File size: 5,235 Bytes
f74bc21 4b06e1e f74bc21 4b06e1e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 |
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.") |