News
A Python tool that uses Google's Gemini AI to automatically extract structured metadata from PDF and DOCX documents, saving results to Excel for easy analysis and organizing raw responses as JSON ...
TaskHubApi2/ ├── parser/ │ ├── usb_pd_parser.py # Extract ToC from PDF │ ├── chunk_pdf_by_toc.py # Chunk PDF into sections │ ├── qa_from_chunks.py # Question-answer interface ├── pdfs/ │ └── ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback