ai_dataset/import_data/result_objects.py

105 lines
3.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import json
import requests
from decimal import Decimal
TOKEN = 'eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpYXQiOjE3MTg3ODk5OTEsImp0aSI6IlNGaWVOcWIxeEFzZ252QmtvUkxXWU9UbXR2VTNvT3R6IiwiaXNzIjoiaHR0cHM6XC9cL2NwLnRhdmFzaS5pciIsImV4cCI6MTcyMDA4OTk5MCwiYXVkIjoiaHR0cHM6XC9cL2NwLnRhdmFzaS5pciIsImRhdGEiOnsiaWQiOjEsImZpcnN0X25hbWUiOiJcdTA2MjhcdTA2MzFcdTA2NDZcdTA2MjdcdTA2NDVcdTA2NDcgXHUwNjQ2XHUwNjQ4XHUwNmNjXHUwNjMzIiwibGFzdF9uYW1lIjoiXHUwNjQxXHUwNjQ2XHUwNmNjIiwiZW1haWwiOiJkZXZAZ21haWwuY29tIiwidXNlcm5hbWUiOiJkZXYiLCJ1c2VyX2xldmVsIjoyfX0.7DzFqHLee3ZI7EnZYjy5ChtVWhT3QJvBNUbLUdPssSo'
ACCEPT = "application/json"
HEADERS = {"Authorization": TOKEN, "Accept": ACCEPT}
url = "https://api.tavasi.ir/repo/dataset/multi/add/qasection/keyword"
headers = HEADERS
# # باز کردن فایل متنی
# file_path = 'G:/_majles/ner_law_dataset.txt'
# with open(file_path, 'r', encoding='utf-8') as file:
# input_text = file.read()
# # تبدیل متن به لیستی از خطوط
# lines = input_text.strip().split('\n')
file_address = './new_law_excel.xlsx'
# output_file_address = './output/keywords_law_excel.xlsx'
column_name = "content"
contents = read_from_excel(file_address, column_name)
contents_list = []
for index, section in enumerate(contents):
#ner_values = inference_main(model, section)
contents_list.append(section)
# contents_list = contents_list + section + '\n********************\n'
new_column_name = 'content_keywords'
key = ''
begin = -1
end = -1
tokenNumber = -1
content = ''
result_token = []
class JSONEncoder(json.JSONEncoder):
def default(self, obj):
if isinstance(obj, Decimal):
return float(obj)
return json.JSONEncoder.default(self, obj)
# content : main text/content
# results : keywords list
def createIndex(content, extracted_keywords):
result_objects = [{
"task":"keyword",
"key":"lama3-8b",
"label":"لاما3 فارسی شده",
"values":extracted_keywords
} ]
output ={
"content": content,
"domain": "مقررات",
"ref_id": "",
"ref_url": "",
"result_objects": result_objects,
}
# print(output)
# print(json.dumps(output, indent=4, ensure_ascii=False))
return output
bulk_data = []
bulk_count = 1
count = 0
for mentry in contents_list:
count += 1
tokenNumber = tokenNumber + 1
extracted_keywords = []
data=createIndex(mentry, extracted_keywords)
bulk_data.append(data)
bulk_count +=1
if bulk_data.__len__() > 10:
print('=' * 10 )
print('count' + str(count))
payload = json.dumps(bulk_data, cls=JSONEncoder) #Works!
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
bulk_data = []
bulk_count = 1
if bulk_data.__len__() > 0:
print(bulk_count)
payload = json.dumps(bulk_data, cls=JSONEncoder) #Works!
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
# نمایش دیکشنری خروجی به صورت JSON
print("***************** end ")