Spaces:
Sleeping
Sleeping
File size: 4,532 Bytes
4c94a49 b35ac00 4c94a49 b35ac00 4c94a49 b35ac00 4c94a49 |
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 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
from pdfminer.high_level import extract_pages
from pdfminer.layout import LTTextContainer
from tqdm import tqdm
import re
import gradio as gr
from llama_cpp import Llama
import os
def process_document(pdf_path, page_ids=None):
extracted_pages = extract_pages(pdf_path, page_numbers=page_ids)
page2content = {}
# Process each extracted page
for extracted_page in tqdm(extracted_pages):
page_id = extracted_page.pageid
content = process_page(extracted_page)
page2content[page_id] = content
return page2content
def process_page(extracted_page):
content = []
elements = [element for element in extracted_page._objs]
elements.sort(key=lambda a: a.y1, reverse=True)
for i, element in enumerate(elements):
# Extract text if the element is a text container
# and text extraction is enabled
if isinstance(element, LTTextContainer):
line_text = extract_text_and_normalize(element)
content.append(line_text)
content = re.sub('\n+', ' ', ''.join(content))
return content
def extract_text_and_normalize(element):
# Extract text from line and split it with new lines
line_texts = element.get_text().split('\n')
norm_text = ''
for line_text in line_texts:
line_text=line_text.strip()
# empty strings after striping convert to newline character
if not line_text:
line_text = '\n'
else:
line_text = re.sub('\s+', ' ', line_text)
# if the last character is not a letter or number,
# add newline character to a line
if not re.search('[\w\d\,\-]', line_text[-1]):
line_text+='\n'
else:
line_text+=' '
# concatenate into single string
norm_text+=line_text
return norm_text
def txt_to_html(text):
html_content = "<html><body>"
for line in text.split('\n'):
html_content += "<p>{}</p>".format(line.strip())
html_content += "</body></html>"
return html_content
def deidentify_doc(pdftext=""):
# prompt = "Please anonymize the following clinical note. Replace all the following information with the term '[redacted]': Redact any strings that might be a name or acronym or initials, patients’ names, doctors’ names, the names of the M.D. or Dr., redact any medical staff names, redact any strings that might be a location or address, such as '3970 Longview Drive', redact any strings that look like 'something years old' or 'age 37', redact any dates and IDs and record dates, redact professions such as 'manager', redact any contact information."
prompt = "Please anonymize the following clinical note. Replace all the following information with the term '[redacted]': Redact any strings that might be a name or initials, patients’ names, doctors’ names, the names Dr., redact any medical staff names, redact any strings that might be a location or address, such as '3970 Longview Drive', redact any strings that look like 'age 37', redact any dates and registration numbers, redact professions such as 'manager', redact any contact information."
print('Input prompt is ',prompt)
print('Input pdf text is ',pdftext)
output = model.create_chat_completion(
messages = [
{"role": "assistant", "content": prompt},
{
"role": "user",
"content": pdftext
}
],
max_tokens=600,
temperature=0
)
output = output['choices'][0]['message']['content']
return output
def pdf_to_text(file):
pdftext=""
if(file):
page2content = process_document(file, page_ids=[0])
pdftext = page2content[1]
display_text = deidentify_doc(pdftext)
html = txt_to_html(display_text)
with open('out.html', "w", encoding="utf-8") as file:
file.write(html)
return html
model_id = "srijaydeshpande/llama3-8B-Instruct-Q5KM/Meta-Llama-3-8B-Instruct.Q5_K_M.gguf"
model = Llama(model_path=model_id, n_ctx=2048, n_threads=8, n_gpu_layers=32, n_batch=128)
css = ".gradio-container {background: 'logo.png'}"
iface = gr.Interface(
fn = pdf_to_text,
inputs = ['file'],
outputs="html",
title='COBIx Endoscopy Report De-Identification',
description="This application assists to remove personal information from the uploaded clinical report",
theme=gr.themes.Soft(),
)
iface.launch() |