Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{177598,
        author = {G. Santhoshi and Mamilla Rithika and Manda Anjani and Berelli Preetham Rao},
        title = {Generative AI Based Teaching Assistant},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {2958-2963},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177598},
        abstract = {Our project proposes a method for building GenAI-Based Teaching Assistant, an AI-powered educational tool designed to assist teachers by generating content and Bloom’s Taxonomy-based questions from either text input or uploaded documents. The system is built using OpenAI's GPT models and integrated with LangChain for orchestrating prompt management and document handling workflows. To ensure efficient semantic retrieval, we utilized Sentence Transformers for embedding the text and stored the vectorized content in ChromaDB. Document inputs, including PDFs, DOCX files, are processed using custom-built tools to clean, chunk, and summarize data before question generation. A Flask-based backend facilitates communication between the model and the user, while the web interface is designed using HTML, CSS, and JavaScript for intuitive usability. This assistant aims to reduce teachers' workload by automatically generating level-based questions, making educational content creation faster, structured, and more adaptive.},
        keywords = {Bloom’s Taxonomy, ChromaDB, GPT-4.0, Generative AI, LangChain, Large Language Models (LLMs), Natural Language Processing, OpenAI API, Question Generation, Sentence Transformers.},
        month = {May},
        }