College AI Bot: Multilingual AI College Enquiry Assistant

Abstract

Accessing accurate and up-to-date information about colleges is often challenging for students due to scattered data across multiple websites and platforms. To address this issue, this paper presents a Multilingual College AI Bot, a smart conversational assistant designed to provide students with instant access to information related to admissions, courses, fees, placements, and campus facilities. The system is developed using the Django web framework and integrates advanced Large Language Models (LLMs) through Google Gemini and OpenAI APIs to generate intelligent and context-aware responses. The proposed system employs a Retrieval- Augmented Generation (RAG) architecture that combines FAISS-based vector search with BM25 keyword retrieval to improve the accuracy and relevance of responses. Additionally, an asynchronous web crawling module built with Playwright continuously gathers data from official college websites and educational sources, ensuring that the chatbot provides updated information. The chatbot supports multilingual interaction in English, Telugu, Hindi, and Kannada, along with voice input and output capabilities, enabling natural and accessible communication for diverse users. Experimental evaluation demonstrates that the proposed system improves information accessibility, reduces response time, and enhances user interaction compared to traditional static information portals. The system provides a scalable solution for educational institutions seeking to automate student support and information delivery.

Introduction

Educational institutions increasingly face challenges in providing students with fast, accurate, and accessible information about admissions, courses, fees, placements, and campus facilities. Traditional methods such as static websites, brochures, and manual help desks are often slow, fragmented, and unable to handle large volumes of student queries effectively, leading to delays and poor user experience. To address these issues, the study proposes a Multilingual College AI Bot, an intelligent conversational system designed to automate student support.

The system leverages recent advances in Artificial Intelligence, Natural Language Processing, and Large Language Models (LLMs) to understand and respond to student queries in real time. It integrates a Retrieval-Augmented Generation (RAG) framework that combines semantic search (FAISS) and keyword-based retrieval (BM25) to fetch relevant institutional information before generating responses using models like Google Gemini and OpenAI. This helps ensure responses are accurate, context-aware, and grounded in reliable data, reducing hallucination issues common in LLMs.

A key feature of the system is its hybrid knowledge pipeline, which continuously collects updated information from official college sources using automated web crawling (Playwright). The chatbot also supports multilingual interaction (English, Telugu, Hindi, Kannada) along with voice-based input and output, making it more accessible to diverse users. It processes queries through language detection, translation, retrieval, and response generation stages, ensuring smooth conversational interaction.

Existing systems are mostly rule-based, static, and lack multilingual and real-time update capabilities, making them less effective for modern educational needs. In contrast, the proposed system offers a scalable and intelligent solution that improves accessibility, reduces administrative workload, and enhances the student experience.

Overall, the paper presents a RAG-based multilingual AI chatbot that integrates dynamic data retrieval, large language models, and conversational AI to deliver accurate, real-time, and user-friendly college information services.

Conclusion

Accessing accurate and comprehensive information about colleges through traditional methods such as static websites, manual inquiries, or physical visits can often be time-consuming and inefficient. To address this challenge, this paper presented a Multilingual College AI Bot, an intelligent conversational system designed to assist students and parents in obtaining information related to admissions, courses, fee structures, placements, and campus facilities through a unified and user-friendly interface. The proposed system integrates Retrieval-Augmented Generation (RAG) with hybrid retrieval techniques, combining FAISS-based semantic vector search and BM25 keyword search to retrieve relevant information from a structured knowledge base. The retrieved information is then processed using Large Language Models accessed through the SDK, enabling the chatbot to generate accurate and context-aware responses. In addition, the chatbot supports multilingual communication in English, Telugu, Hindi, and Kannada, along with voice-based interaction, allowing users to communicate naturally with the system. The integration of an automated web crawling module using Playwright ensures that the chatbot can collect updated information from official college websites and other reliable sources, improving the relevance and accuracy of responses. Experimental evaluation demonstrates that the proposed system effectively handles diverse student queries while reducing response time and improving accessibility. By combining conversational AI, hybrid retrieval mechanisms, and multilingual interaction, the system provides a scalable and efficient solution for college information assistance. In the future, the chatbot can be enhanced by incorporating image- based information retrieval, recommendation systems for courses and colleges, and additional language support, further improving the usability and intelligence of the system.

References

[1] Selvi, V. Mounika, V. Rubika, and B. Uvadharanee, “Collegebot: Virtual assistant system for enquiry using natural language processing,” in 2024 2nd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), IEEE, 2024, pp. 1407–1414. [2] Z. Li et al., “Retrieval-Augmented Generation for Educational Applications: A Survey,” Artificial Intelligence Review, 2025. [3] J. Swacha, “Retrieval-Augmented Generation (RAG) Chatbots for Education: A Survey of Applications,” Applied Sciences, vol. 15, 2025. [4] S. Imambi, K. B. Prakash, and G. R. Kanagachidambaresan, “PyTorch,” in Programming with TensorFlow: Solution for Edge Computing Applications, 2021, pp. 87–104. [5] M. Thway et al., “Battling Botpoop Using GenAI for Higher Education: A Study of a Retrieval-Augmented Generation Chatbot’s Impact on Learning,” arXiv, 2024. [6] R. Yang et al., “RAGVA: Engineering Retrieval- Augmented Generation Conversational Applications,” Information and Software Technology, 2025. [7] N. Ingale, T. A. Jha, R. Dixit, and V. K. Borate, “College enquiry chatbot using RASA,” 2021. [8] A. Alabbas and K. Alomar, “Tayseer: A novel AI-powered Arabic chatbot framework for technical and vocational student helpdesk services and enhancing student interactions,” Applied Sciences, vol. 14, no. 6, p. 2547, 2024. [9] C. Manning and H. Schütze, Foundations of Statistical Natural Language Processing. MIT Press, 1999 [10] S. K. Assayed, M. Alkhatib, and K. Shaalan, “Enhancing student services: Machine learning chatbot intent recognition for high school inquiries,” in BUID Doctoral Research Conference 2023: Multidisciplinary Studies, Springer, 2024, pp. 243–254. [11] H. Koundinya, A. K. Palakurthi, V. Putnala, and A. Kumar, “Smart college chatbot using ML and Python,” in 2020 International Conference on System, Computation, Automation and Networking (ICSCAN), IEEE, 2020, pp. 1–5. [12] S. Janapreethi, S. Janapriya, M. Sarulatha, and G. R. Hemalakshmi, “College enquiry chatbot,” in 2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN), IEEE, 2023, pp. 1–4. [13] B. Gayathri, G. A. E. Satish Kumar, T. Prashanth, and B. Manoj Kumar, “Vardhagenie: Advancing student support through AI,” in 2024 International Conference on Smart Systems for Applications in Electrical Sciences (ICSSES), IEEE, 2024, pp. 1–6. [14] N. A. Al-Madi, K. A. Maria, M. A. Al-Madi, and E. A. Maria, “An inquiry smart chatbot system for Al- Zaytoonah University of Jordan,” Bulletin of Electrical Engineering and Informatics, vol. 13, no. 4, pp. 2758–2773, 2024. [15] S. Neupane et al., “From questions to insightful answers: Building an informed chatbot for university resources,” arXiv preprint arXiv:2405.08120, 2024. [16] D. Patel, N. Shetty, P. Kapasi, and I. Kangriwala, “College enquiry chatbot using conversational AI,” International Journal for Research in Applied Science & Engineering Technology (IJRASET), vol. 11, no. 5, 2023. [17] Deshpande et al., “Implementation of an NLP- driven chatbot and ML algorithms for career counseling,” in 2024 International Conference on Inventive Computation Technologies (ICICT), IEEE, 2024, pp. 853–859

Copyright

Copyright © 2026 Nimmakayala VenkataLakshmi , Pogadadanda Varalakshmi , Nimmakayala Ishwarya , Talluri Swathi . This 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.