For deploying NLP Server on your instance run the following command.
docker run --pull=always -p 5000:5000 johnsnowlabs/nlp-server:latest
This will check if the latest docker image is available on your local machine and if not it will automatically download and run it.
If you want to keep downloaded models between restarts of the docker image, you can mount a volume.
mkdir /var/cache_pretrained chown 1000:1000 /var/cache_pretrained docker run --pull=always -v /var/cache_pretrained:/home/johnsnowlabs/cache_pretrained -p 5000:5000 johnsnowlabs/nlp-server:latest
Deploy on AWS
The steps you need to follow for deploying NLP Server on AWS are illustrated below. First make sure you have a valid AWS account and log in to AWS Marketplace using your credentials.
NLP Server is available on AWS Marketplace at this URL.
For deploying NLP Server on AWS, follow the video instructions or the seven steps described below.
Continue to subscribe button for creating a subscription to the NLP Server product. The software is free of charge.
2.Read the subscription EULA and click on
Accept terms button if you want to continue.
3.In a couple of seconds the subscription becomes active.
Once it is active you see this screen.
4.Go to AWS Marketplace > Manage subscriptions and click on the
Launch new instance button corresponding to the NLP Server subscription.
This will redirect you to the following screen. Click on
Continue to launch through EC2 button.
5.From the available options select the instance type you want to use for the deployment. Then click on
Review and Lauch button.
6.Select an existing key pair or create a new one. This ensures a secured connection to the instance. If you create a new key make sure that you download and safely store it for future usage. Click on the
7.While the instance is starting you will see this screen.
Then the instance will appear on your EC2 Instances list.
The NLP Server can now be accessed via a web browser at http://PUBLIC_EC2_IP .
API documentation is also available at http://PUBLIC_EC2_IP/docs