Upload app.py

app.py

@@ -0,0 +1,112 @@
+import os
+import re
+import PyPDF2
+import pandas as pd
+from transformers import pipeline, AutoTokenizer
+import gradio as gr
+import spaces
+
+# 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):
+    pdf_reader = PyPDF2.PdfReader(pdf_file)
+    text = ''
+    for page_num in range(len(pdf_reader.pages)):
+        text += pdf_reader.pages[page_num].extract_text()
+    return text
+
+# 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])
+
+# Load the LED tokenizer
+led_tokenizer = AutoTokenizer.from_pretrained("allenai/led-base-16384-multi_lexsum-source-long")
+
+# Function to classify text using LED model
+@spaces.GPU(duration=120)
+def classify_text(text):
+    classifier = pipeline("text-classification", model="allenai/led-base-16384-multi_lexsum-source-long", tokenizer=led_tokenizer, framework="pt")
+    try:
+        return classifier(text)[0]['label']
+    except IndexError:
+        return "Unable to classify"
+
+# Function to summarize text using BGE-m3 model
+@spaces.GPU(duration=120)
+def summarize_text(text, max_length=100, min_length=30):
+    summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", tokenizer="sshleifer/distilbart-cnn-12-6", framework="pt")
+    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):
+    summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", tokenizer="sshleifer/distilbart-cnn-12-6", framework="pt")
+    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 PDF files and generate summaries
+@spaces.GPU(duration=120)
+def process_pdfs(pdf_files):
+    data = []
+
+    for pdf_file in pdf_files:
+        text = extract_text(pdf_file)
+        
+        # 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 in the same folder as the source folder
+    csv_file_path = 'processed_pdfs.csv'
+    df.to_csv(csv_file_path, index=False)
+
+    return csv_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_pdfs, 
+    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)