Skip to content
docker-compose script for NLP Building Blocks.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

NLP Building Blocks

This repository contains a docker-compose script for creating the NLP Building Blocks containing:


Starting the Services in Containers

git clone
cd nlp-building-blocks
docker-compose up

Sending Requests to the Containers

Once the containers have started you can access each application at their respective ports:

  • Prose Sentence Extraction Engine - port 8060 - API Guide
  • Renku Language Detection Engine - port 7070 - API Guide
  • Sonnet Tokenization Engine - port 9040 - API Guide
  • Idyl E3 Entity Extraction Engine - port 9090 - API Guide
  • Verso Text Preprocessing Engine - port 7080 - API Guide

Java SDK

The nlp-building-blocks-java-sdk can be used to programatically create NLP pipelines using the services.

Using cURL

You can easily interact with each of the services using cURL as shown below:

Renku Language Detection Engine

To detect the language of text:

curl http://localhost:7070/api/language -d "Can you please tell me what language this text is in?" -H "Content-Type: text/plain"

Prose Sentence Extraction Engine

To extract sentences from text:

curl "http://localhost:8060/api/sentences?language=eng" -d "This is a sentence. This is another sentence." -H "Content-Type: text/plain"

Sonnet Tokenization Engine

To tokenize text:

curl "http://localhost:9040/api/tokenize?language=eng" -d "Tokenize this text please." -H "Content-Type: text/plain"

Idyl E3 Entity Extraction Engine

To extract named-entities from text:

curl "http://localhost:9000/api/extract?language=eng" -d '["George", "Washington", "was", "president."]' -H "Content-Type: application/json"

Verso Text Preprocessing Engine

To preprocess text for an NLP pipeline:

curl "http://$HOST:7080/api/preprocess?lc=y" -d "Preprocess this text, please?" -H "Content-Type: text/plain"


This project is licensed under the Apache License, version 2.0.

You can’t perform that action at this time.
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session.