Update app.py

app.py

@@ -9,6 +9,7 @@ together.api_key = "8052996318422f1b9470840fc6ebc94e80676391f07e71cc15951b08bb43
 
 def clean_text(text):
     """Cleans extracted text for better processing by the model."""
+    print("cleaning")
     text = unicodedata.normalize("NFKC", text)  # Normalize Unicode characters
     text = re.sub(r'\s+', ' ', text).strip()  # Remove extra spaces and newlines
     text = re.sub(r'[^a-zA-Z0-9.,!?;:\'\"()\-]', ' ', text)  # Keep basic punctuation
@@ -17,6 +18,7 @@ def clean_text(text):
 
 def extract_text_from_pdf(pdf_file):
     """Extract and clean text from the uploaded PDF."""
+    print("extracting")
     try:
         with pdfplumber.open(pdf_file) as pdf:
             text = " ".join(clean_text(text) for page in pdf.pages if (text := page.extract_text()))
@@ -27,10 +29,12 @@ def extract_text_from_pdf(pdf_file):
 
 def split_text(text, chunk_size=500):
     """Splits text into smaller chunks for better processing."""
+    print("splitting")
     return [text[i:i+chunk_size] for i in range(0, len(text), chunk_size)]
 
 def chatbot(pdf_file, user_question):
     """Processes the PDF and answers the user's question."""
+    print("chatbot start")
     
     # Extract text from the PDF
     text = extract_text_from_pdf(pdf_file)