Spaces:
Running
Running
File size: 3,795 Bytes
4ec3e55 13585f0 4ec3e55 5f94468 4ec3e55 7bac9bd 4ec3e55 6156244 c425da2 4ec3e55 59cf6d7 8c48eff 59cf6d7 f780a7e 59cf6d7 8c48eff 4ec3e55 |
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 |
from PyPDF2 import PdfReader
from openai import AzureOpenAI
import logging
import os
# Configure logging
logging.basicConfig(
filename='extract_date.log', # You can adjust the log file name here
filemode='a',
format='[%(asctime)s] [%(levelname)s] [%(filename)s] [%(lineno)s:%(funcName)s()] %(message)s',
datefmt='%Y-%b-%d %H:%M:%S'
)
LOGGER = logging.getLogger(__name__)
log_level_env = 'INFO' # You can adjust the log level here
log_level_dict = {
'DEBUG': logging.DEBUG,
'INFO': logging.INFO,
'WARNING': logging.WARNING,
'ERROR': logging.ERROR,
'CRITICAL': logging.CRITICAL
}
if log_level_env in log_level_dict:
log_level = log_level_dict[log_level_env]
else:
log_level = log_level_dict['INFO']
LOGGER.setLevel(log_level)
class ExtractDateAndDuration:
def __init__(self):
"""
Initialize the ExtractDateAndDuration class.
"""
# openai.api_type = os.getenv['api_type']
# openai.api_base = os.getenv['api_base']
# openai.api_version = os.getenv['api_version']
# openai.api_key = os.getenv['api_key']
pass
def get_date_and_duration(self, contract_text: str) -> str:
"""
Extract dates and durations from the provided contract text.
Args:
contract_text (str): The text of the contract to analyze.
Returns:
str: Extracted dates and durations.
"""
try:
client = AzureOpenAI(api_key=os.getenv("AZURE_OPENAI_KEY"),
api_version="2023-07-01-preview",
azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
)
conversation = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": f"""Your task is Identify Dates and Durations Mentioned in the contract and extract that date and duration in key-value pair.
```contract: {contract_text}```
format:
date:extracted date
Durations:extracted Durations
"""}
]
# Call OpenAI GPT-3.5-turbo
chat_completion = client.chat.completions.create(
model = "GPT-3",
messages = conversation,
max_tokens=1000,
temperature=0
)
response = chat_completion.choices[0].message.content
return response
except Exception as e:
LOGGER.error(f"An error occurred during text analysis: {str(e)}")
def itrate_each_page(self, pdf_file_path: str):
"""
Extract text from each page of a PDF document and process it.
Args:
pdf_file_path (str): The path to the PDF document.
Returns:
str: Extracted text from the PDF pages.
"""
try:
# Open the multi-page PDF using PdfReaderer
pdf = PdfReader(pdf_file_path.name)
extracted_date_duration = ""
# Extract text from each page and pass it to the process_text function
for page_number in range(len(pdf.pages)):
# Extract text from the page
page = pdf.pages[page_number]
text = page.extract_text()
# Pass the text to the process_text function for further processing
extracted_date_duration += self.get_date_and_duration(text)
return extracted_date_duration
except Exception as e:
LOGGER.error(f"An error occurred while processing the PDF document: {str(e)}")
|