Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,141 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import fitz  # PyMuPDF for PDF extraction
+from transformers import pipeline
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+# Set page config
+st.set_page_config(page_title="PrepPal", page_icon="📘", layout="wide")
+
+# Load summarizer model (using Hugging Face pipeline)
+@st.cache_resource
+import streamlit as st
+import fitz  # PyMuPDF for PDF extraction
+from transformers import pipeline
+
+# Set page config
+st.set_page_config(page_title="PrepPal", page_icon="📘", layout="wide")
+
+# Load summarizer model (using Hugging Face pipeline)
+@st.cache_resource
+def load_summarizer():
+    return pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
+
+
+# PDF text extraction
+def extract_text_from_pdf(uploaded_file):
+    text = ""
+    try:
+        with fitz.open(stream=uploaded_file.read(), filetype="pdf") as doc:
+            for page in doc:
+                text += page.get_text()
+    except Exception as e:
+        st.error(f"Error extracting text from PDF: {e}")
+    return text
+
+# Summarize text in chunks
+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)  # Corrected 'false' to 'False'
+        summary += result[0]['summary_text'] + "\n"
+    return summary.strip()
+
+# Load summarizer model
+summarizer = load_summarizer()
+
+# Tabs
+tab1, tab2, tab3 = st.tabs(["📄 Summarize Notes", "❓ Ask a Doubt", "💬 Feedback"])
+
+# Tab 1: Summarizer
+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"])
+
+    if uploaded_pdf:
+        with st.spinner("Extracting text from PDF..."):
+            pdf_text = extract_text_from_pdf(uploaded_pdf)
+
+        if pdf_text.strip():
+            st.subheader("📘 Extracted Text (Preview)")
+            st.text_area("Raw Text", pdf_text[:1000] + "...", height=200)
+
+            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.")
+
+# Tab 2: Ask a Doubt (coming soon)
+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!")
+
+# Tab 3: Feedback (coming soon)
+with tab3:
+    st.header("💬 User Feedback")
+    st.info("📬 A feedback form will be added here to collect your thoughts and improve PrepPal.")
+
+# PDF text extraction
+def extract_text_from_pdf(uploaded_file):
+    text = ""
+    try:
+        with fitz.open(stream=uploaded_file.read(), filetype="pdf") as doc:
+            for page in doc:
+                text += page.get_text()
+    except Exception as e:
+        st.error(f"Error extracting text from PDF: {e}")
+    return text
+
+# Summarize text in chunks
+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)  # Corrected 'false' to 'False'
+        summary += result[0]['summary_text'] + "\n"
+    return summary.strip()
+
+# Load summarizer model
+summarizer = load_summarizer()
+
+# Tabs
+tab1, tab2, tab3 = st.tabs(["📄 Summarize Notes", "❓ Ask a Doubt", "💬 Feedback"])
+
+# Tab 1: Summarizer
+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"])
+
+    if uploaded_pdf:
+        with st.spinner("Extracting text from PDF..."):
+            pdf_text = extract_text_from_pdf(uploaded_pdf)
+            
+        if pdf_text.strip():
+            st.subheader("📘 Extracted Text (Preview)")
+            st.text_area("Raw Text", pdf_text[:1000] + "...", height=200)
+
+            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.")
+
+# Tab 2: Ask a Doubt (coming soon)
+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!")
+
+# Tab 3: Feedback (coming soon)
+with tab3:
+    st.header("💬 User Feedback")
+    st.info("📬 A feedback form will be added here to collect your thoughts and improve PrepPal.")