Rancang Bangun Asisten Virtual untuk Layanan Bengkel Berbasis Retrieval-Augmented Generation dan Tool Calling
-
Patrick Ardian Yoga Purnomo
*
Universitas Stikubank, Semarang,
Indonesia
- Dwi Budi Santoso Universitas Stikubank, Semarang, Indonesia (*) Corresponding Author
Abstract
The development of Artificial Intelligence (AI) has created new opportunities for Small and Medium Enterprises (SMEs) to improve customer service quality through communication automation. C Maestro Workshop in Semarang still handles customer inquiries manually through telephone and messaging applications, resulting in delayed responses to service cost inquiries, service reservations, and vehicle repair status updates. These services also depend on staff availability and cannot be provided consistently on a 24-hour basis, leading to inefficient customer service and potentially reducing customer satisfaction. This study aims to design and develop a Retrieval-Augmented Generation (RAG)-based virtual assistant utilizing the OpenRouter Application Programming Interface (API) to address these issues. The system was developed using a TypeScript-based client-server architecture running on the Node.js runtime environment. The RAG approach was implemented through a context injection mechanism by integrating the workshop's internal knowledge base, which includes service information, estimated service costs, Frequently Asked Questions (FAQ), initial diagnostic guidance, and other supporting information, into the system prompt of the Large Language Model (LLM). In addition, the system implements a tool-calling mechanism that enables the virtual assistant to perform business functions such as service reservations, vehicle repair status inquiries, and complaint escalation to mechanics. Operational data are stored in an SQLite database, while the user interface is provided through a web-based chat application with Server-Sent Events (SSE) support to deliver real-time responses. The evaluation results indicate that the system is capable of generating relevant responses based on the knowledge base, automating the service reservation process, and escalating requests beyond its capabilities. This study contributes by developing a virtual assistant architecture that integrates Retrieval-Augmented Generation (RAG) based on context injection with a tool calling mechanism using the OpenRouter API to support both information services and workshop operational processes. Therefore, the developed virtual assistant offers an effective, practical, and cost-efficient digital solution for supporting the digital transformation of customer services in small and medium-sized automotive workshops.
Downloads
References
Albert, G. D., & Voutama, A. (2025). Pengembangan Chatbot Berbasis Pdf Menggunakan Local Retrieval-Augmented Generation (Rag) Dan Ollama. Jurnal Informatika Dan Teknik Elektro Terapan, 13(2). https://doi.org/10.23960/jitet.v13i2.6361
Dharma, R., Raya, A., Lia, F., Cahyanti, D., & Mandiri, N. (2025). Perancangan Sistem Informasi Chatbot Retrieval Augmented Generation Berbasis Website Pada PT. Revolusi Cita Edukasi. Journal Computer Science, 4(1), 15–21. https://doi.org/10.31294/m75d4782
Elysia, S., & Herianto. (2024). Chatbot Berbasis Retrieval Augmented Generation (RAG) untuk Peningkatan Layanan Informasi Sekolah. Journal TIFDA (Technology Information and Data Analytic), 1(2), 52–58. https://doi.org/10.70491/tifda.v1i2.52
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2024). Retrieval-Augmented Generation for Large Language Models: A Survey. http://arxiv.org/abs/2312.10997
Hidayah Nova, S., Puji Widodo, A., & Warsito, B. (2022). Analisis Metode Agile pada Pengembangan Sistem Informasi Berbasis Website: Systematic Literature Review Analysis of Agile Method on Website-Based Information System Development: Systematic Literature Review. Techno.COM, 21(1), 139–148. https://doi.org/10.33633/tc.v21i1.5659
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. http://arxiv.org/abs/2005.11401
Mozilla Developer Network. (2024). Using Server-Sent Events. Mozilla Developer Network. https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events
OpenAI. (2024). OpenAI API Documentation. OpenAI. https://platform.openai.com/docs
OpenJS Foundation. (2024). Node.js Documentation. https://nodejs.org/docs/latest/api/
Patil, S. G., Zhang, T., Wang, X., & Gonzalez, J. E. (2023). Gorilla: Large Language Model Connected with Massive APIs. http://arxiv.org/abs/2305.15334
Pressman, R. S., & Maxim, B. R. (2020). Software Engineering: A Practitioner’s Approach (9th ed.). McGraw-Hill Education.
Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., Qian, B., Zhao, S., Hong, L., Tian, R., Xie, R., Zhou, J., Gerstein, M., Li, D., Liu, Z., & Sun, M. (2023). ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs. http://arxiv.org/abs/2307.16789
Ram, O., Levine, Y., Dalmedigos, I., Muhlgay, D., Shashua, A., Leyton-Brown, K., & Shoham, Y. (2023). In-Context Retrieval-Augmented Language Models. http://arxiv.org/abs/2302.00083
Russell, S. J. ., Norvig, Peter., Chang, M.-Wei., Devlin, Jacob., Dragan, Anca., Forsyth, David., Goodfellow, Ian., Malik, Jitendra., Mansinghka, Vikash., Pearl, Judea., & Wooldridge, M. J. . (2021). Artificial intelligence : a modern approach. Pearson.
Saidi Rahman, M., Ekawati, F., & Indra Wijaya, Y. (2025). Chatbot Ai Sebagai Media Pencarian Informasi Dengan Menggunakan Metode Large Language Models (Llm) Ai Chatbot As A Media For Searching Information With Natural Language Processing Methods. In Jurnal Sains Komputer dan Teknologi Informasi e-issn (Vol. 7, Number 2). https://doi.org/DOI:10.33084/jsakti.v7i2.9952
Saman, M., Ahmad, G., Alfarisy, F., Amelia, R., & Fadhliana, N. R. (2025). A RAG-Based Academic Information Chatbot Using Lightweight LLaMA and Indo-Sencence-BERT. Indonesian Journal of Artificial Intelligence and Data Mining (IJAIDM), 8(3), 687–696. https://doi.org/10.24014/ijaidm.v8i3.38150
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023). Toolformer: Language Models Can Teach Themselves to Use Tools. https://doi.org/10.48550/arXiv.2302.04761
Sugiyono. (2022). Metode Penelitian Kuantitatif, Kualitatif, dan R&D (2nd ed.). Alfabeta.
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., Zhao, W. X., Wei, Z., & Wen, J. (2024). A survey on large language model based autonomous agents. In Frontiers of Computer Science (Vol. 18, Number 6). Higher Education Press Limited Company. https://doi.org/10.1007/s11704-024-40231-1
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang, C., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang, X., Liu, Z., … Wen, J.-R. (2023). A Survey of Large Language Models. http://arxiv.org/abs/2303.18223
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Rancang Bangun Asisten Virtual untuk Layanan Bengkel Berbasis Retrieval-Augmented Generation dan Tool Calling
Pages: 1134-1144
Copyright (c) 2026 Patrick Ardian Yoga Purnomo, Dwi Budi Santoso
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
