File size: 1,472 Bytes
8cb1867
44e21a6
 
f4067be
 
 
 
44e21a6
2bb61b8
06bc437
 
 
 
 
 
 
2bb61b8
12b0ed7
95d05cb
8cb1867
 
1aa90a2
95d05cb
 
1aa90a2
95d05cb
 
 
367a8a1
95d05cb
 
 
 
 
 
12b0ed7
 
 
 
7044543
8cb1867
f4067be
bcb2ab6
12b0ed7
 
 
8cb1867
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
import gradio as gr
from pptx import Presentation
import re
from transformers import pipeline

# Create a summarization pipeline
summarizer = pipeline("summarization", model="Falconsai/text_summarization")

def extract_text_from_pptx(file_path):
    presentation = Presentation(file_path)
    text = []
    for slide_number, slide in enumerate(presentation.slides, start=1):
        for shape in slide.shapes:
            if hasattr(shape, "text"):
                text.append(shape.text)
    return "\n".join(text)

def predict_pptx_content(file_path):
    try:
        extracted_text = extract_text_from_pptx(file_path)
        cleaned_text = re.sub(r'\s+', ' ', extracted_text)

        # Summarize the cleaned text
        summary = summarizer(cleaned_text, max_length=80, min_length=30, do_sample=False)[0]['summary_text']

        prediction = {
            "Summary": summary
        }

        return prediction

    except Exception as e:
        # Log the error details
        print(f"Error in predict_pptx_content: {e}")
        return {"error": str(e)}

# Define the Gradio interface
iface = gr.Interface(
    fn=predict_pptx_content,
    inputs=gr.File(type="filepath", label="Upload PowerPoint (.pptx) file"),
    outputs="text",  # Only output the summary
    live=False,  # Change to True for one-time analysis
    title="<h1 style='color: lightgreen; text-align: center;'>HackTalk Analyzer</h1>",
)

# Deploy the Gradio interface
iface.launch(share=True)