Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,71 +1,120 @@
 import os
-os.environ["TRANSFORMERS_CACHE"] = "/tmp/huggingface"
+os.environ["TRANSFORMERS_CACHE"] = "/cache"  # Special directory in Spaces
 
 import streamlit as st
 import fitz  # PyMuPDF
 from transformers import pipeline
 
 # Set page config
-st.set_page_config(page_title="PrepPal", page_icon="📘", layout="wide")
+st.set_page_config(
+    page_title="PrepPal",
+    page_icon="📘",
+    layout="wide",
+    menu_items={
+        'About': "PrepPal - AI-powered study assistant"
+    }
+)
 
-# Load summarizer model
+# Load summarizer model (using a smaller, faster model)
 @st.cache_resource
 def load_summarizer():
-    return pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
-
+    try:
+        return pipeline(
+            "summarization", 
+            model="Falconsai/text_summarization",  # Smaller model
+            device=-1  # Use CPU (more reliable in Spaces)
+        )
+    except Exception as e:
+        st.error(f"❌ Failed to load model: {str(e)}")
+        return None
 
-# Extract text from uploaded PDF
+# Extract text from PDF with size limit
 def extract_text_from_pdf(uploaded_file):
     text = ""
     try:
+        # Check file size (max 5MB)
+        if uploaded_file.size > 5_000_000:
+            st.error("File too large (max 5MB)")
+            return ""
+            
         with fitz.open(stream=uploaded_file.read(), filetype="pdf") as doc:
             for page in doc:
                 text += page.get_text()
+        return text.strip()
     except Exception as e:
-        st.error(f"❌ Error extracting text from PDF: {e}")
-    return text
+        st.error(f"❌ Error extracting text: {str(e)}")
+        return ""
 
-# Summarize large text
-def summarize_text(text, summarizer, max_chunk_length=2000):
-    chunks = [text[i:i + max_chunk_length] for i in range(0, len(text), max_chunk_length)]
-    summary = ""
-    for chunk in chunks:
-        result = summarizer(chunk, max_length=130, min_length=30, do_sample=False)
-        summary += result[0]['summary_text'] + "\n"
-    return summary.strip()
+# Summarize text in chunks
+def summarize_text(text, summarizer, max_chunk=1024):
+    if not text:
+        return ""
+        
+    try:
+        chunks = [text[i:i+max_chunk] for i in range(0, len(text), max_chunk)]
+        summary = ""
+        for chunk in chunks:
+            result = summarizer(
+                chunk,
+                max_length=150,
+                min_length=30,
+                do_sample=False
+            )
+            summary += result[0]['summary_text'] + " "
+        return summary.strip()
+    except Exception as e:
+        st.error(f"❌ Summarization failed: {str(e)}")
+        return ""
 
 # Load model
 summarizer = load_summarizer()
 
-# UI
-tab1, tab2, tab3 = st.tabs(["📄 Summarize Notes", "❓ Ask a Doubt", "💬 Feedback"])
+# UI Layout
+st.title("📘 PrepPal - Study Assistant")
+st.markdown("Upload your notes and get an AI-powered summary")
+
+tab1, tab2 = st.tabs(["📄 Summarize Notes", "💬 Feedback"])
 
 with tab1:
-    st.header("📄 Upload Notes & Get Summary")
-    st.write("Upload your class notes in PDF format to receive a summarized version.")
-    uploaded_pdf = st.file_uploader("Upload your PDF notes (PDF only)", type=["pdf"])
+    st.header("PDF Summarizer")
+    uploaded_file = st.file_uploader(
+        "Choose a PDF file (max 5MB)",
+        type=["pdf"],
+        accept_multiple_files=False
+    )
 
-    if uploaded_pdf:
-        with st.spinner("Extracting text from PDF..."):
-            pdf_text = extract_text_from_pdf(uploaded_pdf)
+    if uploaded_file and summarizer:
+        with st.spinner("Extracting text..."):
+            text = extract_text_from_pdf(uploaded_file)
 
-        if pdf_text.strip():
-            st.subheader("📘 Extracted Text (Preview)")
-            st.text_area("Raw Text", pdf_text[:1000] + "...", height=200)
+        if text:
+            st.subheader("Extracted Text Preview")
+            st.text_area("", text[:500] + "...", height=150, disabled=True)
 
-            if st.button("✂️ Summarize"):
-                with st.spinner("Summarizing... Please wait."):
-                    summary = summarize_text(pdf_text, summarizer)
-                st.subheader("✅ Summary")
-                st.text_area("Summary Output", summary, height=300)
-                st.download_button("⬇️ Download Summary", summary, file_name="summary.txt")
-        else:
-            st.warning("⚠️ No text found in the uploaded PDF.")
+            if st.button("Generate Summary"):
+                with st.spinner("Summarizing..."):
+                    summary = summarize_text(text, summarizer)
+                
+                if summary:
+                    st.subheader("AI Summary")
+                    st.write(summary)
+                    
+                    st.download_button(
+                        "Download Summary",
+                        data=summary,
+                        file_name="summary.txt",
+                        mime="text/plain"
+                    )
+                else:
+                    st.warning("No summary generated")
 
 with tab2:
-    st.header("❓ Ask a Doubt")
-    st.info("🔧 This feature is under development. You’ll soon be able to chat with your notes using AI!")
+    st.header("Feedback")
+    st.write("We'd love to hear your thoughts!")
+    feedback = st.text_area("Your feedback")
+    if st.button("Submit Feedback"):
+        st.success("Thank you! Your feedback has been recorded.")
 
-with tab3:
-    st.header("💬 User Feedback")
-    st.info("📬 A feedback form will be added here to collect your thoughts and improve PrepPal.")
+# Add footer
+st.markdown("---")
+st.caption("PrepPal v1.0 | AI-powered study assistant")