Model Storage

You are viewing documentation for our open source project which is maintained by the community. If you want to get started building assistants with Rasa please check out our latest documentation here.

You can load your trained model in three different ways:

  1. Load the model from your local disk (see Load Model from Disk)

  2. Fetch the model from your own HTTP server (see Load Model from Server)

  3. Fetch the model from cloud storage like S3 (see Load Model from Cloud)

By default all commands of Rasa's CLI will load models from your local disk.

Load Model from Disk

By default models will be loaded from your local disk. You can specify the path to your model with the --model parameter:

rasa run --model models/20190506-100418.tar.gz

If you want to load the latest model in a directory, you can specify a directory instead of a file:

rasa run --model models/

Rasa will check all the models in that directory and load the one that was trained most recently.

If you don't specify a --model argument, Rasa will look for models in the models/ directory. The two following calls will load the same model:

# this command will load the same model
rasa run --model models/

# ... as this command (using defaults)
rasa run

Load Model from Server

You can configure the Rasa server to regularly fetch a model from a server and deploy it.

How to Configure Rasa

You can configure the HTTP server to fetch models from another URL by adding it to your endpoints.yml:

models:
  url: http://my-server.com/models/default
  wait_time_between_pulls:10 # In seconds, optional, default: 100

The server will query the url for a zipped model every wait_time_between_pulls seconds.

If you want to pull the model only when starting up the server, you can set the time between pulls to null:

models:
  url: http://my-server.com/models/default
  wait_time_between_pulls:null # fetches model only once

How to Configure Your Server

Rasa will send a GET request to the URL you specified in the endpoints.yml, e.g. http://my-server.com/models/default in the above examples. You can use any URL. The GET request will contain an If-None-Match header that contains the model hash of the last model it downloaded. An example request from Rasa Open Source to your server would look like this:

curl --header "If-None-Match: d41d8cd98f00b204e9800998ecf8427e" http://my-server.com/models/default

The response of your server to this GET request should be one of these:

Rasa uses the If-None-Match and ETag headers for caching. Setting the headers will avoid re-downloading the same model over and over, saving bandwidth and compute resources.

Load Model from Cloud

You can also configure the Rasa server to fetch your model from a remote storage:

rasa run --model 20190506-100418.tar.gz --remote-storage aws

The zipped model will be downloaded from cloud storage, unzipped, and deployed. Rasa supports loading models from:

Models need to be stored in the root folder of the storage service. Currently, it is not possible to manually specify the path on the cloud storage.

Amazon S3 Storage

Amazon S3 is supported using the boto3 package which you need to install as an additional dependency using pip3:

pip3 install boto3

For Rasa to be able to authenticate and download the model, you need to set the following environment variables before running any command requiring the storage:

Once all environment variables are set, you can start the Rasa server with remote-storage option set to aws:

rasa run --model 20190506-100418.tar.gz --remote-storage aws

Google Cloud Storage

Google Cloud Storage (GCS) is supported using the google-cloud-storage package which you need to install as an additional dependency using pip3:

pip3 install google-cloud-storage

If you are running Rasa on Google App Engine or Compute Engine, the auth credentials are already set up (for the GCS in the same project). In this case, you can skip setting any additional environment variables.

If you are running locally or on a machine outside of GAE or GCE you need to provide the authentication details to Rasa manually:

  1. Check out the GCS documentation and follow the descriptions on "Creating a service account" and "Setting the environment variable."
  2. After you have completed the GCS instructions, you should have set an environment variable called GOOGLE_APPLICATION_CREDENTIALS to the path of a service account key file with access to your GCS.

Once all environment variable is set, you can start the Rasa server with remote-storage option set to gcs:

rasa run --model 20190506-100418.tar.gz --remote-storage gcs

Azure Storage

Azure Storage is supported using the azure-storage-blob package which you need to install as an additional dependency using pip3:

pip3 install azure-storage-blob

Once all environment variables are set, you can start the Rasa server with remote-storage option set to azure:

rasa run --model 20190506-100418.tar.gz --remote-storage azure

Other Remote Storages

If you want to use any other Cloud Storage, you can provide your own python implementation of the rasa.nlu.persistor.Persistor class.

You can start the Rasa server with remote-storage option set to the module path of your persistor implementation:

rasa run --remote-storage <your module>.<class name>