Premade Rasa Containers
Let's discuss how you can use Docker together with Rasa using pre-made containers.
You can build your own Docker containers, but you can also make use of containers that others have pre-built. In particular, Rasa hosts many pre-built Docker containers on dockerhub that you can run locally as well.
The containers from Rasa are designed differently than the containers that we built in the previous video. In the previous video we trained a new model as part of the building process. The Rasa containers assume that you already have a trained model and you just want to run it inside of the container. That means that we need to make the container aware of the filesystem so that it can find the model we're interested in.
Here's the command that we used in the video to run the Rasa container.
docker run -it -p 8080:8080 -v $(pwd):/app rasa/rasa run --enable-api --port 8080
You can also specify the Rasa version you'd like to run and Rasa also offers containers that come with optional dependencies installed. You can explore all the available tags on dockerhub to get an impression of what is available. The following command uses the 2.8.1 version of Rasa with all the optional dependencies.
docker run -it -p 8080:8080 -v $(pwd):/app rasa/rasa:2.8.1-full run --enable-api --port 8080
If you have a pretrained model that trained on both the nlu and dialogues, you should be able
to confirm the version of Rasa by pinging the
In the next video, we'll discuss the need for a tool like Kubernetes to run our containers.
Try to answer the following questions to test your knowledge.
- What variants are there for the Rasa Open Source container?
- How large are the containers that you can download from Rasa? What are the main contributing factors?