Spaces:
Sleeping
Sleeping
| import os | |
| import base64 | |
| import tempfile | |
| import streamlit as st | |
| from transformers import pipeline | |
| from PyPDF2 import PdfReader | |
| from transformers import AutoTokenizer, AutoModelForSeq2SeqLM | |
| # Load the summarization model | |
| tokenizer = AutoTokenizer.from_pretrained("MBZUAI/LaMini-Flan-T5-248M") | |
| base_model = AutoModelForSeq2SeqLM.from_pretrained("MBZUAI/LaMini-Flan-T5-248M") | |
| # Function to extract text from a PDF using PyPDF2 | |
| def extract_text_from_pdf(pdf_path): | |
| reader = PdfReader(pdf_path) | |
| text = "" | |
| for page in reader.pages: | |
| page_text = page.extract_text() | |
| if page_text: # Only add page text if it exists | |
| text += page_text | |
| if text.strip(): | |
| return text | |
| return None | |
| # LLM pipeline for summarization | |
| def llm_pipeline(input_text): | |
| pipe_sum = pipeline( | |
| 'summarization', | |
| model=base_model, | |
| tokenizer=tokenizer, | |
| max_length=500, | |
| min_length=50, | |
| ) | |
| result = pipe_sum(input_text) | |
| return result[0]['summary_text'] | |
| # Function to display the PDF | |
| def displayPDF(file_path): | |
| with open(file_path, "rb") as f: | |
| base64_pdf = base64.b64encode(f.read()).decode('utf-8') | |
| pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="100%" height="600" type="application/pdf"></iframe>' | |
| st.markdown(pdf_display, unsafe_allow_html=True) | |
| # Streamlit App | |
| def main(): | |
| st.title('PDF Content Summarizer') | |
| # PDF Upload Section | |
| uploaded_file = st.file_uploader("Upload your PDF file", type=['pdf']) | |
| if uploaded_file is not None: | |
| if st.button("Summarize PDF"): | |
| col1, col2 = st.columns(2) | |
| # Save the uploaded file to a temporary location | |
| with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf", dir="/tmp/") as temp_file: | |
| temp_file.write(uploaded_file.read()) | |
| temp_filepath = temp_file.name | |
| with col1: | |
| st.info("Uploaded PDF File") | |
| displayPDF(temp_filepath) | |
| with col2: | |
| st.info("Summarization") | |
| input_text = extract_text_from_pdf(temp_filepath) | |
| if input_text: # Proceed only if text extraction was successful | |
| summary = llm_pipeline(input_text) | |
| st.success(summary) | |
| # Text Input Section | |
| st.header("Summarize Your Text") | |
| user_input = st.text_area("Enter your content here:", height=200) | |
| if st.button("Summarize Text"): | |
| if user_input.strip(): | |
| col1, col2 = st.columns(2) | |
| with col1: | |
| st.info("Original Content") | |
| st.write(user_input) | |
| with col2: | |
| st.info("Summarization") | |
| summary = llm_pipeline(user_input) | |
| st.success(summary) | |
| else: | |
| st.warning("Please enter some content to summarize.") | |
| if __name__ == '__main__': | |
| main() | |