Spaces:
Build error
Build error
import collections | |
import math | |
import re | |
import string | |
import streamlit as st | |
from transformers.pipelines import pipeline | |
import json | |
import sys | |
from predict import run_prediction | |
import random | |
from io import StringIO | |
import requests | |
import boto3 | |
from transformers import ( | |
AutoConfig, | |
AutoModelForQuestionAnswering, | |
AutoTokenizer, | |
squad_convert_examples_to_features | |
) | |
from transformers.data.processors.squad import SquadResult, SquadV2Processor, SquadExample | |
from transformers.data.metrics.squad_metrics import compute_predictions_logits | |
import gradio as gr | |
import json | |
import torch | |
import time | |
from torch.utils.data import DataLoader, RandomSampler, SequentialSampler | |
st.set_page_config(layout="wide") | |
st.cache(show_spinner=False, persist=True) | |
def load_questions(): | |
questions = [] | |
with open('data/questions.txt') as f: | |
questions = f.readlines() | |
# questions = [] | |
# for i, q in enumerate(data['data'][0]['paragraphs'][0]['qas']): | |
# question = data['data'][0]['paragraphs'][0]['qas'][i]['question'] | |
# questions.append(question) | |
return questions | |
st.cache(show_spinner=False, persist=True) | |
def load_contracts(): | |
with open('data/test.json') as json_file: | |
data = json.load(json_file) | |
contracts = [] | |
for i, q in enumerate(data['data']): | |
contract = ' '.join(data['data'][i]['paragraphs'][0]['context'].split()) | |
contracts.append(contract) | |
return contracts | |
questions = load_questions() | |
# contracts = load_contracts() | |
### DEFINE SIDEBAR | |
st.sidebar.title("Interactive Contract Analysis") | |
st.sidebar.markdown( | |
""" | |
Process text with [Huggingface](https://huggingface.co) models and visualize the results. | |
This model uses a pretrained snapshot trained on the [Atticus](https://www.atticusprojectai.org/) Dataset - CUAD | |
""" | |
) | |
st.sidebar.header("Contract Selection") | |
# select contract | |
contracts_drop = ['contract 1', 'contract 2', 'contract 3'] | |
contracts_files = ['contract-1.txt', 'contract-2.txt', 'contract-3.txt'] | |
contract = st.sidebar.selectbox('Please Select a Contract', contracts_drop) | |
idx = contracts_drop.index(contract) | |
with open('data/'+contracts_files[idx-1]) as f: | |
contract_data = f.read() | |
# upload contract | |
user_upload = st.sidebar.file_uploader('Please upload your own', type=['docx', 'pdf', 'txt'], accept_multiple_files=False) | |
print(user_upload) | |
# process upload | |
if user_upload is not None: | |
print(user_upload.name,user_upload.type) | |
extension = user_upload.name.split('.')[-1].lower() | |
if extension == 'txt': | |
print('text file uploaded') | |
# To convert to a string based IO: | |
stringio = StringIO(user_upload.getvalue().decode("utf-8")) | |
# To read file as string: | |
contract_data = stringio.read() | |
elif extension == 'pdf': | |
import PyPDF4 | |
try: | |
# Extracting Text from PDFs | |
pdfReader = PyPDF4.PdfFileReader(user_upload) | |
print(pdfReader.numPages) | |
contract_data = '' | |
for i in range(0,pdfReader.numPages): | |
print(i) | |
pageobj = pdfReader.getPage(i) | |
contract_data = contract_data + pageobj.extractText() | |
except: | |
st.warning('Unable to read PDF, please try another file') | |
elif extension == 'docx': | |
import docx2txt | |
contract_data = docx2txt.process(user_upload) | |
else: | |
st.warning('Unknown uploaded file type, please try again') | |
results_drop = ['1', '2', '3'] | |
number_results = st.sidebar.selectbox('Select number of results', results_drop) | |
### DEFINE MAIN PAGE | |
st.header("Legal Contract Review Demo") | |
st.write("This demo uses the CUAD dataset for Contract Understanding.") | |
paragraph = st.text_area(label="Contract",value=contract_data,height=400) | |
question = st.selectbox('Choose one of the 41 queries from the CUAD dataset:', questions) | |
if st.button('Analyze'): | |
if (not len(paragraph)==0) and not (len(question)==0): | |
print('getting predictions') | |
with st.spinner(text='Analysis in progress...'): | |
#predictions = run_prediction([question], paragraph, '../models/roberta-base/') | |
data = {} | |
data['question']=[question] | |
data['context']=paragraph | |
print(data) | |
predictions = run_prediction(data['question'], data['context'], 'akdeniz27/roberta-base-cuad', | |
n_best_size=int(number_results)) | |
# print(resp) | |
# predictions=resp.json() | |
# print(predictions) | |
if predictions['0'] == "": | |
answer = 'No answer found in document' | |
else: | |
if number_results == '1': | |
answer = predictions['0'] | |
st.text_area(label="Answer", value=f"{answer}") | |
else: | |
f = open("nbest.json") | |
st.success(f.readlines()) | |
st.success("Successfully processed contract!") | |
else: | |
st.write("Unable to call model, please select question and contract") | |