Serverless Google Assistant with Firebase

This sample google assistant dialogflow is a facts-based action designed to report metrics out of firebase. The idea is that something external would update firebase, which would then be read through google assistant.

Design

Prereqs

Install NodeJS
A Google Project is created
- the project should have enabled firebase, cloud functions Deployment Manager V2 API
- a service account should be created. For production, the role should be restricted but for now Owner will work.
- the credentials JSON should be placed in root of the project, as serverless will need it

Devtime dependencies

A firebase collection must be created for facts.
- The collection should contain a field of "metric" i. The field should be lowercase space separated words
- The collection should have a "total_count" and "response" attributes
The following environment variables should be baked into your system
- GOOGLE_APPLICATION_CREDENTIALS - path to credentials file
- PROJECT_ID - available in admin console

Install instructions

Clone the repository
Run npm install
Start building your action in the google actions console
Click ‘Add Action’ and build a custom intent. This will open dialogflow.
Create an intent called metrics. In the Action and parameters menu, set parameter name, entity, and value to metrics, @metrics, $metrics exclusively. Also enable all options under Fulfillment.
Update entities.yml with the entities and synonyms for your metric (Note: metric names correlate 1:1 back to firebase metrics)
Run npm run-script update-entities to deploy your entities
run sls deploy or npm run-script deploy to index to google cloud.
In dialogflow, go to Fulfillment on the left side, enable web hook, and place the URL given by serverless as the fulfillment address. https://us-central1-<Project_ID>.cloudfunctions.net/index
Go to integrations and add your intent to the implicit invocation. Then click See how it works in Google Assistant. to try your new skill out. If you notice your entities are not catching on, you may need to train the assistant back under intents.

Sample Entities/Sayings