Deploying your Rasa Assistant
These docs are for version 1.x of Rasa Open Source.
Deploying your Rasa Assistant
This page explains when and how to deploy an assistant built with Rasa. It will allow you to make your assistant available to users and set you up with a production-ready environment.
When to deploy your assistant: The best time to deploy your assistant and make it available to test users is once it can handle the most important happy paths or is what we call a minimum viable assistant.
Recommended Deployment Methods: The recommended way to deploy an assistant is using either the Docker Compose or Kubernetes/Openshift options we support. Both deploy Rasa X and your assistant. They are the easiest ways to deploy your assistant, allow you to use Rasa X to view conversations and turn them into training data, and are production-ready.
Kubernetes/Openshift
Kubernetes/Openshift is the best option if you need a scalable architecture. It’s straightforward to deploy if you use the helm charts we provide. However, you can also customize the Helm charts if you have specific requirements.
- Default: Read the docs here.
- Custom: Read the docs here and customize the open source Helm charts.
Docker Compose
Rasa-Only Deployment with Docker Compose
It is also possible to deploy a Rasa assistant using Docker Compose without Rasa X.
Installing Docker: If you’re not sure if you have Docker installed, you can check by running:
docker -v && docker-compose -vBuilding an Assistant with Rasa and Docker: This section will cover:
- Setting up your Rasa project and training an initial model
- Talking to your AI assistant via Docker
- Choosing a Docker image tag
- Training your Rasa models using Docker
- Talking to your assistant using Docker
- Running a Rasa server with Docker
Setup
Just like in the tutorial, you’ll use the rasa init command to create a project. The only difference is that you’ll be running Rasa inside a Docker container, using the image rasa/rasa.
docker run -v $(pwd):/app rasa/rasa init --no-prompt
What does this command mean?
-v $(pwd):/appmounts your current working directory to the working directory in the Docker container. This means that files you create on your computer will be visible inside the container, and files created in the container will get synced back to your computer.rasa/rasais the name of the docker image to run.
Running this command will produce a lot of output. What happens is:
- a Rasa project is created
- an initial model is trained using the project’s training data.
To check that the command completed correctly, look at the contents of your working directory:
ls -1
The initial project files should all be there, as well as a models directory that contains your trained model.
Note: By default Docker runs containers as root user. Hence, all files created by these containers will be owned by root. See the documentation of docker and docker-compose if you want to run the containers with a different user.
Talking to Your Assistant
To talk to your newly-trained assistant, run this command:
docker run -it -v $(pwd):/app rasa/rasa shell
This will start a shell where you can chat to your assistant.
Customizing your Model
Choosing a Tag
To keep images as small as possible, we publish different tags of the rasa/rasa image with different dependencies installed. All tags start with a version – the latest tag corresponds to the current master build. The tags are:
{version}{version}-spacy-en{version}-spacy-de{version}-mitie-en{version}-full
Training a Custom Rasa Model with Docker
Edit the config.yml file to use the pipeline you want, and place your NLU and Core data into the data/ directory. Now you can train your Rasa model by running:
docker run \
-v $(pwd):/app \
rasa/rasa:latest-full \
train \
--domain domain.yml \
--data data \
--out models
Running the Rasa Server
To run your AI assistant in production, configure your required Messaging and Voice Channels in credentials.yml. If this file does not exist, create it using:
touch credentials.yml
Then edit it according to your connected channels. After, run the trained model with:
docker run \
-v $(pwd)/models:/app/models \
rasa/rasa:latest-full \
run
Using Docker Compose to Run Multiple Services
To run Rasa together with other services, such as a server for custom actions, it is recommended to use Docker Compose.
Start by creating a file called docker-compose.yml:
touch docker-compose.yml
Add the following content to the file:
version: '3.0'
services:
rasa:
image: rasa/rasa:latest-full
ports:
- 5005:5005
volumes:
- ./:/app
command:
- run
Adding Custom Actions
To create more sophisticated assistants, you will want to use Custom Actions.
Creating a Custom Action
Start by creating the custom actions in a directory actions:
mkdir actions
touch actions/__init__.py
touch actions/actions.py
Then build a custom action using the Rasa SDK, e.g.:
import requests
import json
from rasa_sdk import Action
class ActionJoke(Action):
def name(self):
return "action_joke"
def run(self, dispatcher, tracker, domain):
request = requests.get('http://api.icndb.com/jokes/random').json() # make an api call
joke = request['value']['joke'] # extract a joke from returned json response
dispatcher.utter_message(text=joke) # send the message back to the user
return []
Then add the custom action in your stories and your domain file.
Adding the Action Server
The custom actions are run by the action server. To spin it up together with the Rasa instance, add a service action_server to the docker-compose.yml:
version: '3.0'
services:
rasa:
image: rasa/rasa:latest-full
ports:
- 5005:5005
volumes:
- ./:/app
command:
- run
action_server:
image: rasa/rasa-sdk:latest
volumes:
- ./actions:/app/actions
Adding Custom Dependencies
If your custom action has additional dependencies of systems or Python libraries, you can add these by extending the official image.
Adding a Custom Tracker Store
By default, all conversations are saved in memory. This means that all conversations are lost as soon as you restart the Rasa server. If you want to persist your conversations, you can use a different Tracker Store.
Using PostgreSQL as Tracker Store
postgres:
image: postgres:latest
Then add PostgreSQL to the tracker_store section of your endpoint configuration config/endpoints.yml:
tracker_store:
type: sql
dialect: "postgresql"
url: postgres
db: rasa
Using MongoDB as Tracker Store
mongo:
image: mongo
environment:
MONGO_INITDB_ROOT_USERNAME: rasa
MONGO_INITDB_ROOT_PASSWORD: example
Then add the MongoDB to the tracker_store section of your endpoints configuration endpoints.yml:
tracker_store:
type: mongod
url: mongodb://mongo:27017
username: rasa
password: example
Using Redis as Tracker Store
redis:
image: redis:latest
Then add Redis to the tracker_store section of your endpoint configuration endpoints.yml:
tracker_store:
type: redis
url: redis
Using a Custom Tracker Store Implementation
If you have a custom implementation of a tracker store you have two options to add this store to Rasa:
- extending the Rasa image
- mounting it as volume
Then add the required configuration to your endpoint configuration endpoints.yml as it is described in Tracker Stores. If you want the tracker store component (e.g. a certain database) to be part of your Docker Compose file, add a corresponding service and configuration there.