![](https://d7umqicpi7263.cloudfront.net/img/product/25228140-4208-460c-940c-7026cecb9440/b5a39304-c88d-499d-9ad6-61c9bbfce711.png)
![](https://d7umqicpi7263.cloudfront.net/img/product/25228140-4208-460c-940c-7026cecb9440/b5a39304-c88d-499d-9ad6-61c9bbfce711.png)
Document Lens
Linux/Unix
Product Overview
The Document Lens recognises and extracts entities from text files in the PDF, DOCX, and TXT formats. Based on a scalable Natural Language Processing pipeline, the Lens can be easily configured to retrieve entities belonging to a multi-domain knowledge graph or any dataset accessible via a SPARQL endpoint. With provenance as standard, this lightweight, highly-scalable, platform-agnostic tool has support for all the common Knowledge Graphs and generic SPARQL support for the less common.