# mcp/nlp.py

import spacy

def load_model():
    try:
        return spacy.load("en_core_web_sm")
    except OSError:
        raise RuntimeError(
            "spaCy model 'en_core_web_sm' not found. "
            "Install it in your Dockerfile or requirements.txt before building the app."
        )

nlp = load_model()

def extract_keywords(text: str):
    """Extract entities (longer than 2 chars, no duplicates)."""
    doc = nlp(text)
    return list({ent.text for ent in doc.ents if len(ent.text.strip()) > 2})