Create app.py (#10)

- Create app.py (7c6a41d0440367755939c63cb5486541b7a93ed0)

app.py

@@ -13,14 +13,15 @@ base_model = AutoModelForSeq2SeqLM.from_pretrained("MBZUAI/LaMini-Flan-T5-248M")
 
 # Function to extract text from a PDF using PyPDF2
 def extract_text_from_pdf(pdf_path):
-      reader = PdfReader(pdf_path)
-      text = ""
-      for page in reader.pages:
-          text += page.extract_text()  # Extract text from each page
-      if not text.strip():
-          raise ValueError("The PDF file contains no extractable text.")
-      return text
-
+    reader = PdfReader(pdf_path)
+    text = ""
+    for page in reader.pages:
+        page_text = page.extract_text()
+        if page_text:  # Only add page text if it exists
+            text += page_text
+    if text.strip():
+        return text
+    return None
 
 # LLM pipeline for summarization
 def llm_pipeline(input_text):
@@ -37,16 +38,14 @@ def llm_pipeline(input_text):
 @st.cache_data
 # Function to display the PDF
 def displayPDF(file_path):
-    
-      with open(file_path, "rb") as f:
-          base64_pdf = base64.b64encode(f.read()).decode('utf-8')
-      pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="100%" height="600" type="application/pdf"></iframe>'
-      st.markdown(pdf_display, unsafe_allow_html=True)
-
+    with open(file_path, "rb") as f:
+        base64_pdf = base64.b64encode(f.read()).decode('utf-8')
+    pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="100%" height="600" type="application/pdf"></iframe>'
+    st.markdown(pdf_display, unsafe_allow_html=True)
 
 # Streamlit App
 def main():
-    st.title('Content Summarizer')
+    st.title('PDF Content Summarizer')
 
     # PDF Upload Section
     uploaded_file = st.file_uploader("Upload your PDF file", type=['pdf'])