Spaces:
Running
Running
Anupam251272
commited on
Commit
•
badae39
1
Parent(s):
31523b3
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from transformers import pipeline
|
3 |
+
import PyPDF2
|
4 |
+
import torch
|
5 |
+
|
6 |
+
# Function to extract text from PDF
|
7 |
+
def extract_text_from_pdf(pdf_file):
|
8 |
+
text = ""
|
9 |
+
try:
|
10 |
+
pdf_reader = PyPDF2.PdfReader(pdf_file)
|
11 |
+
for page in pdf_reader.pages:
|
12 |
+
text += page.extract_text()
|
13 |
+
except Exception as e:
|
14 |
+
return f"Error parsing PDF: {str(e)}"
|
15 |
+
return text
|
16 |
+
|
17 |
+
# Load Summarization Model
|
18 |
+
summarizer = pipeline("summarization", model="facebook/bart-large-cnn", device=0 if torch.cuda.is_available() else -1)
|
19 |
+
|
20 |
+
# Summarization Function
|
21 |
+
def summarize_text(text):
|
22 |
+
try:
|
23 |
+
summaries = summarizer(text[:1024], max_length=150, min_length=40, do_sample=False)
|
24 |
+
return summaries[0]['summary_text']
|
25 |
+
except Exception as e:
|
26 |
+
return f"Error during summarization: {str(e)}"
|
27 |
+
|
28 |
+
# Load Question-Answering Model
|
29 |
+
qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2", device=0 if torch.cuda.is_available() else -1)
|
30 |
+
|
31 |
+
# Key Findings Extraction Function
|
32 |
+
def extract_key_findings(text, query="What are the main findings?"):
|
33 |
+
try:
|
34 |
+
result = qa_pipeline({'question': query, 'context': text[:1024]})
|
35 |
+
return result['answer']
|
36 |
+
except Exception as e:
|
37 |
+
return f"Error extracting key findings: {str(e)}"
|
38 |
+
|
39 |
+
# Main Function to Process PDF
|
40 |
+
def process_paper(pdf_file):
|
41 |
+
extracted_text = extract_text_from_pdf(pdf_file.name)
|
42 |
+
if "Error" in extracted_text:
|
43 |
+
return extracted_text, None, None
|
44 |
+
|
45 |
+
summary = summarize_text(extracted_text)
|
46 |
+
findings = extract_key_findings(extracted_text)
|
47 |
+
|
48 |
+
return extracted_text, summary, findings
|
49 |
+
|
50 |
+
# Gradio Interface
|
51 |
+
with gr.Blocks() as app:
|
52 |
+
gr.Markdown("## AI-Assisted Literature Review Tool")
|
53 |
+
|
54 |
+
with gr.Row():
|
55 |
+
pdf_input = gr.File(label="Upload Research Paper (PDF)")
|
56 |
+
process_button = gr.Button("Process")
|
57 |
+
|
58 |
+
with gr.Row():
|
59 |
+
extracted_text_output = gr.Textbox(label="Extracted Text", lines=10, interactive=False)
|
60 |
+
summary_output = gr.Textbox(label="Summary", lines=5, interactive=False)
|
61 |
+
findings_output = gr.Textbox(label="Key Findings", lines=5, interactive=False)
|
62 |
+
|
63 |
+
process_button.click(process_paper, inputs=pdf_input, outputs=[extracted_text_output, summary_output, findings_output])
|
64 |
+
|
65 |
+
app.launch()
|