- Python 3.6 or Python 3.7 Install Python 3.7 on Ubuntu 18.04
- Docker
- Tensorflow Hardware requirements
Note if your hardware doesn't support
AVX
instructions then u will have to build tensorflow from source as described here
-
Install Python. Please make sure to install Python 3.6 or Python 3.7. Rasa won't work with any other python version
Windows
You can install it from heremacOS
$ brew update $ brew install python3.7
Linux
- Follow this blog
-
Install, create and activate a Virtual Environment
-
Install virtual Environment
python -m pip install --user virtualenv
-
Create a virtual environment
Linux / macOS
$ python3 -m venv ./venv
Windows
C:\> python3 -m venv ./venv
-
Activate the virtual environment:
Linux / macOS
$ source ./venv/bin/activate
Windows
C:\> .\venv\Scripts\activate
-
-
Install the required packages from requirements.txt inside this virtual environment:
pip install -r requirements.txt
-
Install spacy. Ref: here
$ pip install rasa[spacy] $ python -m spacy download en_core_web_md $ python -m spacy link en_core_web_md en
-
Train the model
$ rasa train
- Activate the environment:
- Linux / macOS:
source venv/bin/activate
- Windows:
.\venv\Scripts\activate.bat
- Linux / macOS:
- Open a new terminal and run actions
rasa run actions
- Open a new terminal and run duckling which is used for entity extraction
docker run -p 8000:8000 rasa/duckling
- Lastly, open a new terminal to run rasa
rasa run