International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | JITD AI, a Fully Offline RAG-based University Assistant System using Local LLM with Ollama |
|---|---|
| ABSTRACT | Large Language Models (LLMs) are widely used in applications such as chatbots, code generation, and automated assistance systems. However, most existing LLMs rely on cloud-based platforms, creating challenges related to data privacy, internet dependency, latency, and cost. In secure or low-connectivity environments, these systems may become less efficient. This project aims to develop a fully offline Local LLM-based system that can generate responses, execute code, and detect errors directly on a local machine. The system integrates locally deployed LLMs with Natural Language Processing (NLP) and runtime |
| AUTHOR | SPANDANA MAHADEVAPPA KANDAGAL, VASISTHA C V, SUDEEP SAGAR, RITHIN P VALI, DR. LATHA BM, MANJULA P UG Students, Dept. of CSE, Jain Institute of Technology Davanagere, Karnataka, India Head and Professor, Dept. of CSE, Jain Institute of Technology Davanagere, Karnataka, India Assistant Professor, Dept. of CSE, Jain Institute of Technology Davanagere, Karnataka, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405071 |
| pdf/71_JITD AI, a Fully Offline RAG-based University Assistant System using Local LLM with Ollama.pdf | |
| KEYWORDS | |
| References | 1. Kechaoui, T., Ouhab, M. W., Djamaa, B., & Senouci, M. R. (2025, April). Locally-deployed Open-source LLMs for Code Generation: Promises and Challenges. In 2025 7th International Conference on Pattern Analysis and Intelligent Systems (PAIS) (pp. 1-6). IEEE. 2. Umesh, R., & Kumar, P. (2025, October). AI-Powered Offline Voice Assistant for Rural Communities. In 2025 7th International Conference on Innovative Data Communication Technologies and Application (ICIDCA) (pp. 1468-1474). IEEE. 3. Anand, Yuvanesh, et al. "GPT4All: An ecosystem of open source compressed language models." Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023). 2023. 4. Jiang, Albert Q., Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot et al. "Mixtral of experts." arXiv preprint arXiv:2401.04088 (2024). 5. Wang, Yongheng, Wensheng Gan, and S. Yu Philip. "AI-Driven Log Analysis: Advances and Challenges." In 2025 IEEE International Conference on Big Data (BigData), pp. 7728-7743. IEEE, 2025. 6. Alam, M.S., Javed, Q., Akbar, M., Rehman, M.R.U. and Anwer, M.B., 2004, June. Adaptive load balancing architecture for snort. In 2004 International Networking and Communication Conference (pp. 48-52). IEEE. 7. Ogrezeanu, Iulian, Anamaria Vizitiu, Costin Ciușdel, Andrei Puiu, Simona Coman, Cristian Boldișor, Alina Itu et al. "Privacy-preserving and explainable AI in industrial applications." Applied Sciences 12, no. 13 (2022): 6395. 8. Dresselhaus, Nicole. "Case Study: Local LLM-Based NER with n8n and Ollama." (2025). 9. Simpson, J. (2023). Fetching Data, APIs, and Promises. In How JavaScript Works: Master the Basics of JavaScript and Modern Web App Development (pp. 223-258). Berkeley, CA: Apress. 10. Hayes-Roth, Barbara. "An architecture for adaptive intelligent systems." Artificial intelligence 72, no. 1-2 (1995): 329-365. 11. Marcondes, Francisco S., et al. "Using ollama." Natural Language Analytics with Generative Large-Language Models: A Practical Approach with Ollama and Open-Source LLMs. Cham: Springer Nature Switzerland, 2025. 23-35. 12. Long, Sifan, et al. "A survey on intelligent network operations and performance optimization based on large language models." IEEE Communications Surveys & Tutorials 27.6 (2025): 3915-3949. |
