OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Pytorch Ie

PyTorch-IE is an experimental Python framework for building information-extraction systems with PyTorch, including named-entity recognition, relation extraction and relation classification. It structures projects around documents, task modules and models, with support for document-based data and annotations.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pytorch Ie — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use PyTorch-IE when building or experimenting with a PyTorch-based extraction workflow and you want to define how documents, annotations, model logic and task conversion fit together.

Who it is for

  • Python developers implementing information-extraction methods.
  • Researchers experimenting with entity recognition and relation tasks across datasets.
  • Teams that want control over document preparation and model structure.

Documented uses

  • Represent documents and their entity or relation annotations in a reusable format.
  • Build model and task-module components for information-extraction workflows.
  • Develop extraction experiments on datasets, including document-level and non-plain-text inputs.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed. The README documents installation with pip.

  • The framework leaves document preparation and model structure under developer control through use-case-specific Document, Taskmodule and Model classes.
  • PyTorch Lightning is identified for training and logging, while Hugging Face Datasets is identified for dataset reading.
  • Hugging Face Evaluate support is described as coming soon in the README, rather than as an established component there.
  • The repository describes the framework as experimental.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a PyTorch-IE development environment

Install repository dependencies, including development dependencies.

Before you start

  • Poetry installed.
  • The PyTorch-IE repository checked out locally.

Steps

  1. From the repository root, run poetry install --with dev.

  2. If installation gets stuck, try poetry config experimental.new-installer false.

Expected outcome

The repository dependencies, including development dependencies, are installed through Poetry.

Guide limitations

  • The guide covers development setup, not running tests or building an extraction pipeline.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
ArneBinder/pytorch-ie · Official homepage title · retained in its source language
How we review sourcesSuggest a correction