File size: 423 Bytes
030432c
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
from transformers import pipeline

ner_pipeline = pipeline("ner", model="dslim/bert-base-NER", grouped_entities=True)

def extract_ingredients(text):
    entities = ner_pipeline(text)
    ingredients = []
    for ent in entities:
        word = ent['word'].lower().strip()
        if ent['entity_group'] == 'MISC' and word.isalpha() and len(word) > 2:
            ingredients.append(word)
    return list(set(ingredients))