src/streamlit_app.py

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
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.")