This application shows the capabilities of Watson Assistant and Discovery services to work together to find answers on a given query. In this sample app, the user is chatting with a virtual car dashboard, giving it commands in plain English such as "Turn on the wipers," "Play me some music," or "Let's find some food." If the user makes a request and Watson Assistant is not confident in its answer (e.g. "How do I check my tire pressure?"), Discovery will search the car manual and return the most relevant results, if relevant materials exist.

This demo is a reworking of a previous one but with an OpenWhisk back-end and React front-end. OpenWhisk is IBM's "serverless" offering, allowing users to upload functions to the cloud, call them via REST API, and pay only by the millisecond of usage.

• How it Works
• Run Locally
  • Getting Started
  • Setting up Watson Services
  • Train Watson Services
  • Setting up the OpenWhisk Back-end
  • Setting up the React Front-end
  • Running the App
• License

Under the hood, there are two components to this app:

• One is the front-end, which is simply static assets (HTML, CSS, and React), it uses CSS with Sass for cleaner, more maintainable source code.
• The other is the OpenWhisk actions:
  • When the user inputs text, the UI sends the current context and input to the OpenWhisk sequence. These are processed by the Watson Assistant service and returned, with an output and new context. The results are sent to the next action.
  • The Discovery action checks for a flag from the Watson Assistant output, and if it is present takes the original input and queries the manual with it. If there is no flag, the Watson Assistant results pass through the function unchanged. The Sequence returns the output and updated context back to the UI.

1. If you don't already have an IBM Cloud account, you can sign up here

Make sure you have at least 2 services available in your IBM Cloud account.

2. Clone (or fork) this repository, and go to the new directory

git clone https://github.com/watson-developer-cloud/assistant-with-discovery-openwhisk.git
cd assistant-with-discovery-openwhisk

3. Install Node.js (Versions >= 6).

4. In the root directory of your repository, install the project dependencies.

npm install

Skip this section if you have downloaded the project from Watson Console and already have a credentials.json file

1. Create a project using the Watson Console using Watson Assistant and Discovery services.

2. In the Watson Console navigate to Projects, click your newly created project, copy credentials from Project View page and paste them in to a new credentials.json file.

Run following commands to train Watson Assistant and Discovery services:

  npm run train

1. Install the Openwhisk Command Line Interface.

2. Download and install the Bluemix CLI.

3. Login by running the following:

bx login

4. Install jq as a dependency.

5. Run the provided shell script create-openwhisk-actions.sh to create your OpenWhisk actions & sequence. The syntax to do so may vary by system, but for example:

   sh create-openwhisk-actions.sh

Create an optimized build of your project. During this stage, your environment variable will be inserted into App.js for use by your components.

npm run build

All that's left is to serve your static files locally. You should see the project running in a new tab!

npm start

Licensed under Apache 2.0.