Warning: This document is for an old version of rasa NLU. The latest version is 0.15.1.

Model PersistenceΒΆ

rasa NLU supports using S3 and GCS to save your models.

  • Amazon S3 Storage

    S3 is supported using the boto3 module which you can install with pip install boto3.

    Start the rasa NLU server with storage option set to aws. Get your S3 credentials and set the following environment variables:

  • Google Cloud Storage

    GCS is supported using the google-cloud-storage package which you can install with pip install google-cloud-storage

    Start the rasa NLU server with storage option set to gcs.

    When running on google app engine and compute engine, the auth credentials are already set up. For running locally or elsewhere, checkout their client repo for details on setting up authentication. It involves creating a service account key file from google cloud console, and setting the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of that key file.

If there is no bucket with the name $BUCKET_NAME rasa will create it. Models are gzipped before saving to cloud.

If you run the rasa NLU server with a server_model_dirs which does not exist and BUCKET_NAME is set, rasa will attempt to fetch a matching zip from your cloud storage bucket. E.g. if you have server_model_dirs = ./data/model_20161111-180000 rasa will look for a file named model_20161111-180000.tar.gz in your bucket, unzip it and load the model.