Update app.py

app.py

@@ -1,10 +1,13 @@
 import os
 import re
 import pandas as pd
-import PyPDF2
-from concurrent.futures import ThreadPoolExecutor
+from PyPDF2 import PdfReader
 from transformers import pipeline, AutoTokenizer
-import gradio as gr
+from gradio import Interface, File
+import space
+
+# 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")
@@ -17,21 +20,6 @@ summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", to
 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 = PyPDF2.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()
@@ -39,6 +27,7 @@ def split_text(text, chunk_size=1024):
         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']
@@ -46,6 +35,7 @@ def classify_text(text):
         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']
@@ -53,65 +43,71 @@ def summarize_text(text, max_length=100, min_length=30):
         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"
 
-# Function to process each PDF file and extract relevant information
-def process_pdf(pdf_file):
-    text = extract_text(pdf_file)
-
-    # Skip encrypted files
-    if text is None:
-        return None
-
-    # 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)
-
-    return [title, final_abstract, final_cleaned_text]
-
-# Function to handle multiple PDF files in parallel
-def process_pdfs(files):
-    data = []
-    with ThreadPoolExecutor() as executor:
-        results = list(executor.map(process_pdf, files))
-        data.extend(result for result in results if result is not None)
-    return data
-
-# Gradio interface function
-def gradio_interface(files):
-    data = process_pdfs([file.name for file in files])
+# 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'])
-    csv_path = gr.File(label="Download CSV")  # Adjust this to your actual path
-    df.to_csv(csv_path, index=False)
-    return csv_path
 
-# Gradio app setup
+    # 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=gradio_interface,
-    inputs=gr.File(file_count="multiple", file_types=[".pdf"]),
+    fn=process_pdfs, 
+    inputs=pdf_input, 
     outputs=csv_output,
-    title="PDF Research Paper Dataset Creator",
-    description="Upload PDF research papers to create a dataset with title, abstract, and content."
-).launch()
+    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)