Apache OpenNLP — NLP Toolkit for Legal Documents
Apache-licensed Java/Python NLP toolkit with tokenization, sentence detection, NER, POS tagging, and chunking — production-ready for legal document pipelines.
Apache OpenNLP — NLP Toolkit for Legal Documents
Apache OpenNLP is a mature, production-grade NLP toolkit from the Apache Software Foundation. It provides a full suite of language processing components — tokenizer, sentence detector, part-of-speech tagger, named entity finder, chunker, parser, and coreference resolver — implemented as trainable maximum-entropy models. Widely used in legal document pipelines for court filing processing, regulatory text extraction, and contract analysis in enterprise Java environments.
Key Features
- Full NLP pipeline: tokenize → sentence detect → POS tag → NER → parse
- Trainable on domain-specific corpora (legal, medical, financial)
- REST service via OpenNLP Sandbox for microservice deployments
- Python bindings available via
opennlp-python - Apache-2.0 — clear IP for commercial legal software
Quick Start
# Via opennlp Python wrapper
pip install opennlp
import opennlp
nlp = opennlp.OpenNLP("/path/to/models/")
sentences = nlp.sentence_detector("The plaintiff filed suit. The court denied relief.")
tokens = nlp.tokenizer(sentences[0])
pos_tags = nlp.pos_tagger(tokens)
print(list(zip(tokens, pos_tags)))
npx ai-supply add apache-opennlp
Curated mirror of the open-source Apache OpenNLP (Apache-2.0). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/apache-opennlp/check). Click a policy:
Consume Apache OpenNLP — NLP Toolkit for Legal Documents programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/apache-opennlp
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/apache-opennlp/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add apache-opennlp
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/apache-opennlp/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "apache-opennlp" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.