Compare the semantic content of two texts with a single call to the API

The Retina API gives you the opportunity to develop your own, intelligent NLU application. You can use the free trial API to create and test your app. Once you want to switch to a production system, you only need to change the endpoint address.

Retina API at a glance

  • Core NLU module:
    • Conversion of words or text items into semantic fingerprints
    • Computation of Boolean operations with semantic fingerprints (semantic expressions)
    • Text functions like segmentation, keyword extraction, parsing, identification of contexts and similar terms
    • Comparison of semantic fingerprints
    • Decoding context words of semantic fingerprints
    • Access to Retina Database General English
  • Feature extraction for semantic classification and filtering


  • Access via a REST API
  • Java, JavaScript and Python client libraries¬†
  • sandbox API to test the endpoints
  • Free trial API available (fair usage)
  • Available as private AMI instance on Amazon Web Services
  • JSON data format

The free trial API allows access to all endpoints based on the principle of fair use (heavy usage might be throttled or limited. See also our terms of service). The API accesses Retina databases that are based on static versions of Wikipedia. Recent addition to Wikipedia (for example, the term "Brexit") are not included. Upon request, we create customized retinas that are trained with the vocabulary domain of your business or industry. For more information about this premium service, please contact [email protected].