MATERNAL HEALTH BOT USING RAG ARCHITECTURE | IJCT Volume 13 – Issue 2 | IJCT-V13I2P100
International Journal of Computer Techniques
ISSN 2394-2231
Author
Ranga.Jaswanth, Ootla.Eswar Sai, G.Rajashekar, Ms. S.A.NEELAVANI
Abstract
This study describes the deployment of a voice-activated chatbot designed to assist expectant mothers by offering trustworthy maternal health information. To provide precise and contextually aware responses, the system employs a Retrieval-Augmented Generation (RAG) technique, which combines a language model with a local knowledge store. We developed this totally with free and open-source technologies to make the solution more accessible in rural or low-resource environments. Open-source approaches, such as Whisper for speech-to-text, are used to add voice capabilities. To ensure accuracy and validity, the data is also gathered from reputable sources like the WHO and other health portals. We used PDFs from these sources for RAG and stored them in vector databases for efficient document retrieval, as this system aims to bridge the information gap.
Keywords
Maternal health, RAG, chatbot, voice interface, NLP, vector database
Conclusion
In order to provide accurate and dependable information about maternity care utilizing open-source and free resources, the study introduces a voice-activated chatbot based on RAG architecture. For pregnant women in low-resource locations, the solution helps to close the information gap by integrating a lightweight, offline-friendly architecture.
Reducing hallucinations and improving accuracy, the chatbot gets verified information from reliable sources such as WHO and other national health portals, converts it into vector embeddings, and then responds.
Automation with agentic RAG and enhanced interactions with multilingual support are potential avenues for future growth. The project demonstrates how effective AI-powered solutions can be, even when implemented with little funding.
References
[1]S. H. Afrizal, N. Hakiem, A. Erna Permanasari, H. Syaifullah Albab, G. Yoki Sanjaya and L. Lazuardi, “A User-Centered Design of Natural Language Processing for Maternal Monitoring Chatbot System,” 2022 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), Jakarta, Indonesia, 2022, pp. 244-
248,doi:10.1109/ICIMCIS56303.2022.1
0017517. [2]S. Vakayil, D. S. Juliet, A. J and S. Vakayil, “RAG-Based LLM Chatbot Using Llama-2,” 2024 7th International Conference on Devices, Circuits and Systems (ICDCS), Coimbatore, India, 2024, pp. 1-5, doi: 10.1109/ICDCS59278.2024.10561020.
[3]D. Balasooriya et al., “Baby Bump: A Monitoring System for Pregnant Mothers and Babies,” 2024 IEEE 9th International Conference for Convergence in Technology (I2CT), Pune, India, 2024, pp. 1-6, doi: 10.1109/I2CT61223.2024.10544017 [4]A. Ilapaka and R. Ghosh, “A Comprehensive RAG-Based LLM for AI-Driven Mental Health Chatbot,” 2025 7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA), Ankara, Turkiye, 2025, pp. 1-5, doi: 10.1109/ICHORA65333.2025.1101701
7.
[5]P. Lewis, E. Perez, A. Piktus, F. Petroni,
V. Karpukhin, N. Goyal, H. Schwenk, D. Kiela, and S. Riedel, “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” in Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 9459–9474. [Online].
Available: https://arxiv.org/abs/2005.11401
[6]A. Singh, N. Gupta, and S. Das, “Agentic-RAG: A Survey on Agentic Retrieval-Augmented Generation,” arXiv preprint, arXiv:2501.09136, 2025. [Online]. Available:
https://arxiv.org/abs/2501.09136
How to Cite This Paper
Ranga.Jaswanth, Ootla.Eswar Sai, G.Rajashekar, Ms. S.A.NEELAVANI (2026). MATERNAL HEALTH BOT USING RAG ARCHITECTURE. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
