PDF-Document Chatbot Responses using Large Language Models  to Enable Smart City Engagement

Mutiara Auliya Khadija; Wahyu Nurharjadmo; Abdul Aziz; Ina Primasari

doi:10.30591/jpit.v10i3.8262

PDF-Document Chatbot Responses using Large Language Models to Enable Smart City Engagement

Mutiara Auliya Khadija, Wahyu Nurharjadmo, Abdul Aziz, Ina Primasari

Abstract

Traditional documents, including Rencana Pembangunan Jangka Menengah Daerah (RPJMD), Strategic Plans (Renstra), and e-masterplans, have undergone a remarkable transformation, evolving from their conventional printed formats to the dynamic realm of electronic versions. While this shift holds the promise of enhanced accessibility and convenience for the public, the full potential of these resources remains unrealized due to inherent challenges. On the other hand, a Generative AI approach is employed for the creation of an intelligent chatbot. Our primary contribution lies in the PDF-Document Chatbot Response utilizing Large Language Models (LLMs) GPT 3.5 Turbo from OpenAI, aimed at fostering engagement within Smart City. The dataset consists of Masterplan documents for Smart City development in Yogyakarta City, presented in PDF format and employing the Indonesian language. This research leverages the Large Language Models (LLMs) GPT-3.5 Turbo from OpenAI, in conjunction with user input and prompts. The development process for crafting this chatbot utilizes the LangChain Framework and Pinecone for storing vector embeddings. The results underscore the chatbot's capability to generate coherent responses closely aligned with the context found within the PDF document.

Keywords

PDF-Document Chatbot; Large Language Model; Open AI; Smart City.

Full Text:

References

B. Casselden and R. Pears, ‘Higher education student pathways to ebook usage and engagement, and understanding: Highways and cul de sacs’, J. Librariansh. Inf. Sci., vol. 52, no. 2, pp. 601–619, Jun. 2020, doi: 10.1177/0961000619841429.

B. C. Y. Lim, L. W. L. Liu, and C. Chian Hou, ‘Investigating the Effects of Interactive E-Book towards Academic Achievement’, Asian J. Univ. Educ., vol. 16, no. 3, p. 78, Oct. 2020, doi: 10.24191/ajue.v16i3.10272.

D. P. Srirahayu and G. C. Premananto, ‘The Printed Book and Electronic Book (Ebook) Experiences of Digital Natives in Indonesia’, J. Southwest Jiaotong Univ., vol. 55, no. 6, p. 17, 2020, doi: 10.35741/issn.0258-2724.55.6.17.

M. Gasco-Hernandez, G. Nasi, M. Cucciniello, and A. M. Hiedemann, ‘The role of organizational capacity to foster digital transformation in local governments: The case of three European smart city’, Urban Gov., vol. 2, no. 2, pp. 236–246, Dec. 2022, doi: 10.1016/j.ugj.2022.09.005.

S. S. Cruz and S. R. Paulino, ‘Experiences of innovation in public services for sustainable urban mobility’, J. Urban Manag., vol. 11, no. 1, pp. 108–122, Mar. 2022, doi: 10.1016/j.jum.2021.10.003.

J. K. Kim, M. Chua, M. Rickard, and A. Lorenzo, ‘ChatGPT and large language model (LLM) chatbots: The current state of acceptability and a proposal for guidelines on utilization in academic medicine’, J. Pediatr. Urol., p. S1477513123002243, Jun. 2023, doi: 10.1016/j.jpurol.2023.05.018.

R. Csaky, ‘Deep Learning Based Chatbot Models’, ArXiv190808835 Cs, Aug. 2019, Accessed: Jul. 11, 2020. [Online]. Available: http://arxiv.org/abs/1908.08835

D. Bahdanau, K. Cho, and Y. Bengio, ‘Neural Machine Translation by Jointly Learning to Align and Translate’, ArXiv14090473 Cs Stat, May 2016, Accessed: Sep. 03, 2020. [Online]. Available: http://arxiv.org/abs/1409.0473

D. W. Otter, J. R. Medina, and J. K. Kalita, ‘A Survey of the Usages of Deep Learning for Natural Language Processing’, IEEE Trans. Neural Netw. Learn. Syst., pp. 1–21, 2020, doi: 10.1109/TNNLS.2020.2979670.

R. Agarwal and M. Wadhwa, ‘Review of State-of-the-Art Design Techniques for Chatbots’, SN COMPUT SCI, vol. 1, no. 5, p. 246, Sep. 2020, doi: 10.1007/s42979-020-00255-3.

M. A. Khadija, Widyawan, and L. Edi Nugroho, ‘Deep learning Indonesian chatbot using PyTorch for customer support automation’, presented at the THE PROCEEDINGS OF THE 5TH INTERNATIONAL CONFERENCE ON MARITIME EDUCATION AND TRAINING (The 5th ICMET) 2021, Makassar, Indonesia, 2023, p. 020015. doi: 10.1063/5.0115529.

C. Zhou et al., ‘A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT’. arXiv, May 01, 2023. Accessed: Aug. 22, 2023. [Online]. Available: http://arxiv.org/abs/2302.09419

S. T. Islam and M. Nurul Huda, ‘Design and Development of Question Answering System in Bangla Language from Multiple Documents’, in 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), May 2019, pp. 1–4. doi: 10.1109/ICASERT.2019.8934447.

K. Lanyo and A. Wausi, ‘A Comparative Study of Supervised and Unsupervised Classifiers Utilizing Extractive Text Summarization Techniques to Support Automated Customer Query Question-Answering’, in 2018 5th International Conference on Soft Computing Machine Intelligence (ISCMI), Nov. 2018, pp. 88–92. doi: 10.1109/ISCMI.2018.8703237.

K. A. Hambarde and H. Proenca, ‘Information Retrieval: Recent Advances and Beyond’. arXiv, Jan. 20, 2023. Accessed: Aug. 18, 2023. [Online]. Available: http://arxiv.org/abs/2301.08801

A. Androutsopoulou, N. Karacapilidis, E. Loukis, and Y. Charalabidis, ‘Transforming the communication between citizens and government through AI-guided chatbots’, Gov. Inf. Q., vol. 36, no. 2, pp. 358–367, Apr. 2019, doi: 10.1016/j.giq.2018.10.001.

H. Naveed et al., ‘A Comprehensive Overview of Large Language Models’. arXiv, Aug. 18, 2023. Accessed: Aug. 22, 2023. [Online]. Available: http://arxiv.org/abs/2307.06435

N. Shi, Q. Zeng, and R. Lee, ‘Language Chatbot–The Design and Implementation of English Language Transfer Learning Agent Apps’, in 2020 IEEE 3rd International Conference on Automation, Electronics and Electrical Engineering (AUTEEE), Nov. 2020, pp. 403–407. doi: 10.1109/AUTEEE50969.2020.9315567.

A. U. Haq et al., ‘Detection of Breast Cancer Through Clinical Data Using Supervised and Unsupervised Feature Selection Techniques’, IEEE Access, vol. 9, pp. 22090–22105, 2021, doi: 10.1109/ACCESS.2021.3055806.

O. Topsakal and T. C. Akinci, ‘Creating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM Apps Fast’, Int. Conf. Appl. Eng. Nat. Sci., vol. 1, no. 1, pp. 1050–1056, Jul. 2023, doi: 10.59287/icaens.1127.

S. Hobert, A. Følstad, and E. L.-C. Law, ‘Chatbots for active learning: A case of phishing email identification’, Int. J. Hum.-Comput. Stud., vol. 179, p. 103108, Nov. 2023, doi: 10.1016/j.ijhcs.2023.103108.

P. Muangkammuen, N. Intiruk, and K. R. Saikaew, ‘Automated Thai-FAQ Chatbot using RNN-LSTM’, in 2018 22nd International Computer Science and Engineering Conference (ICSEC), Nov. 2018, pp. 1–4. doi: 10.1109/ICSEC.2018.8712781.

X. Zhang, X. Liang, A. Zhiyuli, S. Zhang, R. Xu, and B. Wu, ‘AT-LSTM: An Attention-based LSTM Model for Financial Time Series Prediction’, IOP Conf Ser Mater Sci Eng, vol. 569, p. 052037, Aug. 2019, doi: 10.1088/1757-899X/569/5/052037.

E. Wang, W. L. Putera, H. Lucky, and A. Chowanda, ‘Chatbot Application to Automate Services in FnB Business Using Seq2Seq LSTM’, in 2022 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), Nov. 2022, pp. 413–417. doi: 10.1109/ICIMCIS56303.2022.10017854.

M. A. Khadija, W. Nurharjadmo, and Widyawan, ‘Deep Learning Generative Indonesian Response Model Chatbot for JKN-KIS’, in 2022 1st International Conference on Smart Technology, Applied Informatics, and Engineering (APICS), Aug. 2022, pp. 70–74. doi: 10.1109/APICS56469.2022.9918686.

J. Ye et al., ‘A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models’, 2022.

J. Ju, L. Liu, and Y. Feng, ‘Citizen-centered big data analysis-driven governance intelligence framework for smart city’, Telecommun. Policy, vol. 42, no. 10, pp. 881–896, Nov. 2018, doi: 10.1016/j.telpol.2018.01.003.

P. I. Prayitno, R. P. Pujo Leksono, F. Chai, R. Aldy, and W. Budiharto, ‘Health Chatbot Using Natural Language Processing for Disease Prediction and Treatment’, in 2021 1st International Conference on Computer Science and Artificial Intelligence (ICCSAI), Oct. 2021, pp. 62–67. doi: 10.1109/ICCSAI53272.2021.9609784.

H. Chase, ‘Python LangChain’, Python LangChain, Jan. 08, 2023. https://python.langchain.com/docs/get_started/introduction

S. Kamnis, ‘Generative pre-trained transformers (GPT) for surface engineering’, Surf. Coat. Technol., vol. 466, p. 129680, Aug. 2023, doi: 10.1016/j.surfcoat.2023.129680.

E. Liberty, ‘Pinecone’, Pinecone, Jan. 08, 2023. https://www.pinecone.io/

DOI: https://doi.org/10.30591/jpit.v10i3.8262