Copyright © 2026 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{205007,
        author = {Nilesh Navnath Koigade and Shruti Sanjay Nikade and Sanyog Shrimant Kamble and Sayali Vijay Karambe},
        title = {Design And Development Of An Intelligent Mental Health Support Chatbot Using Gemma LLM And Django Framework},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {4628-4633},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205007},
        abstract = {Mental health disorders affect over 970 million people worldwide, yet access to professional care remains severely limited by cost, stigma, geography, and workforce shortages. This paper presents Serene, a full-stack AI-powered mental health companion that integrates Google Gemma—a state-of-the-art open-weight large language model (LLM) accessed via the Hugging Face Inference Providers API—with clinically validated psychological assessment instruments (PHQ-9 and GAD-7), a four-step personalised onboarding pipeline, longitudinal mood analytics, and a context-aware memory system. The backend is built on Django 5 with Django REST Framework and a PostgreSQL database; the frontend is a React 18 single-page application. Serene achieves meaningful response personalisation through dynamic system-prompt injection derived from user-specific onboarding profiles. Preliminary evaluation indicates high user satisfaction and improved accessibility for underserved populations in South Asian contexts. This work demonstrates that production-grade mental health AI companions are attainable on accessible, open-weight LLMs without proprietary APIs or local GPU infrastructure.},
        keywords = {Mental Health, Chatbot, Large Language Model, Gemma, AI Healthcare, Natural Language Processing, Django, Personalisation, PHQ-9, GAD-7},
        month = {June},
        }