Update app.py

app.py

@@ -16,10 +16,11 @@ import shap
 # PDF and OCR Processing
 import pdfplumber
 import pytesseract
-from pdf2image import convert_from_path
+from pdf2image import convert_from_bytes
 import spacy
 from spacy import displacy
 from sentence_transformers import SentenceTransformer
+import io
 
 # Machine Learning
 from sklearn.impute import SimpleImputer
@@ -58,17 +59,25 @@ from transformers import TFBertForSequenceClassification
 # --------------------------
 pytesseract.pytesseract.tesseract_cmd = r'/usr/bin/tesseract'  # Update this path if Tesseract is installed elsewhere
 
-def extract_text_from_pdf(pdf, ocr_enabled):
-    pages = convert_from_path(pdf, 500)
+
+def extract_text_from_pdf(pdf_file, ocr_enabled):
+    # Convert the uploaded file to bytes and read it
+    pdf_bytes = pdf_file.read()
+
+    # Convert the PDF bytes to images
+    pages = convert_from_bytes(pdf_bytes, 500)
+
     text = ""
     for page in pages:
         if ocr_enabled:
             text += pytesseract.image_to_string(page)
         else:
-            text += page.get_text()
+            # As we don't have a 'get_text()' method for images, use pytesseract
+            text += pytesseract.image_to_string(page)
     return text
 
 
+
 def enhance_section_title(title, icon="✨"):
     """Helper function to create a styled section title with an icon."""
     st.markdown(f"<h2 style='border-bottom: 2px solid #ccc; padding-bottom: 5px;'>{icon} {title}</h2>", unsafe_allow_html=True)