entity_extractor

Entity Extractor

v0.1.2MITValidatedOutdated — v0.1.3 available2 installs3/12/2026pipelex/methodsEvotis S.A.S
Main pipeextract_entities

Install

$npx mthds install https://github.com/pipelex/methods --method entity_extractor

Run

$npx mthds run method entity_extractor

Entity Extractor

Extract named entities (persons, organizations, dates, amounts, locations, products, regulations) from any document.

What it does

Given a document (PDF, Word, etc.), this method:

  1. Extracts content from the document into readable pages
  2. Identifies all named entities with type classification, surrounding context, and normalized values

Concepts

  • Entity: A named entity with name, entity_type, context, and optional normalized_value

Exports

entity_extraction

extract_entitiesidentify_entities

Method Flowchart

Loading diagram…

Bundle Files

Select a file to view its contents

METHODS.toml

METHODS.toml
[package]
name = "entity_extractor"
display_name = "Entity Extractor"
address = "github.com/pipelex/methods"
version = "0.1.2"
description = "# Entity Extractor\n\nExtract named entities (persons, organizations, dates, amounts, locations, products, regulations) from any document.\n\n## What it does\n\nGiven a **document** (PDF, Word, etc.), this method:\n\n1. **Extracts** content from the document into readable pages\n2. **Identifies** all named entities with type classification, surrounding context, and normalized values\n\n## Concepts\n\n- **Entity**: A named entity with `name`, `entity_type`, `context`, and optional `normalized_value`"
license = "MIT"
authors = ["Evotis S.A.S"]
main_pipe = "extract_entities"

[exports.entity_extraction]
pipes = ["extract_entities", "identify_entities"]