Update src/streamlit_app.py

src/streamlit_app.py

@@ -6,69 +6,56 @@ import streamlit as st
 import fitz  # PyMuPDF
 from transformers import pipeline
 
-# Security configuration
+# App configuration
 st.set_page_config(
     page_title="PrepPal",
     page_icon="📘",
-    layout="wide",
-    menu_items={'About': "PrepPal - AI-powered PDF summarizer"}
+    layout="wide"
 )
 
-# Fix for 403 errors
+# Security headers
 st.markdown("""
-    <meta http-equiv="Content-Security-Policy" content="default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline'; img-src 'self' data:;">
+<meta http-equiv="Content-Security-Policy" content="default-src 'self'; script-src 'self' 'unsafe-inline'">
 """, unsafe_allow_html=True)
 
 @st.cache_resource
-def load_summarizer():
+def load_model():
     try:
         return pipeline(
-            "summarization", 
-            model="facebook/bart-large-cnn",  # Reliable model
-            device=-1  # Force CPU for Hugging Face Spaces
+            "summarization",
+            model="Falconsai/text_summarization",  # Smaller model for Spaces
+            device=-1  # Use CPU
         )
     except Exception as e:
-        st.error(f"Model loading failed: {str(e)}")
+        st.error(f"Failed to load model: {str(e)}")
         return None
 
-def safe_extract_text(uploaded_file):
-    """Secure PDF text extraction with temp files"""
+def process_pdf(uploaded_file):
     try:
-        # First save to temporary file
         with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
             tmp.write(uploaded_file.getbuffer())
             tmp_path = tmp.name
         
-        # Process from filesystem
         with fitz.open(tmp_path) as doc:
             text = "\n".join([page.get_text() for page in doc])
         
-        # Clean up
         os.unlink(tmp_path)
         return text.strip()
     except Exception as e:
-        st.error(f"PDF processing error: {str(e)}")
+        st.error(f"Error processing PDF: {str(e)}")
         return ""
 
-def summarize_text(text, model, max_chunk=1500):
+def generate_summary(text, model):
     if not text or not model:
         return ""
     
-    chunks = [text[i:i+max_chunk] for i in range(0, len(text), max_chunk)]
+    chunks = [text[i:i+1000] for i in range(0, len(text), 1000)]
     summary = []
-    
     for chunk in chunks:
-        result = model(
-            chunk,
-            max_length=150,
-            min_length=50,
-            do_sample=False
-        )
+        result = model(chunk, max_length=150, min_length=30, do_sample=False)
         summary.append(result[0]['summary_text'])
-    
-    return "\n".join(summary)
+    return " ".join(summary)
 
-# Main App with all tabs
 def main():
     st.title("📘 PrepPal - Study Assistant")
     
@@ -76,52 +63,45 @@ def main():
     
     with tab1:
         st.header("PDF Summarizer")
-        st.write("Upload your PDF (max 10MB) for an AI-generated summary")
-        
         uploaded_file = st.file_uploader(
-            "Choose PDF file",
+            "Upload PDF (max 5MB)",
             type=["pdf"],
-            accept_multiple_files=False,
-            key="pdf_uploader"
+            accept_multiple_files=False
         )
         
         if uploaded_file:
-            if uploaded_file.size > 10_000_000:
-                st.error("File too large (max 10MB)")
+            if uploaded_file.size > 5_000_000:
+                st.error("File too large (max 5MB)")
             else:
-                with st.spinner("Extracting text..."):
-                    text = safe_extract_text(uploaded_file)
+                with st.spinner("Processing PDF..."):
+                    text = process_pdf(uploaded_file)
                 
                 if text:
                     with st.expander("View extracted text"):
-                        st.text(text[:1000] + "...")
+                        st.text(text[:500] + "...")
                     
                     if st.button("Generate Summary"):
-                        with st.spinner("Summarizing..."):
-                            model = load_summarizer()
+                        with st.spinner("Creating summary..."):
+                            model = load_model()
                             if model:
-                                summary = summarize_text(text, model)
-                                
-                                st.subheader("AI Summary")
+                                summary = generate_summary(text, model)
+                                st.subheader("Summary")
                                 st.write(summary)
-                                
                                 st.download_button(
                                     "Download Summary",
                                     data=summary,
-                                    file_name="summary.txt",
-                                    mime="text/plain"
+                                    file_name="summary.txt"
                                 )
     
     with tab2:
         st.header("Ask a Question")
-        st.info("This feature will allow you to ask questions about your documents")
-        st.write("Coming in the next update!")
+        st.info("This feature is coming soon!")
     
     with tab3:
-        st.header("Your Feedback")
-        feedback = st.text_area("How can we improve PrepPal?")
-        if st.button("Submit Feedback"):
-            st.success("Thank you! Your feedback has been recorded.")
+        st.header("Feedback")
+        feedback = st.text_area("Your suggestions")
+        if st.button("Submit"):
+            st.success("Thank you for your feedback!")
 
 if __name__ == "__main__":
     main()