Information Extraction Python Packages

htmldate

Fast and robust date extraction from web pages, with Python or on the command-line

llama-cloud

Python SDK for OCR and document parsing in the cloud with LlamaParse

gliner

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)

eventregistry

Python package for API access to news articles and events in the Event Registry

abbreviations

Python3 implementation of the Schwartz-Hearst algorithm for extracting abbreviation-definition pairs

yargy

Rule-based facts extraction for Russian language

geotext

Geotext extracts country and city mentions from text

adaseq

AdaSeq: An All-in-One Library for Developing State-of-the-Art Sequence Understanding Models

glirel

Generalist and Lightweight Model for Relation Extraction (Extract any relationship types from text)

numerizer

A Python module to convert natural language numerics into ints and floats.

huspacy

HuSpaCy: industrial-strength Hungarian natural language processing

paddlenlp

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

deduce

Deduce: de-identification method for Dutch medical text

solvi

A runtime where decision models propose and your code decides: typed questions, hard rules, quotes checked against the text, escalation with a guaranteed error budget, replayable traces. Works with any System One model.

hyperextract

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

tool-helpers

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

groundgate

Deterministic admission for LLM-extracted facts: admit, flag for review, or reject, with verifiable receipts.

chemdataextractor

Automatically extract chemical information from scientific documents

brevia

Extensible API and framework to build your Retrieval Augmented Generation (RAG) and Information Extraction (IE) applications with LLMs

lettucedetect

Span-level grounding verification for RAG, code, and tool-grounded AI outputs.

fast-dataindex

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

sci-etl-core

Async-first, domain-agnostic Python toolkit for mining scientific literature: LLM-powered ETL pipelines with pluggable extractors, parsers, exporters, and resumable state.

pytorch-ie

PyTorch-IE: State-of-the-art Information Extraction in PyTorch

fieldproof

Document extraction that shows its work: every LLM-extracted field grounded to its source words, verified, and reviewable.