Perancangan Chatbot Fiqih Berbasis Retrieval-Augmented Generation Kitab Safinatun Najah
DOI:
https://doi.org/10.29407/rknp7t18Keywords:
chatbot fiqih, pesantren, retrieval-augmented generation, safinatun najah.Abstract
Pembelajaran fiqih di pesantren menghadapi tantangan, seperti kesulitan santri memahami teks Arab klasik dan ketergantungan pada ustadz akibat keterbatasan waktu. Penelitian ini mengembangkan chatbot fiqih berbasis Retrieval-Augmented Generation (RAG) dengan korpus tertutup kitab Safinatun Najah untuk santri kelas 1 Asasiyah di Pondok Pesantren Al-Ma’ruf Kediri. Pemilihan topik ini penting untuk meningkatkan kemandirian santri dalam mencari dalil fiqih secara akurat melalui teknologi. Metode penelitian menggunakan Research and Development (R&D) dengan model ADDIE, meliputi: analisis kebutuhan melalui observasi dan wawancara, perancangan arsitektur RAG dengan embedding multilingual-e5-large, implementasi menggunakan Python 3.11 dan LangChain serta antarmuka web berbasis Streamlit, serta evaluasi melalui black-box testing dan User Acceptance Test (UAT). Dataset disusun dari kitab Safinatun Najah menjadi sekitar 900 chunk teks. Pengujian awal menunjukkan sistem mampu memberikan jawaban relevan dengan respons cepat dan minim hallucination. Penelitian ini penting karena menyediakan media pembelajaran fiqih yang terkontrol, sehingga mendukung integrasi teknologi dalam pendidikan agama Islam di pesantren.
Downloads
References
[1] W. Fan et al., “A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., pp. 6491–6501, 2024, doi: 10.1145/3637528.3671470.
[2] A. Gan et al., “Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey,” vol. 0, no. 0, pp. 1–18, 2025, [Online]. Available: http://arxiv.org/abs/2504.14891
[3] L. Wang, N. Yang, X. Huang, L. Yang, R. Majumder, and F. Wei, “Multilingual E5 Text Embeddings: A Technical Report,” 2024, [Online]. Available: http://arxiv.org/abs/2402.05672
[4] M. Alshammary, M. N. Uddin, and L. Khan, “RFPG: Question-Answering from Low-Resource Language (Arabic) Texts using Factually Aware RAG,” Proc. - 2024 IEEE 10th Int. Conf. Collab. Internet Comput. CIC 2024, no. Cic, pp. 107–116, 2024, doi: 10.1109/CIC62241.2024.00023.
[5] O. Nacar and A. Koubaa, “Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning,” Stud. Comput. Intell., vol. 1214, pp. 179–216, 2025, doi: 10.1007/978-3-031-90573-5_6.
[6] W. Uriawan, A. O. Hamza, A. R. Nuralim, A. Purnama, A. J. Yunus, and A. A. S. Putri, “Implementing a Sharia Chatbot as a Consultation Medium for Questions About Islam,” 2025, [Online]. Available: http://arxiv.org/abs/2512.16644
[7] A. Rahman Ramadhan, “The AI Chatbot Phenomenon and Its Impact on Learning Fiqh (A Study of the Ethical Dimensions of Artificial Intelligence in Learning Islamic Jurisprudence),” Sci. Educ., vol. 3, pp. 177–186, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Muhammad Ichsan, Alvino Graha Nusantara
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
