Commit
·
e4ecc70
1
Parent(s):
4611c59
Update app.py
Browse files
app.py
CHANGED
@@ -25,7 +25,9 @@ def generate_question_answer_pairs(input_file):
|
|
25 |
pdf_text = extract_text_from_pdf(input_file)
|
26 |
|
27 |
sentences = re.split(r'(?<=[.!?])', pdf_text)
|
28 |
-
|
|
|
|
|
29 |
|
30 |
for sentence in sentences:
|
31 |
if sentence.strip():
|
@@ -33,8 +35,14 @@ def generate_question_answer_pairs(input_file):
|
|
33 |
"inputs": sentence,
|
34 |
})
|
35 |
outputs.append(output)
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
|
37 |
-
return
|
38 |
|
39 |
title = "Question-Answer Pairs Generation"
|
40 |
input_file = gr.File(label="Upload a PDF file")
|
|
|
25 |
pdf_text = extract_text_from_pdf(input_file)
|
26 |
|
27 |
sentences = re.split(r'(?<=[.!?])', pdf_text)
|
28 |
+
|
29 |
+
outputs = []
|
30 |
+
result = ''
|
31 |
|
32 |
for sentence in sentences:
|
33 |
if sentence.strip():
|
|
|
35 |
"inputs": sentence,
|
36 |
})
|
37 |
outputs.append(output)
|
38 |
+
|
39 |
+
for i in outputs:
|
40 |
+
chunk = outputs[i][0]['generated_text']
|
41 |
+
question_part = re.search(r'^(.*?\?)',chunk).group(1).strip()
|
42 |
+
answer_part = re.search(r'\?(.*)', chunk).group(1).strip()
|
43 |
+
result += f"Question: {question_part}\nAnswer: {answer_part}\n\n"
|
44 |
|
45 |
+
return result
|
46 |
|
47 |
title = "Question-Answer Pairs Generation"
|
48 |
input_file = gr.File(label="Upload a PDF file")
|