Jovo Model: Google Assistant
Learn how to turn the Jovo Model into a Conversational Actions model for Google Assistant.
- Google Assistant-specific Elements in the Jovo Model
- Using the Google Assistant Jovo Model with the Jovo CLI
- Using the Google Assistant Jovo Model npm Package
Google Assistant Conversational Actions are a new way to build Google Actions that don't require Dialogflow as NLU service. You can either manage the language models via API (what the Jovo CLI is doing during deployment) or in the Actions Builder console, which offers a graphical user interface.
Learn more about the structure in the official Conversational Actions documentation. The Jovo Model can be translated into this structure by using the
jovo build command (see below) or the npm package (see below).
This section provides an overview of how the Jovo Model see general structure in the main Jovo Model docs can be extended with platform-specific content for Google Assistant.
You can define a Google Assistant-specific invocation name like this:
Find all built-in types in the official Conversational Action System Types Reference.
If your intent uses an input (see how they are added to the Jovo Model) that requires a Google Assistant system type, you can add it like this:
Some elements (intents, types) might be required only by the Google Assistant portion of your Jovo project. For this you can add a
googleAssistant object to your Jovo Model.
This object follows the structure of the Google Assistant Model .yaml files in JSON format.
By using the
jovo build command, you can turn your Jovo Model files in the
models folder in your Jovo project into Conversational Action specific files.
Make sure that you remove the
dialogflow part in your
project.js file. There is no need to specify an
nlu as the built-in service is used.
After successfully running
jovo build, you can find the files inside the
Install the package like this:
You can learn more about all the Jovo Model features here: Using the Jovo Model npm Packages.