Upload app.py

app.py

@@ -0,0 +1,129 @@
+import os
+import re
+import pandas as pd
+from PyPDF2 import PdfReader
+from transformers import pipeline, AutoTokenizer
+from gradio import Interface, File
+import gradio as gr
+import spaces
+
+# Initialize a list to store the data
+data = []
+
+# Load the LED tokenizer and model
+led_tokenizer = AutoTokenizer.from_pretrained("allenai/led-base-16384-multi_lexsum-source-long")
+classifier = pipeline("text-classification", model="allenai/led-base-16384-multi_lexsum-source-long", tokenizer=led_tokenizer, framework="pt")
+
+# Load the summarization model and tokenizer
+summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", tokenizer="sshleifer/distilbart-cnn-12-6", framework="pt")
+
+# Function to clean text by keeping only alphanumeric characters and spaces
+def clean_text(text):
+    return re.sub(r'[^a-zA-Z0-9\s]', '', text)
+    
+# Function to extract text from PDF files
+def extract_text(pdf_file):
+    try:
+        pdf_reader = PdfReader(pdf_file)
+        if pdf_reader.is_encrypted:
+            print(f"Skipping encrypted file: {pdf_file}")
+            return None
+        text = ''
+        for page in pdf_reader.pages:
+            text += page.extract_text() or ''
+        return text
+    except Exception as e:
+        print(f"Error extracting text from {pdf_file}: {e}")
+        return None
+
+# Function to split text into chunks of a specified size
+def split_text(text, chunk_size=1024):
+    words = text.split()
+    for i in range(0, len(words), chunk_size):
+        yield ' '.join(words[i:i + chunk_size])
+
+# Function to classify text using LED model
+@spaces.GPU(duration=120)
+def classify_text(text):
+    try:
+        return classifier(text)[0]['label']
+    except IndexError:
+        return "Unable to classify"
+
+# Function to summarize text using the summarizer model
+@spaces.GPU(duration=120)
+def summarize_text(text, max_length=100, min_length=30):
+    try:
+        return summarizer(text, max_length=max_length, min_length=min_length, do_sample=False)[0]['summary_text']
+    except IndexError:
+        return "Unable to summarize"
+
+# Function to extract a title-like summary from the beginning of the text
+@spaces.GPU(duration=120)
+def extract_title(text, max_length=20):
+    try:
+        return summarizer(text, max_length=max_length, min_length=5, do_sample=False)[0]['summary_text']
+    except IndexError:
+        return "Unable to extract title"
+
+# Define the folder path and CSV file path
+# output_folder_path = '/content/drive/My Drive/path_to_output'  # Adjust this to your actual path
+
+# Define the Gradio interface for file upload and download
+@spaces.GPU(duration=120)
+def process_files(pdf_files):
+    for pdf_file in pdf_files:
+        text = extract_text(pdf_file)
+
+        # Skip encrypted files
+        if text is None:
+            continue
+
+        # Extract a title from the beginning of the text
+        title_text = ' '.join(text.split()[:512])  # Take the first 512 tokens for title extraction
+        title = extract_title(title_text)
+
+        # Initialize placeholders for combined results
+        combined_abstract = []
+        combined_cleaned_text = []
+
+        # Split text into chunks and process each chunk
+        for chunk in split_text(text, chunk_size=512):
+            # Summarize the text chunk
+            abstract = summarize_text(chunk)
+            combined_abstract.append(abstract)
+
+            # Clean the text chunk
+            cleaned_text = clean_text(chunk)
+            combined_cleaned_text.append(cleaned_text)
+
+        # Combine results from all chunks
+        final_abstract = ' '.join(combined_abstract)
+        final_cleaned_text = ' '.join(combined_cleaned_text)
+
+        # Append the data to the list
+        data.append([title, final_abstract, final_cleaned_text])
+
+    # Create a DataFrame from the data list
+    df = pd.DataFrame(data, columns=['Title', 'Abstract', 'Content'])
+
+    # Save the DataFrame to a CSV file
+    output_file_path = 'processed_pdfs.csv'
+    df.to_csv(output_file_path, index=False)
+
+    return output_file_path
+    
+# Gradio interface
+pdf_input = gr.File(label="Upload PDF Files", file_types=[".pdf"], file_count="multiple")
+csv_output = gr.File(label="Download CSV")
+
+gr.Interface(
+    fn=process_files, 
+    inputs=pdf_input, 
+    outputs=csv_output,
+    title="Dataset creation",
+    description="Upload PDF files and get a summarized CSV file.",
+    article="""<p>This is an experimental app that allows you to create a dataset from research papers.</p>
+                <p>This app uses the allenai/led-base-16384-multi_lexsum-source-long and sshleifer/distilbart-cnn-12-6 AI models.</p>
+                <p>The output file is a CSV with 3 columns: title, abstract, and content.</p>"""
+).launch(share=True)