from openai import AzureOpenAI from PyPDF2 import PdfReader import logging import os # 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. """ # 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_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 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 incomplete sentences finder"}, {"role": "user", "content": f"""list out the incomplete sentences in the following text: {contract}"""} ] # 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: # 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_path): """ 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...") result = '' pdf = PdfReader(pdf_file_path.name) # 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() result += self.get_missing_clauses(text) return result 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)}")