Update app.py

app.py

@@ -40,7 +40,11 @@ def extract_text_from_pdf(pdf_file):
     with pdfplumber.open(pdf_file) as pdf:
         text = ""
         for page in pdf.pages:
-            text += page.extract_text() + "\n"  # Add newline for better separation
+            page_text = page.extract_text()
+            if page_text:  # Check if page text is not empty
+                text += page_text + "\n"  # Add newline for better separation
+            else:
+                st.warning("No extractable text found on a page.")
     return text
 
 # Split text into sentences for better matching
@@ -59,12 +63,17 @@ pdf_embeddings = None
 
 if pdf_file:
     pdf_text = extract_text_from_pdf(pdf_file)
-    try:
-        pdf_sentences = split_text_into_sentences(pdf_text)  # Split PDF text into sentences
-        pdf_embeddings = np.array([get_embeddings(sentence) for sentence in pdf_sentences])  # Get embeddings for each sentence
-        st.success("PDF loaded successfully!")
-    except Exception as e:
-        st.error(f"Error while processing PDF: {e}")
+    
+    # Check if the extracted text is empty
+    if not pdf_text.strip():
+        st.error("The extracted PDF text is empty. Please upload a PDF with extractable text.")
+    else:
+        try:
+            pdf_sentences = split_text_into_sentences(pdf_text)  # Split PDF text into sentences
+            pdf_embeddings = np.array([get_embeddings(sentence) for sentence in pdf_sentences])  # Get embeddings for each sentence
+            st.success("PDF loaded successfully!")
+        except Exception as e:
+            st.error(f"Error while processing PDF: {e}")
 
 # User input for chatbot
 user_input = st.text_input("Ask a question about the PDF:")
@@ -90,3 +99,4 @@ if st.button("Get Response"):
         except Exception as e:
             st.error(f"Error while processing user input: {e}")
 
+