A flask extension serving as an API.AI SDK to provide an easy way to create virtual assistants which may be integrated with platforms such as Google Actions (Google Home).
Flask-Assistant allows you to focus on building the core business logic of conversational user interfaces while utilizing API.AI's Natural Language Processing to interact with users.
Anything you can code in python can be integrated into an assistant's capabilties!
- Perfom complicated actions in response to simple user commands
- Integrate with platforms supported by API.AI (Actions on Google, Alexa, Slack, etc...)
- Interact with external services and APIs
- Retain information and respond to user requests in a context-specific manner
- Design conversational flow to build sophisticated contextual dialogues
This project is heavily inspired and based on John Wheeler's Flask-ask for the Alexa Skills Kit.
- Mapping of user-triggered Intents to action functions
- Context support for crafting dialogue dependent on the user's requests
- Define prompts for missing parameters when they are not present in the users request or past active contexts
- A convenient syntax resembling Flask's decoratored routing
- Internal API.AI schema generation and registration
from flask import Flask
from flask_assistant import Assistant, tell
app = Flask(__name__)
assist = Assistant(app)
@assist.action('Demo')
def hello_world():
speech = 'Microphone check 1, 2 what is this?'
return tell(speech)
if __name__ == '__main__':
app.run(debug=True)
- Create an Assistant object with a Flask app and the route to your webhook URL.
- Use action decorators to map the intents to the proper action function.
- Use action view functions to return ask or tell responses.
- Check out the Quick Start to jump right in
- View the full documentation