Natural Language Processing API | Developer Portal | Natural Language Processing API | Developer Portal |

Unlock efficiency with semantic fingerprints

Transform text into semantic fingerprints for pinpoint accuracy with minimal computing resources

Get Started
Where transformers impose a trade-off, semantic fingerprints enable a unique combination of high speed and accuracy.

Semantic fingerprints capture the different meanings of words based on thousands of parameters and form clusters of similar contexts. For document processing tasks like classification and semantic search, the system just needs to measure semantic overlaps between semantic fingerprints - a highly efficient computational approach that powers the processing of very large amounts of text with less computing resources.

Game-Changing approach to Natural Language Processing

With semantic fingerprints, you can:

  • Compare words, sentences and whole texts to each other.
  • Perform meaning-based classification of text and semantic search by simply measuring the overlap of semantic fingerprints.
  • Train custom models with little training data in an unsupervised manner.
API Spec
Digital illustration of a semantic fingerprint showing three layers containing a pixel grid with color coded pixels.
Blue icon depicting a tag attached to file, set against a white background.


Instead of training the classifier with many labeled examples, one reference fingerprint can be used to describe a class. This can be used for real-time classification of emails or social media posts, or for screening candidate profiles for example.

Blue icon depicting a magnifying lense set against a white background.

Semantic search

With semantic fingerprints, queries in natural language can be directly compared with the indexed documents, improving both recall and precision. This can boost intranet search.

A stylized, blue icon depicting a rocket set against a white background.

Model training

With semantic fingerprints, language models can be trained with comparatively little training data and computing resources while achieving similar accuracy levels as with transformers.

Customer Voices

How TBS business school is using semantic fingerprints to analyze large amounts of news

Transparent and fair pricing

Get started for free!

Ready to start? Whether you want to test our API or integrate it in an enterprise application, we have the right plan for you.

SF API - Free Plan

  • Up to 500,000 requests / month
  • Max. 15 requests / second
Start with this plan

Custom Plan

  • Unlimited requests
  • Maximum throughput
Contact Us

For custom plans, please contact us

Sparse distributed representation of text

Learn more about semantic fingerprints

Semantic fingerprints encapsulate all meanings associated with a text in a topographical representation where similar meanings are placed close to each other.

Semantic fingerprints allow direct comparison of the meanings of any two pieces of text, showing thousands of semantic relations.

If two semantic fingerprints look similar, it means that the texts are semantically similar too.

Digital illustration of a semantic fingerprint for the word 'organ'. Set against an orange background.

Context 1

liver, heart, muscle, endothelia, body, anatomy

Context 2a

composer, baroque, music, score, Bach

Context 2b

piano, guitar, trombone, flute, trumpet, music

Context 3

church, altar, baroque, architecture, renaissance
Digital illustration of a semantic fingerprint for the word 'organ'. Set against an orange background.
Semantic fingerprint of the word "Organ"

Semantic Fingerprints simply explained

Watch a short video