Spaces:
Running
Running
Commit
·
6d20f5a
1
Parent(s):
ed5b1fa
Update app.py
Browse files
app.py
CHANGED
@@ -1,15 +1,28 @@
|
|
1 |
import os
|
2 |
import streamlit as st
|
3 |
-
from transformers import pipeline
|
4 |
from PyPDF2 import PdfReader
|
5 |
import tempfile
|
6 |
|
7 |
# Function to perform question-answering
|
8 |
@st.cache_data(show_spinner=False)
|
9 |
-
def
|
10 |
-
|
11 |
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
return answers
|
15 |
|
@@ -30,8 +43,8 @@ def main():
|
|
30 |
pdf_reader = PdfReader(pdf_path)
|
31 |
pdf_text = "\n".join([pdf_page.extract_text() for pdf_page in pdf_reader.pages])
|
32 |
|
33 |
-
# Perform question-answering
|
34 |
-
answers =
|
35 |
|
36 |
st.write("Questions and Answers:")
|
37 |
for i, (question, answer) in enumerate(zip(questions, answers)):
|
@@ -40,4 +53,4 @@ def main():
|
|
40 |
st.write("Score:", answer['score'])
|
41 |
|
42 |
if __name__ == "__main__":
|
43 |
-
main()
|
|
|
1 |
import os
|
2 |
import streamlit as st
|
3 |
+
from transformers import BertTokenizer, BertForQuestionAnswering, pipeline
|
4 |
from PyPDF2 import PdfReader
|
5 |
import tempfile
|
6 |
|
7 |
# Function to perform question-answering
|
8 |
@st.cache_data(show_spinner=False)
|
9 |
+
def question_answering_bert(questions, pdf_text):
|
10 |
+
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
|
11 |
+
model = BertForQuestionAnswering.from_pretrained('bert-base-uncased')
|
12 |
+
|
13 |
+
answers = []
|
14 |
+
|
15 |
+
for question in questions:
|
16 |
+
inputs = tokenizer(question, pdf_text, padding=True, return_tensors='pt')
|
17 |
+
outputs = model(**inputs)
|
18 |
+
start_scores = outputs.start_logits
|
19 |
+
end_scores = outputs.end_logits
|
20 |
+
|
21 |
+
start_index = start_scores.argmax()
|
22 |
+
end_index = end_scores.argmax() + 1
|
23 |
+
|
24 |
+
answer = tokenizer.decode(inputs['input_ids'][0][start_index:end_index])
|
25 |
+
answers.append({"answer": answer, "score": start_scores.max().item() + end_scores.max().item()})
|
26 |
|
27 |
return answers
|
28 |
|
|
|
43 |
pdf_reader = PdfReader(pdf_path)
|
44 |
pdf_text = "\n".join([pdf_page.extract_text() for pdf_page in pdf_reader.pages])
|
45 |
|
46 |
+
# Perform question-answering using BERT model
|
47 |
+
answers = question_answering_bert(questions, pdf_text)
|
48 |
|
49 |
st.write("Questions and Answers:")
|
50 |
for i, (question, answer) in enumerate(zip(questions, answers)):
|
|
|
53 |
st.write("Score:", answer['score'])
|
54 |
|
55 |
if __name__ == "__main__":
|
56 |
+
main()
|