Spaces:
Sleeping
Sleeping
File size: 3,562 Bytes
0a190ad 39720cf 0a190ad c8f0869 90c325f 881b2b7 c8f0869 93313cc 39720cf 881b2b7 39720cf 93313cc edcfa46 39720cf 93313cc 39720cf 881b2b7 39720cf 881b2b7 39720cf 881b2b7 39720cf 881b2b7 39720cf 881b2b7 93313cc 39720cf 881b2b7 39720cf 881b2b7 39720cf 881b2b7 39720cf 881b2b7 39720cf 881b2b7 39720cf 881b2b7 39720cf |
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 |
import os
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",
menu_items={
'About': "PrepPal - AI-powered study assistant"
}
)
# Load summarizer model (using a smaller, faster model)
@st.cache_resource
def load_summarizer():
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 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: {str(e)}")
return ""
# 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 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("PDF Summarizer")
uploaded_file = st.file_uploader(
"Choose a PDF file (max 5MB)",
type=["pdf"],
accept_multiple_files=False
)
if uploaded_file and summarizer:
with st.spinner("Extracting text..."):
text = extract_text_from_pdf(uploaded_file)
if text:
st.subheader("Extracted Text Preview")
st.text_area("", text[:500] + "...", height=150, disabled=True)
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("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.")
# Add footer
st.markdown("---")
st.caption("PrepPal v1.0 | AI-powered study assistant") |