Build your own Voice Assistant with React Native, Node.js and Watson (pt.2) — Orchestrator

How to prepare the “glue” between Watson and the mobile app

Step by step to create our backend

To spare time, IBM provides a sample node application with basic structure to starting up our back-end construction.

• Clone git repo

git clone https://github.com/watson-developer-cloud/assistant-simple.git

• On project root folder, clone file .env.example and rename it to .env
• Next step is in WA Dashboard, click on Assistant Tab > Create Assistant
• We are named Beer Assistant and click Create Assistant
• Afterward, bind Assistant with created skill clicking on Add Dialog Skill

• Choose already created Beer Advisor skill and on three dots on superior right corner, select Settings to get service credentials.

Assistant info dashboard

• And select on left menu, Api Details option. Here is the entire config that we need to connect our orchestrator and Watson Assistant. Copy and paste on .env file inside Node project.

Credentials needed to copy to .env file

That’s it!
To test, run:

npm start

And access http://localhost:3000

If everything is ok, you’ll see the following page:

[ OPTIONAL ]
If you want the orchestrator to be accessed externally, you can deploy to Heroku (if you already have an account) without any fee, this starter app is now ready for this.

At next part, we will building the React Native application.
Check it out!

Build your own Voice Assistant with React Native, Node.js and Watson (pt.3) — Mobile App