gateswang00/job_ner_skills

Jobs SKILL NER pipeline (spaCy)

Trained spaCy pipeline that labels job-description skills with the SKILL entity. Consumed by jobs-shared (jobs_shared.ai.extraction.skill_extractors.ner.NerSkillExtractor).

• Pipeline: pipeline v0.0.0
• Upstream trainer: scripts/train/train_ner_skills.py in jobs-ai-shared (silver labels from cached Vertex extractions filtered through a canon vocabulary).
• HF repo: gateswang00/job_ner_skills

Load locally

import spacy
from huggingface_hub import snapshot_download

local_dir = snapshot_download(repo_id="gateswang00/job_ner_skills")
nlp = spacy.load(local_dir)
doc = nlp("Strong Python and Kubernetes experience required.")
print([(e.text, e.label_) for e in doc.ents])