Spaces:
Running
Running
| import streamlit as st | |
| import PyPDF2 | |
| from transformers import pipeline | |
| import pytesseract | |
| from PIL import Image, ImageEnhance, ImageFilter | |
| # Load pre-trained model and tokenizercheckpoint ="facebook/bart-large-cnn" | |
| checkpoint ="facebook/bart-large-cnn" | |
| model = pipeline('summarization', model=checkpoint) | |
| # Streamlit UI | |
| st.title("Text Summarizer using LLM") | |
| # Function to extract text from PDF | |
| def extract_text_from_pdf(pdf_file): | |
| pdf_reader = PyPDF2.PdfReader(pdf_file) | |
| for page_num in range(len(pdf_reader.pages)): | |
| page = pdf_reader.pages[page_num] | |
| text = page.extract_text() | |
| return text | |
| def summarize_text(text): | |
| summary = model(text, min_length=256, max_length=512, do_sample=True)[0]['summary_text'] | |
| return summary | |
| # Function to perform OCR on uploaded image | |
| def perform_ocr(image): | |
| # Enhance image | |
| # Perform OCR | |
| text = pytesseract.image_to_string(image, lang='eng', config='--psm 3') | |
| return text | |
| def answering(tex): | |
| question_answerer = pipeline("question-answering", model='distilbert-base-cased-distilled-squad') | |
| question = st.text_input("Enter your question:") | |
| if st.button("Answer Question"): | |
| # Generate the answer | |
| result = question_answerer(question=question,context=tex) | |
| # Display the answer | |
| st.subheader("Answer:") | |
| st.write(result["answer"]) | |
| # Radio button for selecting input format | |
| input_format = st.selectbox("Select input format:", ('Text', 'PDF', 'Image')) | |
| # PDF input box for the document to be summarized | |
| if input_format == 'Text': | |
| uploaded_file = st.file_uploader("Upload a text document (.txt)", type="txt") | |
| if uploaded_file is not None: | |
| text = uploaded_file.read().decode("utf-8") | |
| st.subheader("Original Text:") | |
| st.write(text) | |
| if st.button("Summarize"): | |
| # Generate the summary | |
| summary = summarize_text(text) | |
| # Display the summary | |
| st.subheader("Summary:") | |
| st.write(summary) | |
| answering(text) | |
| elif input_format == 'PDF': | |
| uploaded_file = st.file_uploader("Upload a PDF document", type="pdf") | |
| if uploaded_file is not None: | |
| text = extract_text_from_pdf(uploaded_file) | |
| st.subheader("Original Text:") | |
| st.write(text) | |
| if st.button("Summarize"): | |
| # Generate the summary | |
| summary = summarize_text(text) | |
| # Display the summary | |
| st.subheader("Summary:") | |
| st.write(summary) | |
| answering(text) | |
| elif input_format == 'Image': | |
| uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"]) | |
| if uploaded_image is not None: | |
| image = Image.open(uploaded_image) | |
| text = perform_ocr(image) | |
| st.subheader("Extracted Text from Image:") | |
| st.write(text) | |
| if st.button("Summarize"): | |
| # Generate the summary | |
| summary = summarize_text(text) | |
| # Display the summary | |
| st.subheader("Summary:") | |
| st.write(summary) | |
| answering(text) | |