Background

This webpage hosts the prototype of the PDF annotation tool: Yōyaku at current state. The tool annotates institutional PDF documents by retrieval of keywords and keyphrases using Large Language Models (LLM) dependent on Python packages SpaCY, RAKE, and Keybert. This is accomphished by a back-end pipeline that uses the response of a Google Form to initiate annotation of the uploaded PDF. The tool provides multi-language support and was developed as part of a personal project. The static version is displayed for security reasons and the prototype and belonging scripts are released under the license: Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) by ShakiraSA.