Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -2,6 +2,14 @@ import streamlit as st
|
|
2 |
from transformers import pipeline
|
3 |
from pathlib import Path
|
4 |
from llama_index import download_loader
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
|
6 |
def main():
|
7 |
st.title("PDF Summarizer")
|
@@ -13,9 +21,10 @@ def main():
|
|
13 |
# data Loader for reading PDF
|
14 |
PDFReader = download_loader("PDFReader")
|
15 |
loader = PDFReader()
|
16 |
-
documents = loader.load_data(file=Path(uploaded_file))
|
17 |
-
print(type(documents))
|
18 |
-
|
|
|
19 |
st.write(summary)
|
20 |
|
21 |
if __name__ == "__main__":
|
|
|
2 |
from transformers import pipeline
|
3 |
from pathlib import Path
|
4 |
from llama_index import download_loader
|
5 |
+
from PyPDF2 import PdfReader
|
6 |
+
|
7 |
+
def get_pdf_text(pdf_docs):
|
8 |
+
text = ""
|
9 |
+
pdf_reader = PdfReader(pdf)
|
10 |
+
for page in pdf_reader.pages:
|
11 |
+
text += page.extract_text()
|
12 |
+
return text
|
13 |
|
14 |
def main():
|
15 |
st.title("PDF Summarizer")
|
|
|
21 |
# data Loader for reading PDF
|
22 |
PDFReader = download_loader("PDFReader")
|
23 |
loader = PDFReader()
|
24 |
+
#documents = loader.load_data(file=Path(uploaded_file))
|
25 |
+
#print(type(documents))
|
26 |
+
text = get_pdf_text(uploaded_file)
|
27 |
+
summary = summarizer(text, max_length=50, min_length=30, do_sample=False)
|
28 |
st.write(summary)
|
29 |
|
30 |
if __name__ == "__main__":
|