File size: 1,665 Bytes
b8c967e 2360418 b8c967e 44c9e92 b8c967e 2360418 b8c967e 2360418 44c9e92 b8c967e 44c9e92 e4ecc70 b8c967e 2360418 e4ecc70 61625a4 6e22a2e 61625a4 80e218f b8c967e e4ecc70 b8c967e 44c9e92 b8c967e 44c9e92 2360418 b8c967e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
import gradio as gr
import requests
import re
import fitz
def extract_text_from_pdf(pdf_file_path):
doc = fitz.open(pdf_file_path)
text = ""
for page in doc:
text+=page.get_text()
return text
API_URL = "https://api-inference.huggingface.co/models/potsawee/t5-large-generation-squad-QuestionAnswer"
headers = {"Authorization": "Bearer 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"}
def query(payload):
response = requests.post(API_URL, headers=headers, json=payload)
return response.json()
def generate_question_answer_pairs(input_file):
if input_file is None:
return "Please upload a file"
pdf_text = extract_text_from_pdf(input_file)
sentences = re.split(r'(?<=[.!?])', pdf_text)
outputs = []
result = ''
for sentence in sentences:
if sentence.strip():
output = query({
"inputs": sentence,
})
outputs.append(output)
for i in outputs:
if type(i) == dict:
continue
pair = i[0]['generated_text']
question = re.search(r'^(.*?\?)', pair)
answer = re.search(r'\?(.*)', pair)
if question and answer:
question_part = question.group(1).strip()
answer_part = answer.group(1).strip()
result += f"Question: {question_part}\nAnswer: {answer_part}\n\n"
return result
title = "Question-Answer Pairs Generation"
input_file = gr.File(label="Upload a PDF file")
output_text = gr.Textbox()
interface = gr.Interface(
fn=generate_question_answer_pairs,
inputs=input_file,
outputs=output_text,
title=title,
)
interface.launch() |