Installing Rasa in Linux (Ubuntu)and Windows
Creating an AI-assisted chatbot is getting simpler now so that a person with less or no knowledge about Machine Learning and Natural Language Processing can build their own chatbot from scratch with basic programming knowledge.
Visit Rasa documentation for a detailed explanation.
Rasa Installation
Rasa is based on Python and installed using python package installer (pip). It is highly recommended to create a virtual environment before installing Rasa.
Windows
First, download and install Microsoft Visual C++Build Tools
Check whether your system has already installed Python 3.7 using the following commands in the command prompt. If not, install Python 3 here and make sure you tick the option Add to PATH variable
in the installer. If you have installed both Python 2 and Python 3, python3
should be used instead of python
.
python --version
Check whether you have installed pip3 using the following commands. If not, install pip here
pip --version
or
python -m pip --version
Create a new virtual environment for rasa.
python -m venv --system-site-packages
./venv.\venv\Scripts\activate
Your command prompt should look like the following if the virtual environment is properly activated. (venv) C:\Users\user
Upgrade your pip to the latest version
pip install -U pip
Install Rasa in the virtual environment. This may take several minutes.
pip install rasa
Use the following command to check if Rasa is installed correctly
rasa --version
Ubuntu (Linux)
Run the following command in the terminal to see if python 3.7 and pip are already available.
python3 --versionpython3 -m pip --version
If python 3.7 is not installed, install it using the following commands.
sudo apt update
sudo apt install software-properties-common
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt install python3.7
Create a new virtual environment for Rasa and activate it.
python3 -m venv ./venvsource
./venv/bin/activate
Your command prompt should look like the following if the virtual environment is properly activated. (venv)/root/>
Upgrade your pip to the latest version
pip install -U pip
Install Rasa in the virtual environment. This may take several minutes.
pip install rasa
Use the following command to check if Rasa is installed correctly
rasa --version
Congratulations! Now you have successfully installed Rasa.
Creating a New Project
The virtual environment should be activated before running Rasa.
Windows — in command prompt
.\venv\Scripts\activate
Ubuntu — in terminal
source ./venv/bin/activate
To create a new project, run:
rasa init
Select an installation path and train the initial model. This will take several minutes depending on the system hardware.
Once the training has been finished, the bot will be loaded automatically. To run the bot manually, navigate to the created folder and type:
rasa shell
You can type a message and see how the bot responds.
Congratulations! You have created your first Rasa project.