final solution

spacy-spanmarker-final.py

from flask import Flask, request
from datasets import load_dataset, Dataset
import json
from nltk.tokenize import sent_tokenize, word_tokenize

nlp = spacy.load("en_core_web_trf")
nlp.add_pipe("span_marker",config={"model": "lxyuan/span-marker-bert-base-multilingual-cased-multinerd"})

app = Flask(__name__)

@app.route("/people", methods=['POST'])
def people():
   data = request.json
   content = data.get('content')
   entities = extract_people(text = content, model=SpanMarkerModel)
   return  {
       "entities": entities,
   }

def extract_people(text:str, model)->set:
 docs = [word_tokenize(sent) for sent in sent_tokenize(text)]
 data_dict = {
     "tokens": [],
     "document_id": [],
     "sentence_id": [],
 }

 for sentence_id, sentence in enumerate(docs):
     data_dict["document_id"].append(0)
     data_dict["sentence_id"].append(sentence_id)
     data_dict["tokens"].append(sentence)

 dataset = Dataset.from_dict(data_dict)

 entities = nlp.predict(dataset)

 people_only = [entity for doc in entities for entity in doc if entity.label_ in ['PER', 'PERSON']

 def format_people(people_list):
     formatted_names = []
     for person in people_list:
         name = ' '.join(person['span'])
         formatted_names.append(name)
     return formatted_names

 return format_people(people_only)

if __name__ == "__main__":
 app.run()