File size: 3,823 Bytes
6ff6c37 e5939f7 6ff6c37 0162bcf 76805b5 942ee5a 0162bcf 090afab c4e0123 090afab 0162bcf 090afab 0162bcf 6ff6c37 c2349bd 6ff6c37 |
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 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 |
import torch
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
from typing import List, Dict, Any
import requests
import nltk
from transformers import pipeline
# Download required NLTK models
nltk.download("averaged_perceptron_tagger")
nltk.download("averaged_perceptron_tagger_eng")
# Define your model name
NEL_MODEL = "nel-mgenre-multilingual"
def get_wikipedia_page_props(input_str: str):
if ">>" not in input_str:
page_name = input_str
language = "en"
else:
try:
page_name, language = input_str.split(">>")
page_name = page_name.strip()
language = language.strip()
except:
page_name = input_str
language = "en"
wikipedia_url = f"https://{language}.wikipedia.org/w/api.php"
wikipedia_params = {
"action": "query",
"prop": "pageprops",
"format": "json",
"titles": page_name,
}
qid = "NIL"
try:
response = requests.get(wikipedia_url, params=wikipedia_params)
response.raise_for_status()
data = response.json()
if "pages" in data["query"]:
page_id = list(data["query"]["pages"].keys())[0]
if "pageprops" in data["query"]["pages"][page_id]:
page_props = data["query"]["pages"][page_id]["pageprops"]
if "wikibase_item" in page_props:
return page_props["wikibase_item"], language
else:
return qid, language
else:
return qid, language
else:
return qid, language
except Exception as e:
return qid, language
def get_wikipedia_title(qid, language="en"):
url = f"https://www.wikidata.org/w/api.php"
params = {
"action": "wbgetentities",
"format": "json",
"ids": qid,
"props": "sitelinks/urls",
"sitefilter": f"{language}wiki",
}
response = requests.get(url, params=params)
try:
response.raise_for_status()
data = response.json()
except requests.exceptions.RequestException as e:
return "NIL", "None"
except ValueError as e:
return "NIL", "None"
try:
title = data["entities"][qid]["sitelinks"][f"{language}wiki"]["title"]
url = data["entities"][qid]["sitelinks"][f"{language}wiki"]["url"]
return title, url
except KeyError:
return "NIL", "None"
class NelPipeline:
def __init__(self, model_dir: str = "."):
self.model_name = NEL_MODEL
print(f"Loading {model_dir}")
self.device = "cuda" if torch.cuda.is_available() else "cpu"
self.tokenizer = AutoTokenizer.from_pretrained(model_dir)
self.model = pipeline("generic-nel", model="impresso-project/nel-mgenre-multilingual",
tokenizer=self.tokenizer,
trust_remote_code=True,
device=self.device)
def preprocess(self, text: str):
linked_entity = self.model(text)
return linked_entity
def postprocess(self, outputs):
linked_entity = outputs
return linked_entity
class EndpointHandler:
def __init__(self, path: str = None):
# Initialize the NelPipeline with the specified model
self.pipeline = NelPipeline("impresso-project/nel-mgenre-multilingual")
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
# Process incoming data
inputs = data.get("inputs", "")
if not isinstance(inputs, str):
raise ValueError("Input must be a string.")
# Preprocess, forward, and postprocess
preprocessed = self.pipeline.preprocess(inputs)
results = self.pipeline.postprocess(preprocessed)
return results
|