Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
import streamlit as st
|
| 2 |
from transformers import pipeline
|
| 3 |
from PyPDF2 import PdfReader
|
| 4 |
-
import PyPDF2
|
| 5 |
-
import os
|
| 6 |
import nltk
|
| 7 |
|
| 8 |
nltk.download('punkt')
|
|
|
|
|
|
|
| 9 |
|
| 10 |
def get_pdf_text(pdf_docs):
|
| 11 |
text = ""
|
|
@@ -15,35 +15,38 @@ def get_pdf_text(pdf_docs):
|
|
| 15 |
text += page.extract_text()
|
| 16 |
return text
|
| 17 |
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
st.title('Question Generator from PDFs')
|
|
|
|
|
|
|
| 20 |
pipe = pipeline(
|
| 21 |
task = 'text2text-generation',
|
| 22 |
model = 'ramsrigouthamg/t5_squad_v1'
|
| 23 |
)
|
| 24 |
file = st.file_uploader(label='Upload',accept_multiple_files=True)
|
| 25 |
-
pr = st.button(label='
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
st.subheader("Generated Questions are: ")
|
| 35 |
-
s = pipe(sentences)
|
| 36 |
-
for i in s:
|
| 37 |
-
questions.append(i['generated_text'][10:])
|
| 38 |
-
st.write(i['generated_text'][10:])
|
| 39 |
-
if st.toggle(label='Show Pipeline Output'):
|
| 40 |
-
st.write(s)
|
| 41 |
-
if st.toggle(label='Show Questions list'):
|
| 42 |
-
st.write(questions)
|
| 43 |
-
# for i in sts:
|
| 44 |
-
# x = pipe(i)
|
| 45 |
-
# questions.append(x)
|
| 46 |
-
# st.write(x)
|
| 47 |
|
| 48 |
-
if
|
| 49 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import streamlit as st
|
| 2 |
from transformers import pipeline
|
| 3 |
from PyPDF2 import PdfReader
|
|
|
|
|
|
|
| 4 |
import nltk
|
| 5 |
|
| 6 |
nltk.download('punkt')
|
| 7 |
+
st.title(body='7 - Question Generation')
|
| 8 |
+
|
| 9 |
|
| 10 |
def get_pdf_text(pdf_docs):
|
| 11 |
text = ""
|
|
|
|
| 15 |
text += page.extract_text()
|
| 16 |
return text
|
| 17 |
|
| 18 |
+
|
| 19 |
+
########################################################
|
| 20 |
+
st.subheader(body='Proposition 1',divider='orange')
|
| 21 |
+
|
| 22 |
+
if st.toggle(label='Show Proposition 1'):
|
| 23 |
st.title('Question Generator from PDFs')
|
| 24 |
+
if st.checkbox('Show Caption'):
|
| 25 |
+
st.caption('Hugging Face Model used: ramsrigouthamg/t5_squad_v1')
|
| 26 |
pipe = pipeline(
|
| 27 |
task = 'text2text-generation',
|
| 28 |
model = 'ramsrigouthamg/t5_squad_v1'
|
| 29 |
)
|
| 30 |
file = st.file_uploader(label='Upload',accept_multiple_files=True)
|
| 31 |
+
# pr = st.button(label='Process')
|
| 32 |
+
raw_text = get_pdf_text(file)
|
| 33 |
+
sentences = nltk.sent_tokenize(text=raw_text)
|
| 34 |
+
s = pipe(sentences)
|
| 35 |
+
questions = []
|
| 36 |
+
for i in s:
|
| 37 |
+
x = i['generated_text'][10:]
|
| 38 |
+
questions.append(x)
|
| 39 |
+
# st.write(f':blue[{x}]')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
+
if st.toggle(label='Show Questions'):
|
| 42 |
+
st.subheader("*Generated Questions are:*")
|
| 43 |
+
for i in s:
|
| 44 |
+
x = i['generated_text'][10:]
|
| 45 |
+
questions.append(x)
|
| 46 |
+
st.write(f':blue[{x}]')
|
| 47 |
+
if st.toggle('Show Text'):
|
| 48 |
+
st.write(raw_text)
|
| 49 |
+
if st.toggle(label='Show Pipeline Output'):
|
| 50 |
+
st.write(s)
|
| 51 |
+
if st.toggle(label='Show Questions list'):
|
| 52 |
+
st.write(questions)
|