spaCy
Industrial-strength NLP library for Python with pre-trained pipelines for tokenization, NER, parsing, and more.
spaCy
spaCy is a production-ready, industrial-strength NLP library for Python and Cython. It provides pre-trained pipelines for 65+ languages and is designed from the ground up for real applications — prioritizing speed, accuracy, and a clean developer API.
Key Features
- Pre-trained pipelines: Named entity recognition (NER), part-of-speech tagging, dependency parsing, text classification, and sentence segmentation — out of the box for 65+ languages
- Transformer models: Seamlessly integrate BERT, RoBERTa, or any HuggingFace model as a spaCy component
- Custom components: Extend pipelines with your own processing steps using
@Language.component - Rule-based matching:
MatcherandPhraseMatcherfor regex-like matching over linguistic annotations - spaCy Projects: Reproducible NLP workflows with config files, versioning, and remote storage
- Speed: Written in Cython — 5–10x faster than NLTK on most tasks
Quick Start
pip install spacy
python -m spacy download en_core_web_sm
import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("Apple is building a new AI campus in London.")
for ent in doc.ents:
print(ent.text, ent.label_)
# Apple ORG | London GPE
Add to ai-supply
npx ai-supply add spacy-nlp-library
Curated mirror of the open-source spaCy (MIT). 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/spacy-nlp-library/check). Click a policy:
Consume spaCy 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/spacy-nlp-library
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/spacy-nlp-library/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add spacy-nlp-library
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/spacy-nlp-library/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "spacy-nlp-library" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.