machaao / rasa-sample-nlu-bot Goto Github PK

The intent of the document is to provide with a quick and fast development setup guide for python developers looking to develop deeply personalized chat bots on Android & Web

This RASA based Sample NLU chatbot also intends to showcase various RCS-esque messaging options available on the Machaao Platform

• MessengerX.io API Token
• Rasa 3.0.4
• Python 3.7, 3.8 Only
• Docker (Optional for Remote Deployment)
• Heroku Account (Optional for Remote Deployment)

• You can acquire a FREE API Key via https://messengerx.io or by emailing us and replace it in the config/credentials.yml

connectors.MachaaoConnector.MachaaoInputChannel:
    api_token: <YOUR API-TOKEN>
    base_url: "https://ganglia.machaao.com"

• Download or clone this repository

git clone [email protected]:machaao/rasa-sample-nlu-bot.git

cd rasa-sample-nlu-bot

• Setup a dev virtual environment on your local machine

python3 -m venv ./dev
source ./dev/bin/activate

• Setup a dev virtual environment on your local machine (Windows)

python3 -m venv ./dev
.\dev\Scripts\activate

• Install requirements

pip install -r requirements.txt

Refer to https://forum.rasa.com/t/an-unofficial-guide-to-installing-rasa-on-an-m1-macbook/51342

Tensorflow setup instructions: https://developer.apple.com/metal/tensorflow-plugin/

Start the rasa action service(background) and core service in the terminal.

chmod +x local_start.sh
./local_start.sh

Start the rasa action and core services in separate terminals.

call local_start.bat

ngrok http 5005

Update your bot Webhook URL on MessengerX.io Portal with the url provided as shown below to continue development

Webhook Url: <HTTPS-NGROK-TUNNEL-URL>/webhooks/machaao/webhook

Visit: https://messengerx.io/<bot-name>

In order to re-train your RASA model based on the sample files provided in the "data" folder

rm -rf models/*
rasa train --domain domain.yml

We are assuming you have access to a heroku account and have installed heroku command line client for your OS.

heroku login

Create a new app on Heroku and note down your heroku app name

heroku create

docker build -t rasa .

heroku container:login

heroku container:push web

heroku container:release web

heroku open
heroku logs --tail

Update your bot Webhook URL on MessengerX.io Portal with the heroku app url

Webhook Url: <YOUR-RASA-SERVER-URL>/webhooks/machaao/webhook

• You can run the code as it is, and it will use the provided Sample Token.

• Please note that this document isn't mean to be use as a guide for production environment setup and nor it's intended for that purpose.
• Running the RASA chat app on Heroku requires a 2X Instance.
• Please contact us for your Android APK