Spaces:
Sleeping
Sleeping
| import PyPDF2 | |
| import gradio as gr | |
| import json | |
| from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM | |
| # Função para extrair texto do PDF | |
| def extract_text_from_pdf(pdf_file): | |
| reader = PyPDF2.PdfReader(pdf_file) | |
| text = "" | |
| for page in reader.pages: | |
| text += page.extract_text() | |
| return text | |
| # Função para gerar perguntas e respostas usando um modelo da Hugging Face | |
| def generate_qa_pairs(text): | |
| tokenizer = AutoTokenizer.from_pretrained("valhalla/t5-base-qg-hl") | |
| model = AutoModelForSeq2SeqLM.from_pretrained("valhalla/t5-base-qg-hl") | |
| inputs = tokenizer.encode("generate questions: " + text, return_tensors="pt", max_length=512, truncation=True) | |
| outputs = model.generate(inputs, max_length=512, num_beams=4, early_stopping=True) | |
| questions = [tokenizer.decode(output, skip_special_tokens=True) for output in outputs] | |
| # O modelo retorna apenas as perguntas, então precisamos criar respostas fictícias para o exemplo | |
| qas = [{"question": question, "answer": "answer", "answer_start": 0} for question in questions] | |
| return qas | |
| # Função para converter os pares de QA no formato SQuAD | |
| def convert_to_squad_format(qas, context): | |
| squad_data = [] | |
| for i, qa in enumerate(qas): | |
| entry = { | |
| "title": "Generated Data", | |
| "context": context, | |
| "question": qa['question'], | |
| "id": str(i), | |
| "answers": { | |
| "answer_start": [qa['answer_start']], | |
| "text": [qa['answer']] | |
| } | |
| } | |
| squad_data.append(entry) | |
| return squad_data | |
| # Função para salvar os dados no formato SQuAD | |
| def save_to_json(data, file_name): | |
| if not file_name.endswith(".json"): | |
| file_name += ".json" | |
| with open(file_name, "w", encoding='utf-8') as f: | |
| json.dump(data, f, ensure_ascii=False, indent=4) | |
| return file_name | |
| # Função principal para ser usada no Gradio | |
| def process_pdf(pdf_file, file_name): | |
| context = extract_text_from_pdf(pdf_file) | |
| qas = generate_qa_pairs(context) | |
| squad_data = convert_to_squad_format(qas, context) | |
| file_path = save_to_json(squad_data, file_name) | |
| return file_path | |
| # Interface Gradio | |
| with gr.Blocks() as demo: | |
| with gr.Row(): | |
| pdf_file = gr.File(label="Upload PDF", file_types=[".pdf"]) | |
| file_name = gr.Textbox(label="Output JSON File Name", value="squad_dataset") | |
| process_button = gr.Button("Process PDF") | |
| download_link = gr.File(label="Download JSON", interactive=False) | |
| process_button.click(fn=process_pdf, inputs=[pdf_file, file_name], outputs=download_link) | |
| demo.launch() |