Implementasi Chatbot Tafsir Al-Qur'an Menggunakan Chainlit dengan Pendekatan Groq: Implementing a Qur'anic Tafsir Chatbot Through Chainlit with a Groq-Based Approach

Muhammad Rizky Maulana; Nazruddin Safaat Harahap; Okfalisa Okfalisa; Yusra Yusra

doi:10.57152/malcom.v5i3.2082

Authors

Muhammad Rizky Maulana Universitas Islam Negeri Sultan Syarif Kasim Riau
Nazruddin Safaat Harahap Universitas Islam Negeri Sultan Syarif Kasim Riau
Okfalisa Okfalisa Universitas Islam Negeri Sultan Syarif Kasim Riau
Yusra Yusra Universitas Islam Negeri Sultan Syarif Kasim Riau

DOI:

https://doi.org/10.57152/malcom.v5i3.2082

Keywords:

Chainlit Chatbot, Groq, Kecerdasan Buatan, Tafsir

Abstract

Pemahaman terhadap tafsir Al-Qur’an sering kali menjadi tantangan dalam dunia pendidikan, khususnya bagi siswa, mahasiswa, atau masyarakat umum yang tidak memiliki latar belakang ilmu tafsir maupun kemampuan bahasa Arab. Keterbatasan akses terhadap tafsir yang mudah dipahami, serta ketiadaan media pembelajaran yang interaktif dan mampu menjawab pertanyaan secara kontekstual, menjadi hambatan dalam proses pembelajaran keislaman. Penelitian ini bertujuan untuk mengembangkan chatbot berbasis kecerdasan buatan (AI) sebagai media pendukung pembelajaran tafsir Al-Qur’an yang responsif dan adaptif. Sistem dirancang menggunakan framework Chainlit sebagai antarmuka web, didukung oleh Groq untuk mempercepat proses inferensi, serta integrasi LangChain dan Large Language Models (LLM) untuk memahami isi tafsir, khususnya Tafsir Jalalain dalam format PDF berbahasa Indonesia. Dokumen yang digunakan berupa satu file digital utuh yang representatif. Proses sistem meliputi ekstraksi teks, pembagian teks (chunking), pembentukan embedding, dan pencarian semantik berbasis vektor. Evaluasi menggunakan BERTScore menghasilkan nilai rata-rata precision sebesar 71,84%, recall 78,11%, dan F1-score 74,80%, menunjukkan kemampuan sistem dalam memberikan jawaban yang baik secara semantik. Hasil penelitian ini berkontribusi dalam menyediakan media pembelajaran tafsir digital berbasis AI yang efisien dan kontekstual, serta menjadi solusi potensial untuk mendukung proses pendidikan Islam yang lebih interaktif dan modern.

Downloads

Download data is not yet available.

References

A. S. Prihatinoto, N. Safaat Harahap, M. Irsyad, and I. Iskandar, “Question Answering System Tafseer Ibnu Katsir Using Large Language Models,” Jurnal Informatika & Rekayasa Elektronika), vol. 7, no. 1, pp. 68–79, Apr. 2024, doi: 10.36595/jire.v7i1.1155.

I. Fadilatul Kasmar, F. Anwar, and U. N. Padang, “Metode Guru dalam Mengatasi Kesulitan Belajar Alquran Peserta Didik,” An-Nuha: Jurnal Pendidikan Islam, vol. 1, no. 4, pp. 617–629, Nov. 2021, doi: https://doi.org/10.24036/annuha.v1i4.140.

F. Rizki, A. Sutiyo, N. S. Harahap, S. Agustian, and R. M. Candra, “KLIK: Kajian Ilmiah Informatika dan Komputer Implementasi Question Answering Berbasis Chatbot Telegram Pada Tafsir Al-Jalalain Menggunakan Langchain dan LLM,” Media Online, vol. 4, no. 5, pp. 2464–2472, Apr. 2024, doi: 10.30865/klik.v4i5.1784.

O. Topsakal and T. C. Akinci, “Creating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM Apps Fast,” in International Conference on Applied Engineering and Natural Sciences (ICAENS), Vol. 1, No. 1, Halaman 1050–1056, Jul. 2023. doi: 10.59287/icaens.1127.

Aji Bayu Permadi, Nazruddin Safaat H, Lestari Handayani, and Yusra, “Implementasi Question Answering System Tafsir Al-Azhar Menggunakan LangChain dan Large Language Model Berbasis Chatbot Telegram,” Jurnal Teknoif Teknik Informatika Institut Teknologi Padang, vol. 12, no. 1, pp. 62–69, Apr. 2024, doi: 10.21063/jtif.2024.v12.1.62-69.

A. Mansurova, A. Nugumanova, and Z. Makhambetova, “Development of a Question Answering Chatbot for Blockchain Domain,” Scientific Journal of Astana IT University, vol. 15, pp. 27–40, Sep. 2023, doi: 10.37943/15xndz6667.

A. Pesaru, S. Gill, and A. Tangella, “AI assistant for document management Using Lang Chain and Pinecone,” International Research Journal of Modernization in Engineering Technology and Science, Jun. 2023, doi: 10.56726/irjmets42630.

F. Soygazi and D. Oguz, “An Analysis of Large Language Models and LangChain in Mathematics Education,” in Proceedings of the 15th International Conference on Educational Technology (ICET ’23), ACM, Oct. 2023, pp. 92–97. doi: 10.1145/3633598.3633614.

M. Mulky Mar’arif, N. Safaat Harahap, and M. Affandes, “Sistem Tanya-Jawab Berbasis Chatbot Telegram Tentang Fiqih Kontemporer Menggunakan Langchain Dan LLM,” TEKNIKA, vol. 19, no. 2, pp. 1–5, Apr. 2025.

T. Medeiros, M. Medeiros, M. Azevedo, M. Silva, I. Silva, and D. G. Costa, “Analysis of Language-Model-Powered Chatbots for Query Resolution in PDF-Based Automotive Manuals,” Vehicles, vol. 5, no. 4, pp. 1384–1399, Dec. 2023, doi: 10.3390/vehicles5040076.

X. Zhong, J. Tang, and A. J. Yepes, “PubLayNet: largest dataset ever for document layout analysis,” Nat Commun, vol. 8, no. 1, Aug. 2019, doi: 10.1038/s41467-017-00439-1.

M. Y. Firdaus, “Digitalisasi Khazanah Ilmu Al-Qur’an dan Tafsir di Era Digital: Studi Analisis pada Website Tanwir.id,” Reslaj: Religion Education Social Laa Roiba Journal, vol. 5, pp. 2710–2716, 2023, doi: 10.47476/as.v5i6.2552.

W. Grosky and T. Ruas, Data Science for Software Engineers, 9th ed. McGraw-Hill Education, 2019.

T. Wolf et al., “Transformers: State-of-the-Art Natural Language Processing,” in Proceedings ofthe 2020 EMNLP (Systems Demonstrations), Nov. 2020, pp. 38–45. doi: 10.18653/v1/2020.emnlp-demos.6.

N. S. Harahap, A. Saad, and H. Ubaidullah, “Comprehensive Bibliometric Literature Review of Chatbot Research: Trends, Frameworks, and Emerging Applications,” (IJACSA) International Journal of Advanced Computer Science and Applications, vol. 16, no. 1, p. 2025, 2025, [Online]. Available: www.ijacsa.thesai.org

S. Xiang et al., “HeteroFlow: An Accelerator Programming Model with Decoupled Data Placement for Software-Defined FPGAs,” in FPGA 2022 - Proceedings of the 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, Association for Computing Machinery, Inc, Feb. 2022, pp. 78–88. doi: 10.1145/3490422.3502369.

L. Yuan, D.-J. Han, S. Wang, and C. G. Brinton, “Local-Cloud Inference Offloading for LLMs in Multi-Modal, Multi-Task, Multi-Dialogue Settings,” ArXiv, vol. 1, pp. 1–15, Feb. 2025, doi: 10.48550/arXiv.2502.11007.

C. Dasanayaka, K. Dandeniya, M. B. Dissanayake, C. Gunasena, and R. Jayasinghe, “Multimodal AI and Large Language Models for Orthopantomography Radiology Report Generation and Q&A,” Applied System Innovation, vol. 8, no. 2, Apr. 2025, doi: 10.3390/asi8020039.

K. Hrushikesh Koundinya, A. K. Palakurthi, V. Putnala, and A. K. Kumar, “Smart College Chatbot using ML and Python,” in 2020 International Conference on System, Computation, Automation and Networking, ICSCAN 2020, Institute of Electrical and Electronics Engineers Inc., Jul. 2020. doi: 10.1109/ICSCAN49426.2020.9262426.

A. Pak, A. Ziyaden, T. Saparov, I. Akhmetov, and A. Gelbukh, “Word Embeddings: A Comprehensive Survey,” Computacion y Sistemas, vol. 28, no. 4, pp. 2005–2029, 2024, doi: 10.13053/CyS-28-4-5225.

E. Meiliverani and C. Yefta, “Web-Based Chatbot with Natural Language Processing and Knuth-Morris-Pratt (Case Study: Universitas Internasional Batam),” Jurnal Sains dan Teknologi, vol. 11, pp. 132–141, 2022, doi: 10.23887/jst-undiksha.v11i1.

T. Zhang, V. Kishore, F. Wu, K. Q. Weinberger, and Y. Artzi, “BERTScore: Evaluating Text Generation with BERT,” in Proceedings of the 8th International Conference on Learning Representations (ICLR 2020), Apr. 2019. doi: 10.48550/arXiv.1904.09675.

M. Clinciu, A. Eshghi, and H. Hastie, “A Study of Automatic Metrics for the Evaluation of Natural Language Explanations,” in Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), Mar. 2021. doi: 10.18653/v1/2021.eacl-main.202.

C. Sun, X. Qiu, Y. Xu, and X. Huang, “How to Fine-Tune BERT for Text Classification?,” in Proceedings of the Chinese Computational Linguistics (CCL 2019), Lecture Notes in Computer Science, Springer, May 2019. doi: 10.1007/978-3-030-32381-3_16.

Y. Moslem, R. Haque, and A. Way, “Arabisc: Context-Sensitive Neural Spelling Checker,” in Proceedings of the 6th Workshop on Natural Language Processing Techniques for Educational Applications (NLPTEA), E. Yang, E. Xun, B. Zhang, and G. Rao, Eds., Suzhou: Association for Computational Linguistics, Feb. 2020, pp. 11–19. doi: https://doi.org/10.18653/v1/2020.nlptea-1.2.