This is a example Rasa frequently asked question and answer Chatbot that developed for Hamrah e Aval IT Helpdesk.
Here is an example of a conversation you can have with this bot:
Table of Contents
In a Python3 virtual environment run:
pip install -r requirements.txt
Use rasa train
to train a model.
Then to talk to the bot, run:
rasa shell
The bot has one main skill to answers to questions about:
- Activate and purchase Internet data packages
- Cancel automatic continuation of a data package
- costs of Internet connection
- Internet connection problems
Take a look at data/nlu.md
to see what the bot is currently trained to recognize.
It can also respond to requests for help (e.g. "help me").
If configured, the bot can also hand off to another bot in response to the user asking for handoff. More details on handoff below.
This bot includes a simple skill for handing off the conversation to another bot or a human.
The simplest way to use the handoff feature is to do the following:
- copy WebChat folder to the project location
- run the rasa server and action server at the default ports (shown here for clarity)
In one terminal window:
rasa run -m models --enable-api --cors "*" –debug
- Open index.html in a browser to see handoff in action
You can test the bot on the test conversations by running rasa test
.
This will run end-to-end testing on the conversations in tests/conversation_tests.md
.