Update src/streamlit_app.py

src/streamlit_app.py

@@ -13,21 +13,19 @@ st.set_page_config(
     layout="wide"
 )
 
-# Security headers
-st.markdown("""
-<meta http-equiv="Content-Security-Policy" content="default-src 'self'; script-src 'self' 'unsafe-inline'">
-""", unsafe_allow_html=True)
-
-@st.cache_resource
+# Load model with better error handling
+@st.cache_resource(show_spinner=False)
 def load_model():
     try:
+        # Using a smaller, more reliable model
         return pipeline(
             "summarization",
-            model="Falconsai/text_summarization",  # Smaller model for Spaces
-            device=-1  # Use CPU
+            model="facebook/bart-large-cnn",
+            device=-1  # Force CPU
         )
     except Exception as e:
-        st.error(f"Failed to load model: {str(e)}")
+        st.error(f"❌ Model loading failed: {str(e)}")
+        st.error("Please try again later or contact support")
         return None
 
 def process_pdf(uploaded_file):
@@ -42,19 +40,38 @@ def process_pdf(uploaded_file):
         os.unlink(tmp_path)
         return text.strip()
     except Exception as e:
-        st.error(f"Error processing PDF: {str(e)}")
+        st.error(f"❌ PDF processing error: {str(e)}")
         return ""
 
 def generate_summary(text, model):
-    if not text or not model:
+    if not text:
+        st.error("No text extracted from PDF")
+        return ""
+    
+    if not model:
+        st.error("AI model not loaded")
         return ""
     
-    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=30, do_sample=False)
-        summary.append(result[0]['summary_text'])
-    return " ".join(summary)
+    try:
+        # More efficient chunking
+        chunks = [text[i:i+1024] for i in range(0, len(text), 1024)]
+        summaries = []
+        
+        progress_bar = st.progress(0)
+        for i, chunk in enumerate(chunks):
+            progress_bar.progress((i + 1) / len(chunks))
+            result = model(
+                chunk,
+                max_length=150,
+                min_length=30,
+                do_sample=False
+            )
+            summaries.append(result[0]['summary_text'])
+        
+        return " ".join(summaries)
+    except Exception as e:
+        st.error(f"❌ Summarization failed: {str(e)}")
+        return ""
 
 def main():
     st.title("📘 PrepPal - Study Assistant")
@@ -64,34 +81,43 @@ def main():
     with tab1:
         st.header("PDF Summarizer")
         uploaded_file = st.file_uploader(
-            "Upload PDF (max 5MB)",
+            "Upload PDF (max 10MB)",
             type=["pdf"],
             accept_multiple_files=False
         )
         
         if uploaded_file:
-            if uploaded_file.size > 5_000_000:
-                st.error("File too large (max 5MB)")
+            if uploaded_file.size > 10_000_000:
+                st.error("File too large (max 10MB)")
             else:
-                with st.spinner("Processing PDF..."):
+                with st.spinner("Extracting text from PDF..."):
                     text = process_pdf(uploaded_file)
                 
                 if text:
                     with st.expander("View extracted text"):
-                        st.text(text[:500] + "...")
+                        st.text(text[:1000] + "...")
                     
                     if st.button("Generate Summary"):
-                        with st.spinner("Creating summary..."):
+                        with st.spinner("Loading AI model..."):
                             model = load_model()
-                            if model:
-                                summary = generate_summary(text, model)
-                                st.subheader("Summary")
+                        
+                        if model:
+                            st.info("Generating summary... This may take a minute")
+                            summary = generate_summary(text, model)
+                            
+                            if summary:
+                                st.subheader("✅ Summary")
                                 st.write(summary)
                                 st.download_button(
-                                    "Download Summary",
+                                    "⬇️ Download Summary",
                                     data=summary,
-                                    file_name="summary.txt"
+                                    file_name="summary.txt",
+                                    mime="text/plain"
                                 )
+                            else:
+                                st.warning("No summary was generated")
+                        else:
+                            st.error("Could not load AI model")
     
     with tab2:
         st.header("Ask a Question")
@@ -100,7 +126,7 @@ def main():
     with tab3:
         st.header("Feedback")
         feedback = st.text_area("Your suggestions")
-        if st.button("Submit"):
+        if st.button("Submit Feedback"):
             st.success("Thank you for your feedback!")
 
 if __name__ == "__main__":