Spaces:
Running
Running
| from openai import AzureOpenAI | |
| from PyPDF2 import PdfReader | |
| import os | |
| import gradio as gr | |
| class HeadingsExtractor: | |
| def __init__(self): | |
| """ | |
| Extract headings from a given paragraph using OpenAI's GPT-3. | |
| Args: | |
| contract_page (str): The paragraph from which headings need to be extracted. | |
| Returns: | |
| str: Extracted headings. | |
| """ | |
| # 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 file_output_fnn(self,file_path): | |
| file_path = file_path.name | |
| return file_path | |
| def extract_headings(self,contract_page: str) -> str: | |
| """ | |
| Extract headings from a given paragraph using OpenAI's GPT-3. | |
| Args: | |
| contract_page (str): The paragraph from which headings need to be extracted. | |
| Returns: | |
| str: Extracted headings. | |
| """ | |
| try: | |
| #get response from openai api | |
| 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"""Extract Headings from given paragraph do not generate jsu extract the headings from paragraph. | |
| ```paragraph :{contract_page}```"""} | |
| ] | |
| # 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 | |
| print(f"Error while extracting headings: {str(e)}") | |
| def extract_text(self,pdf_file_path: str) -> str: | |
| """ | |
| Extract text from a PDF document and extract headings from each page. | |
| Args: | |
| pdf_file_path (str): Path to the PDF file to extract text from. | |
| Returns: | |
| str: Extracted headings from the PDF document. | |
| """ | |
| try: | |
| # Open the multi-page PDF using PdfReader | |
| print("path",pdf_file_path) | |
| pdf = PdfReader(pdf_file_path.name) | |
| headings = '' | |
| # 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 | |
| result = self.extract_headings(text) | |
| headings = headings + result | |
| return headings | |
| except Exception as e: | |
| # If an error occurs during the key-value extraction process, log the error | |
| print(f"Error while extracting text from PDF: {str(e)}") | |
| def gradio_interface(self): | |
| with gr.Blocks(css="style.css",theme='xiaobaiyuan/theme_brief') as demo: | |
| with gr.Row(elem_id = "col-container",scale=0.80): | |
| with gr.Column(elem_id = "col-container",scale=0.80): | |
| file1 = gr.File(label="File",elem_classes="filenameshow") | |
| with gr.Column(elem_id = "col-container",scale=0.20): | |
| upload_button1 = gr.UploadButton( | |
| "Browse File",file_types=[".txt", ".pdf", ".doc", ".docx",".json",".csv"], | |
| elem_classes="uploadbutton") | |
| headings_btn = gr.Button("Get Headings",elem_classes="uploadbutton") | |
| with gr.Row(elem_id = "col-container",scale=0.60): | |
| headings = gr.Textbox(label = "Headings") | |
| upload_button1.upload(self.file_output_fnn,upload_button1,file1) | |
| headings_btn.click(self.extract_text,upload_button1,headings) | |