PirateXX commited on
Commit
aa83d5b
·
1 Parent(s): b85c66d

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +41 -0
app.py CHANGED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from flask import Flask, request
2
+ from transformers import RobertaForSequenceClassification, RobertaTokenizer, RobertaConfig
3
+ from transformers import AutoTokenizer, AutoModelForSequenceClassification
4
+ from transformers import RobertaConfig
5
+ from torch import cuda
6
+ import torch
7
+ import gradio as gr
8
+ import os
9
+ import re
10
+ import pdfplumber
11
+
12
+ app = Flask(__name__)
13
+
14
+ # function to break text into an array of sentences
15
+
16
+ def upload_file(file):
17
+
18
+ if file:
19
+ pdf_file = file.name
20
+ text = ""
21
+ with pdfplumber.open(pdf_file) as pdf:
22
+ cnt = 0
23
+ for page in pdf.pages:
24
+ cnt+=1
25
+ text+=(page.extract_text(x_tolerance = 1))
26
+ if cnt>5:
27
+ break
28
+ text = text.replace('\n', ' ')
29
+ return text
30
+ else:
31
+ return {"error":'No PDF file found in request'}
32
+
33
+
34
+ demo = gr.Interface(
35
+ fn=upload_file,
36
+ inputs=gr.File(),
37
+ article = "Visit <a href = \"https://ai-content-detector.online/\">AI Content Detector</a> for better user experience!",
38
+ outputs=gr.outputs.JSON(),
39
+ interpretation="default",)
40
+
41
+ demo.launch(show_api=False)