Lacuna Document Classification Engine Quick Start

This is a quick start to get you up and running with Lacuna Document Classification Engine fast and painless. To do this, we are going to launch Lacuna as a docker container. If you launched Lacuna from the AWS Marketplace you can skip installing Docker and jump down to the example commands.

First install Docker if you haven’t already. Once done, run the following commands:

docker run -p 9090:9090 -it mtnfog/lacuna:1.0.0

Once Sonnet has started, open a console and run the following command:

curl "http://localhost:9090/api/classify?language=eng" -d "The quick brown fox jumped over the lazy dog." -H "Content-Type: text/plain"

This sends a request to Lacuna to categorize the input text. If you launched Lacuna from the AWS Marketplace you will need to substitute localhost with the public IP address of the EC2 instance.  The response from Lacuna will look like:

{"scores":{"scores":{"category2":0.689,"category3":0.478,"category1":0.92}}}

The NLP Building Blocks Java SDK can be used to create NLP pipelines and to integrate Lacuna in your existing NLP pipeline.