Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from transformers import pipeline, AutoModelForSeq2SeqLM, AutoTokenizer | |
| import pytesseract | |
| from PIL import Image | |
| import requests # For downloading PDFs (optional) | |
| import numpy as np | |
| # Download PDF function (optional) | |
| def download_pdf(url): | |
| try: | |
| response = requests.get(url, stream=True) | |
| if response.status_code == 200: | |
| with open("temp.pdf", "wb") as f: | |
| for chunk in response.iter_content(1024): | |
| f.write(chunk) | |
| return True | |
| else: | |
| st.error("Error downloading PDF") | |
| return False | |
| except Exception as e: | |
| st.error(f"Error: {e}") | |
| return False | |
| # OCR function | |
| def extract_text(file): | |
| if not file: | |
| return None | |
| if file.type == "application/pdf": | |
| # Download PDF if URL provided (optional) | |
| if st.checkbox("Document is a URL?"): | |
| pdf_url = st.text_input("Enter the PDF URL:") | |
| if pdf_url and download_pdf(pdf_url): | |
| file = open("temp.pdf", "rb") | |
| else: | |
| return None | |
| # Use PyTesseract for PDF OCR | |
| pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe" # Update path if needed | |
| text = pytesseract.image_to_string(Image.open(file)) | |
| return text | |
| elif file.type in ("image/jpeg", "image/png"): | |
| # Use PyTesseract for image OCR | |
| pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe" # Update path if needed | |
| text = pytesseract.image_to_string(Image.open(file)) | |
| return text | |
| else: | |
| st.error("Please upload a PDF or image file") | |
| return None | |
| # Urdu content generation model (replace with your preferred model) | |
| urdu_gen_model_name = "mwz/UrduGPT2" # Replace placeholder | |
| # Load the model using TensorFlow weights | |
| urdu_gen_pipe = pipeline("text-generation", model=urdu_gen_model_name, framework="tf") | |
| def answer_questions(document, question): | |
| if not document or not question: | |
| return None | |
| # Use a pre-trained RAG model for Urdu (needs to be implemented) | |
| # You can explore custom RAG models with Urdu models like Udify | |
| # This section is a placeholder until an Urdu RAG model is available. | |
| # Example using a non-Urdu RAG model (for demonstration purposes) | |
| rag_model_name = "facebook/bart-large-cnn" # Replace with Urdu RAG (if available) | |
| rag_pipe = pipeline("question-answering", model=rag_model_name) | |
| answer = rag_pipe({"question": question, "context": document})["answer"] | |
| return answer | |
| def main(): | |
| st.title("Urdu Question Answering App") | |
| st.write("This app uses OCR to extract text from your document and a generative model to answer your questions in Urdu.") | |
| uploaded_file = st.file_uploader("Upload Reference Document (PDF or Image)") | |
| document = extract_text(uploaded_file) | |
| if document: | |
| st.success("Document Text Extracted!") | |
| st.write(document) | |
| question = st.text_input("Ask your question in Urdu:") | |
| if question: | |
| answer = answer_questions(document, question) | |
| if answer: | |
| st.success("Answer:") | |
| st.write(answer) | |
| else: | |
| st.warning("Couldn't find an answer. Try rephrasing your question.") | |
| if __name__ == "__main__": | |
| main() | |