J

json

Labels blocks of a PDF-JSON document according to document structuring rules

The service performs the classification of text blocks in PDF documents described in JSON files.

Converts DOCX documents into a structured JSON representation

Analyzes noun tokens in a given text fragment and identifies those referring to human beings.

The service segments natural language text into sentences and then extracts individual phrases built around identified activities.

A Pydantic-based data model for representing and validating NLP document analysis results in a standardized JSON format

Includes JSON model created with Pydantic for JSON documents transformed from PDF documents

Includes JSON model created with Pydantic for JSON documents transformed from DOCX documents