Abstract：Automated Knowledge Organization AI ML based Subject Indexing System for Libraries The research study as reported here is an attempt to explore the possibilities of an AIML-based semi-automated indexing system in a library setup to handle large volumes of documentsIt uses the Python virtual environment to install and configure an open source AI environmentnamed Annifto feed the LODLinked Open Datadataset of Library of Congress Subject HeadingsLCSHas a standard KOSKnowledge Organization SystemThe framework deployed the Turtle format of LCSH after cleaning the file with Skosifyapplied TF-IDF as a language modelbackend algorithmand selected Snowball as an analyzerThe training of Annif was conducted with a large set of bibliographic records populated with subject descriptorsMARC tag 650aand indexed by trained LIS professionalsThe training dataset is first treated with MarcEdit to export it in a format suitable for OpenRefineand then in OpenRefine it undergoes many steps to produce a bibliographic record set suitable to train AnnifThe frameworkafter traininghas been tested with a bibliographic dataset to measure indexing efficienciesand finallythe automated indexing framework is integrated with a data wrangling softwareOpenRefineto produce suggested headings on a mass scaleThe entire framework is based on open source softwareopen datasetsand open standards Library AutomationThis involves the establishment of a semi-automatic index system using AIMLRetrieval and IndexingThe core of this research is an automatic index systemwhich involves the search and index of a large number of documentsMachine learningThe article refers to the semi-automatic index system that uses the AIMLmachine learningfoundationand the training process of AnnifMode recognitionTF-IDF is the application of the language modelback-end algorithmand the test of the automatic index frameworkNLPArticle focuses on indexing and theme markswhich is related to the field of natural language processing