File size: 1,875 Bytes
0a3aede
 
1974999
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a3aede
1974999
 
 
 
 
 
 
0a3aede
1974999
 
0375bcb
 
1974999
0375bcb
1974999
 
 
 
bb95791
0a3aede
1974999
 
 
 
 
 
 
0a3aede
1974999
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
# mcp/nlp.py

#!/usr/bin/env python3
"""MedGenesis – spaCy helper for lightweight keyword extraction.

Features
~~~~~~~~
* Lazy‑loads **`en_core_web_sm`** at first call; cached thereafter.
* If model missing, raises actionable RuntimeError — Dockerfile must
  install via `python -m spacy download en_core_web_sm` (already in Dockerfile).
* `extract_keywords` returns **unique named‑entity strings** (>2 chars)
  stripped of whitespace, preserving original casing.
* Adds fallback to simple noun‑chunk extraction when no entities found –
  helps very short abstracts.
"""
from __future__ import annotations

import spacy
from functools import lru_cache
from typing import List


# ---------------------------------------------------------------------
# Model loader (cached)
# ---------------------------------------------------------------------

@lru_cache(maxsize=1)
def _load_model():
    try:
        return spacy.load("en_core_web_sm")
    except OSError as e:
        raise RuntimeError(
            "spaCy model 'en_core_web_sm' is not installed. Add\n"
            "    RUN python -m spacy download en_core_web_sm\n"
            "to your Dockerfile build stage."
        ) from e


# ---------------------------------------------------------------------
# Public API
# ---------------------------------------------------------------------

def extract_keywords(text: str, *, min_len: int = 3) -> List[str]:
    """Return de‑duplicated entity keywords (fallback noun chunks)."""
    nlp = _load_model()
    doc = nlp(text)

    ents = {ent.text.strip() for ent in doc.ents if len(ent.text.strip()) >= min_len}
    if ents:
        return list(ents)

    # Fallback: noun chunks if spaCy found no entities (rare for tiny texts)
    chunks = {chunk.text.strip() for chunk in doc.noun_chunks if len(chunk.text.strip()) >= min_len}
    return list(chunks)