Update incompletesentencefinder.py

incompletesentencefinder.py

@@ -1,4 +1,4 @@
-import fitz  # PyMuPDF
+from PyPDF2 import PdfReader
 import openai
 import gradio as gr
 
@@ -17,8 +17,7 @@ class IncompleteSentenceFinder:
         Args:
             api_key (str): Your OpenAI API key.
         """
-        # openai.api_key = openai_api_key
-        pass
+        self.client = OpenAI()
 
     def _check_incomplete_sentence(self, text: str) -> str:
 
@@ -31,19 +30,20 @@ class IncompleteSentenceFinder:
           Returns:
               str: Incomplete sentences identified by GPT-3.
           """
-          # Create a request to OpenAI's GPT-3 engine to identify incomplete sentences.
-          response = openai.Completion.create(
-              engine="text-davinci-003",
-              prompt=f"list out the incomplete sentences in the following text:\n{text}",
-              max_tokens=1000,
+          conversation = [
+                        {"role": "system", "content": "You are a helpful incomplete sentences finder"},
+                        {"role": "user", "content": f"""list out the incomplete sentences in the following text: {text}"""}
+                        ]
+                    
+          # Call OpenAI GPT-3.5-turbo
+          chat_completion = self.client.chat.completions.create(
+            model = "gpt-3.5-turbo",
+            messages = conversation,
+            max_tokens=500,
+            temperature=0
           )
-
-          # Extract and strip the text of identified incomplete sentences from the GPT-3 response.
-          incomplete_sentences = response.choices[0].text.strip()
-
-          print("incomplete_sentences Extracted Successfully!")
-
-          return incomplete_sentences
+          response = chat_completion.choices[0].message.content
+          return response
 
     def get_incomplete_sentence(self,pdf_file) -> str:
 
@@ -54,13 +54,17 @@ class IncompleteSentenceFinder:
             str: Incomplete sentences identified by GPT-3.
         """
         try:
-            # Open the PDF file using PyMuPDF's fitz library
-            doc = fitz.open(pdf_file.name)
+            # Open the multi-page PDF using PdfReaderer
+            pdf = PdfReader(pdf_file_path)
+    
             incomplete_text = ""
-
-            # Iterate through each page in the PDF document and extract the text
-            for page in doc:
-                text = page.get_text()
+    
+            # 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()
                 incomplete_text += self._check_incomplete_sentence(text)
 
             return incomplete_text