Update app.py
Browse files
app.py
CHANGED
|
@@ -1,54 +1,5 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
import os
|
| 4 |
-
import tempfile
|
| 5 |
-
from typing import List
|
| 6 |
-
|
| 7 |
-
import fitz # PyMuPDF
|
| 8 |
-
import requests
|
| 9 |
-
from transformers import pipeline
|
| 10 |
-
from gtts import gTTS
|
| 11 |
-
import streamlit as st
|
| 12 |
-
|
| 13 |
-
# ---------- CONFIG ----------
|
| 14 |
-
def summarize_text(text: str) -> str:
|
| 15 |
-
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
|
| 16 |
-
return summarizer(text, max_length=200, min_length=30, do_sample=False)[0]['summary_text']
|
| 17 |
-
|
| 18 |
-
def extract_text_from_pdf(pdf_path: str) -> str:
|
| 19 |
-
doc = fitz.open(pdf_path)
|
| 20 |
-
text = ""
|
| 21 |
-
for page in doc:
|
| 22 |
-
text += page.get_text()
|
| 23 |
-
return text
|
| 24 |
-
|
| 25 |
-
def classify_topic(text: str, topics: List[str]) -> str:
|
| 26 |
-
classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
|
| 27 |
-
result = classifier(text[:1000], candidate_labels=topics)
|
| 28 |
-
return result['labels'][0]
|
| 29 |
-
|
| 30 |
-
def generate_audio(text: str, output_path: str):
|
| 31 |
-
tts = gTTS(text)
|
| 32 |
-
tts.save(output_path)
|
| 33 |
-
|
| 34 |
-
# ---------- STREAMLIT UI ----------
|
| 35 |
-
st.set_page_config(page_title="Research Paper Summarizer", layout="centered")
|
| 36 |
-
st.title("π AI Research Paper Summarizer")
|
| 37 |
-
|
| 38 |
-
st.markdown("""
|
| 39 |
-
Upload a research paper (PDF) and a list of topics. The app will:
|
| 40 |
-
1. Extract and summarize the paper
|
| 41 |
-
2. Classify it into a topic
|
| 42 |
-
3. Generate an audio summary π§
|
| 43 |
-
""")
|
| 44 |
-
|
| 45 |
-
with st.form("upload_form"):
|
| 46 |
-
uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
|
| 47 |
-
topic_input = st.text_input("Enter comma-separated topics")
|
| 48 |
-
submitted = st.form_submit_button("Summarize and Generate Audio")
|
| 49 |
-
|
| 50 |
-
if submitted and uploaded_file and topic_input:
|
| 51 |
-
with st.spinner("Processing paper..."):
|
| 52 |
temp_dir = tempfile.mkdtemp()
|
| 53 |
file_path = os.path.join(temp_dir, uploaded_file.name)
|
| 54 |
|
|
@@ -69,4 +20,7 @@ if submitted and uploaded_file and topic_input:
|
|
| 69 |
|
| 70 |
st.markdown("### π Audio Summary")
|
| 71 |
st.audio(audio_path)
|
| 72 |
-
st.success("Done! Audio summary is ready.")
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
with st.spinner("Processing paper..."):
|
| 2 |
+
try:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
temp_dir = tempfile.mkdtemp()
|
| 4 |
file_path = os.path.join(temp_dir, uploaded_file.name)
|
| 5 |
|
|
|
|
| 20 |
|
| 21 |
st.markdown("### π Audio Summary")
|
| 22 |
st.audio(audio_path)
|
| 23 |
+
st.success("Done! Audio summary is ready.")
|
| 24 |
+
|
| 25 |
+
except Exception as e:
|
| 26 |
+
st.error(f"β Error: {str(e)}")
|