Spaces:
Running
Running
| import os | |
| import PyPDF2 | |
| from langchain import PromptTemplate, LLMChain | |
| from langchain.llms import OpenAI | |
| class PdftoJson: | |
| def __init__(self): | |
| """ | |
| Initialize the PdftoJson class with OpenAI API key. | |
| """ | |
| # OPENAI_API_KEY = "" | |
| # os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY | |
| def _get_json(self, input_text: str) -> str: | |
| """ | |
| Generate JSON result by analyzing and splitting input text into topics and content. | |
| Args: | |
| input_text (str): Text to be analyzed. | |
| Returns: | |
| str: JSON result containing topics and content. | |
| """ | |
| try: | |
| # Initialize the OpenAI language model with specified settings | |
| llm = OpenAI(temperature=0, max_tokens=1000) | |
| # Define a template that instructs the model to split input text into topics and content | |
| template = """ | |
| Your task is Get the text and analyse and split it into Topics and Content in json format.Give Proper Name to Topic dont give any Numbers and Dont Give any empty Contents.The Output Format Should Be very good. | |
| {text} | |
| """ | |
| prompt = PromptTemplate(template=template, input_variables=["text"]) | |
| # Create an LLMChain instance to chain the prompt and language model together | |
| llm_chain = LLMChain(prompt=prompt, llm=llm) | |
| # Use the provided input text to generate JSON result using the model | |
| text = input_text | |
| json_result = llm_chain.run(text) | |
| return json_result | |
| except Exception as e: | |
| print(f"Error occurred while generating JSON result: {str(e)}") | |
| def extract_text_from_pdf(self, pdf_path: str): | |
| """ | |
| Extract text from a PDF file, generate JSON result, and save it to a file. | |
| Args: | |
| pdf_path (str): Path to the PDF file. | |
| """ | |
| try: | |
| # Open the PDF file in binary read mode | |
| with open(pdf_path.name, "rb") as pdf_file: | |
| # Create a PDF reader object | |
| pdf_reader = PyPDF2.PdfReader(pdf_file) | |
| # Iterate through each page in the PDF | |
| for page_number in range(len(pdf_reader.pages)): | |
| # Extract text from the current page | |
| page = pdf_reader.pages[page_number] | |
| text = page.extract_text() | |
| # Generate JSON result for the extracted text | |
| json_result = self._get_json(text) | |
| # # Clear Extra Spaces | |
| # clear_json_result = self._remove_empty_lines(json_result) | |
| # # Save the JSON result to a file | |
| # self._save_json(clear_json_result) | |
| return json_result | |
| except Exception as e: | |
| print(f"Error occurred during extraction and processing: {str(e)}") | |