import openai import pdfplumber import logging # Configure logging logging.basicConfig( filename='contract_missing_clausses.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 ContractMissingClauses: """ Class for identifying missing clauses, sub-clauses, and terms in a contract. """ def __init__(self): """ Initialize the ContractMissingClauses class and set up the OpenAI API client. """ pass def get_missing_clauses(self, contract: str): """ Generate and print missing clauses, sub-clauses, and terms in the given contract. Args: contract (str): The text of the contract. """ try: LOGGER.info("Analyzing contract and extracting missing clauses...") # Generate text using the OpenAI GPT-3 model response = openai.Completion.create( engine="text-davinci-003", # You can specify different engines prompt="identify missing clauses,sub-clauses and terms from given contrct ***{contract}*** return only missing (clauses,sub-clauses and terms) seperately.", temperature=0, max_tokens=500, # The maximum number of tokens (words) in the generated text ) # Print the generated text return response.choices[0].text except Exception as e: # If an error occurs during the key-value extraction process, log the error LOGGER.error(f"Error occurred while extracting missing clauses: {str(e)}") def iterate_each_page(self,pdf_file): """ Iterate through each page of a PDF contract, extract text, and call get_missing_clauses for each page. """ try: LOGGER.info("Analyzing contract and extracting pdf page...") # Initialize pdfplumber pdf = pdfplumber.open(pdf_file.name) # Iterate through each page and extract text for page in pdf.pages: contract = page.extract_text() self.get_missing_clauses(contract) except Exception as e: # If an error occurs during the key-value extraction process, log the error LOGGER.error(f"Error occurred while extracting pdf page: {str(e)}")