant service instance

2. Click the Import workspace icon in the Watson Assistant service tool. Specify the location of the workspace JSON file in your local copy of the app project:

   <project_root>/training/bank_simple_workspace.json

3. Select Everything (Intents, Entities, and Dialog) and then click Import. The car dashboard workspace is created.

4. Click the menu icon in the upper-right corner of the workspace tile, and then select View details.

5. Click the icon to copy the workspace ID to the clipboard.

   

6. In the application folder, copy the .env.example file and create a file called .env

   cp .env.example .env
   

7. Open the .env file and add the service credentials that you obtained in the previous step. The Watson SDK automatically locates the correct environmental variables for either username, password, and url or the apikey and url credentials found in the .env file.

   Example .env file that configures the apikey and url for a Watson Assistant service instance hosted in the US East region:

   ASSISTANT_IAM_APIKEY=X4rbi8vwZmKpXfowaS3GAsA7vdy17Qhxxxxxxxx
   ASSISTANT_URL=https://gateway-wdc.watsonplatform.net/assistant/api
   

   • If your service instance uses username and password credentials, add the ASSISTANT_USERNAME and ASSISTANT_PASSWORD variables to the .env file.

   Example .env file that configures the username, password, and url for a Watson Assistant service instance hosted in the US South region:

   ASSISTANT_USERNAME=522be-7b41-ab44-dec3-xxxxxxxx
   ASSISTANT_PASSWORD=A4Z5BdGENxxxx
   ASSISTANT_URL=https://gateway.watsonplatform.net/assistant/api
   

   However, if your credentials contain an IAM API key, copy the apikey and url to the relevant fields.

     {
       "apikey": "ca2905e6-7b5d-4408-9192-xxxxxxxx",
       "iam_apikey_description": "Auto generated apikey during resource-key ...",
       "iam_apikey_name": "auto-generated-apikey-62b71334-3ae3-4609-xxxxxxxx",
       "iam_role_crn": "crn:v1:bluemix:public:iam::::serviceRole:Manager",
       "iam_serviceid_crn": "crn:v1:bluemix:public:iam...",
       "url": "https://gateway-syd.watsonplatform.net/assistant/api"
     }

   ASSISTANT_IAM_APIKEY=ca2905e6-7b5d-4408-9192-xxxxxxxx
   

8. Add the ASSISTANT_ID to the previous properties

   ASSISTANT_ID=522be-7b41-ab44-dec3-xxxxxxxx
   

Running locally

1. Install the dependencies

   npm install
   

2. Run the application

   npm start
   

3. View the application in a browser at localhost:3000

Deploying to the SAP Cloud Platform

1. Select the correct region and log in

   cf api https://api.cf.eu10.hana.ondemand.com
   cf login
   

2. Edit the manifest.yml file. Change the name field to something unique.
   For example, - name: my-app-name.

3. Deploy the application

   cf push
   

4. View the application online at the app URL.
   For example: https://my-app-name.cfapps.eu10.hana.ondemand.com

License

This sample code is licensed under Apache 2.0.
Full license text is available in LICENSE.

Open Source @ IBM

Find more open source projects on the IBM Github Page.