Update app.py

app.py

@@ -6,14 +6,18 @@ import fitz  # PyMuPDF
 qa_model = pipeline("question-answering", "timpal0l/mdeberta-v3-base-squad2")
 
 # Function to extract text from a PDF file
-def extract_text_from_pdf(pdf_file):
-    doc = fitz.open(pdf_file)
-    text = ""
-    for page_num in range(doc.page_count):
-        page = doc[page_num]
-        text += page.get_text()
-    doc.close()
-    return text
+def extract_text_from_pdf(uploaded_file):
+    try:
+        doc = fitz.open(stream=uploaded_file, filetype="pdf")
+        text = ""
+        for page_num in range(doc.page_count):
+            page = doc[page_num]
+            text += page.get_text()
+        doc.close()
+        return text
+    except Exception as e:
+        st.error(f"Error extracting text from PDF: {str(e)}")
+        return None
 
 # Streamlit app
 def main():
@@ -26,22 +30,23 @@ def main():
         # Read the PDF file and extract text
         pdf_text = extract_text_from_pdf(uploaded_file)
 
-        # Display the extracted text
-        st.subheader("Extracted Text from PDF")
-        st.text(pdf_text)
-
-        # Input for user question
-        question = st.text_input("Ask a question about the PDF:")
-
-        # Button to trigger question answering
-        if st.button("Get Answer"):
-            if question:
-                # Use the QA model to get the answer
-                answer = qa_model(question=question, context=pdf_text)
-                st.subheader("Answer:")
-                st.write(answer["answer"])
-            else:
-                st.warning("Please enter a question.")
+        if pdf_text is not None:
+            # Display the extracted text
+            st.subheader("Extracted Text from PDF")
+            st.text(pdf_text)
+
+            # Input for user question
+            question = st.text_input("Ask a question about the PDF:")
+
+            # Button to trigger question answering
+            if st.button("Get Answer"):
+                if question:
+                    # Use the QA model to get the answer
+                    answer = qa_model(question=question, context=pdf_text)
+                    st.subheader("Answer:")
+                    st.write(answer["answer"])
+                else:
+                    st.warning("Please enter a question.")
 
 if __name__ == "__main__":
     main()