Upload headings_extractor.py

headings_extractor.py

@@ -0,0 +1,77 @@
+import openai
+from PyPDF2 import PdfReader
+import fitz
+import os
+
+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.
+        """
+        pass
+
+    def extarct_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
+            response = openai.Completion.create(
+                engine="text-davinci-003",
+                prompt=f"""Extract Headings from given paragraph do not generate jsu extract the headings from paragraph.
+                        ```paragraph :{contract_page}```""",
+                max_tokens=100,
+                temperature=0
+            )
+            headings = response.choices[0].text.strip()
+            return headings
+
+        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 extarct_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.extarct_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)}")