We use Rasa mainly to assist People Ops-related processes, and also to assist engineering.
We use Rasa Open Source edition. Note: Rasa X is free but closed source, requires either Kubernetes or Docker Compose, with 4 to 8 GB RAM.
Install Rasa on Ubuntu VM
Launch a t3a.small (2 GB) instance, with security groups
ssh-server-public, with 8 GiB storage. First, run the usual Ubuntu preparation.
Note about RAM: 2 GB is required to first install rasa, 1 GB will be killed. After this, Rasa uses about 800 – 960 MiB to train, and (separately) run, so 1 GB should be enough.
Note: As of May 2021, Rasa does not support Arm/Graviton2, especially tensorflow-text:
ERROR: Could not find a version that satisfies the requirement tensorflow-text<2.4,>=2.3; sys_platform != “win32” (from rasa) (from versions: none)
ERROR: No matching distribution found for tensorflow-text<2.4,>=2.3; sys_platform != “win32” (from rasa)
Make sure .bashrc contains
sudo apt install -y python3-dev python3-pip pipenv pip3 install -U pip pipenv # Use pipenv instead of plain Python3 virtual environment mkdir rasaops cd rasaops pipenv install rasa # If error here, uninstall user's virtualenv: pip uninstall virtualenv; to use globally installed virtualenv pipenv shell rasa init
Train, Shell, and Run
After editing NLU data, you must train first. This requires 950 MB RAM but can be bigger, and if you connect via VS Code Remote-SSH then it can grow beyond that. It’s recommended to either use 2 GB or enable 512 MB swap.
Shell to test: (to stop/quit Rasa Shell, type
rasa shell # or, for more debugging: rasa shell --debug
rasa run # if you need more debugging: rasa run -v rasa run -vv
Rasa will take some time to load model. Wait until “Rasa server is up and running” message.
For any chatbot with typical functionality you’ll need Rasa Action Server as well:
pipenv rasa run actions --debug # Useful during development pipenv rasa run actions --auto-reload --debug
Rocket.Chat Built-in Connector
Use ALB to serve, target instance is HTTP port 5050. Alternatively without ALB, configure security group to open port 5050.
TODO: Rocket.Chat Custom Connector
Develop / Deploy Rasa using Docker / Docker Compose
Initialize new project in current folder
# Run as host's user ID docker run --user 1000 -v $(pwd):/app:Z rasa/rasa:latest-full init --no-prompt # Run shell docker run --user 1000 -v $(pwd):/app:Z rasa/rasa:latest-full shell
TODO: Deploying Rasa Assistant to AWS Lambda Docker