Create a banking chatbot with FAQ discovery, anger detection and natural language understanding

In this code pattern, we will create a chatbot using Node.js and Watson Assistant. The Assistant flow will detect customer emotions and be enhanced by using Natural Language Understanding to identify location entities. For FAQs, a call to the Discovery service will use passage retrieval to pull answers from a collection of documents.

When the reader has completed this pattern, they will understand how to:

• Create a chatbot that converses via a web UI using Watson Assistant and Node.js
• Use Watson Discovery with passage retrieval to find answers in FAQ documents
• Identify location entities with Watson Natural Language Understanding

NOTE: This code pattern has been updated to include instructions for accessing Watson services running on IBM Cloud Pak for Data. These updates can be found in the specific instructions for deploying your app locally, or deploying your app to OpenShift on IBM Cloud. The main change required is that your application will need additional credentials to access the IBM Cloud Pak for Data cluster that is hosting the Watson services.

Click here for more information about IBM Cloud Pak for Data.

Flow

1. The FAQ documents are added to the Discovery collection.
2. The user interacts with a chatbot via the app UI.
3. User input is processed with Natural Language Understanding (NLU). The context is enriched with NLU-detected entities and keywords (e.g., a location).
4. The input and enriched context is sent to Assistant. Assistant recognizes intent, entities and dialog paths. It responds with a reply and/or action.
5. Optionally, a requested action is performed by the app. This may include one of the following:
   • Lookup additional information from bank services to append to the reply
   • Use Discovery to reply with an answer from the FAQ documents

Included components

• IBM Watson Assistant: Build, test and deploy a bot or virtual agent across mobile devices, messaging platforms, or even on a physical robot.
• IBM Watson Discovery: A cognitive search and content analytics engine for applications to identify patterns, trends, and actionable insights.
• IBM Watson Natural Language Understanding: Analyze text to extract meta-data from content such as concepts, entities, keywords, categories, sentiment, emotion, relations, semantic roles, using natural language understanding.

Featured technologies

• Node.js: An asynchronous event driven JavaScript runtime, designed to build scalable applications.

Steps

1. Clone the repo
2. Create Watson services
3. Customize the Watson Assistant skill
4. Load Discovery documents
5. Deploy the application
6. Use the web app

1. Clone the repo

Clone the watson-banking-chatbot locally. In a terminal, run:

git clone https://github.com/IBM/watson-banking-chatbot

2. Create Watson services

Provision the following services:

• Watson Assistant
• Watson Discovery
• Watson Natural Language Understanding

NOTE: If you will be using the Deploy to Cloud Foundry on IBM Cloud deployment option, then you can skip these next steps and jump right to the Deploy the Application section. That deployment option automatically creates the services and links them to your application.

The instructions will depend on whether you are provisioning services using IBM Cloud Pak for Data or on IBM Cloud.

Click to expand one:

3. Customize the Watson Assistant skill

The following instructions will depend on if you are provisioning Assistant from IBM Cloud or from an IBM Cloud Pak for Data cluster. Choose one:

To find the Skill ID for Watson Assistant:

• Go back to the Skills tab.

• Click on the three dots in the upper right-hand corner of a card and select View API Details.

• Copy the Skill ID GUID. Use this value when setting up your run-time environment.

• By default the application will import and use the skill named watson-banking-chatbot, but you can configure it to use another skill by setting the run-time environment variable SKILL_ID.

  

To view the Assistant dialog, click on the skill and choose the Dialog tab. Here's a snippet of the dialog:

4. Load Discovery documents

By default, the application will create a collection named watson-banking-chatbot, but you can configure it to use another collection by setting the run-time environment variables DISCOVERY_COLLECTION_ID and DISCOVERY_ENVIRONMENT_ID.

The following instructions will depend on if you are provisioning Discovery from IBM Cloud or from an IBM Cloud Pak for Data cluster. Choose one:

5. Deploy the application

Click on one of the options below for instructions on deploying the Node.js server.

6. Use the web app

The web app presents a customer service chatbot. Interact with the chatbot by pressing the buttons when prompted or use the Type something box. The chatbot is powered by Watson Assistant with additional information coming from Discovery and Natural Language Understanding.

Troubleshooting

• Error: Unable to list workspaces for Watson Assistant: Forbidden: Access is denied due to invalid credentials.

  This error occurs with Deploy to IBM Cloud button. Configure a runtime environment variable for ASSISTANT_APIKEY to allow automatic configuration of the default skill or configure SKILL_ID to use another skill.

• Fail: An operation for service instance wbc-discovery-service is in progress.

  This error occurs when starting the app before the service is ready. It is currently common behavior with the Deploy to IBM Cloud button. In this case, click the Run button to restart the application. It will succeed when the service is ready.

• Error: Environment {GUID} is still not active, retry once status is active

  This is common during the first run. The app tries to start before the Discovery environment is fully created. Wait a few minutes and click the Run button to restart the application.

• Error: Only one free environment is allowed per organization

  To work with a free trial, a small free Discovery environment is created. If you already have a Discovery environment, this will fail. If you are not using Discovery, check for an old service thay you may want to delete. Otherwise use the .env DISCOVERY_ENVIRONMENT_ID to tell the app which environment you want it to use. A collection will be created in this environment using the default configuration.

Links

• Demo on Youtube
• Watson Node.js SDK
• Relevancy Training Demo Video
• Relevancy Training Demo Notebook

License

This code pattern is licensed under the Apache License, Version 2. Separate third-party code objects invoked within this code pattern are licensed by their respective providers pursuant to their own separate licenses. Contributions are subject to the Developer Certificate of Origin, Version 1.1 and the Apache License, Version 2.

Apache License FAQ