Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Making a prototype of Seoul historical sites chatbot using Langchain

Jae Young Suh, Minsoo Kwak, Soo Yong Kim, Hyoungseo Cho

TL;DR

The paper tackles disseminating information about Seoul's historical sites to visitors via a chatbot. It combines Langchain, Streamlit, and the OpenAI API to build a conversational agent that operates on an English dataset provided by the Seoul Metropolitan Government. Due to limited data, the authors rely on vectorization with a Chroma store and prompting strategies to enable contextual, dataset-driven conversations. The work details the architecture, data flow, and potential improvements to data coverage and dialogue quality. It aims to promote cultural accessibility and hospitality, with future work focused on scaling data and enriching dialogue for broader cultural content.

Abstract

In this paper, we are going to share a draft of the development of a conversational agent created to disseminate information about historical sites located in the Seoul. The primary objective of the agent is to increase awareness among visitors who are not familiar with Seoul, about the presence and precise locations of valuable cultural heritage sites. It aims to promote a basic understanding of Korea's rich and diverse cultural history. The agent is thoughtfully designed for accessibility in English and utilizes data generously provided by the Seoul Metropolitan Government. Despite the limited data volume, it consistently delivers reliable and accurate responses, seamlessly aligning with the available information. We have meticulously detailed the methodologies employed in creating this agent and provided a comprehensive overview of its underlying structure within the paper. Additionally, we delve into potential improvements to enhance this initial version of the system, with a primary emphasis on expanding the available data through our prompting. In conclusion, we provide an in-depth discussion of our expectations regarding the future impact of this agent in promoting and facilitating the sharing of historical sites.

Making a prototype of Seoul historical sites chatbot using Langchain

TL;DR

The paper tackles disseminating information about Seoul's historical sites to visitors via a chatbot. It combines Langchain, Streamlit, and the OpenAI API to build a conversational agent that operates on an English dataset provided by the Seoul Metropolitan Government. Due to limited data, the authors rely on vectorization with a Chroma store and prompting strategies to enable contextual, dataset-driven conversations. The work details the architecture, data flow, and potential improvements to data coverage and dialogue quality. It aims to promote cultural accessibility and hospitality, with future work focused on scaling data and enriching dialogue for broader cultural content.

Abstract

In this paper, we are going to share a draft of the development of a conversational agent created to disseminate information about historical sites located in the Seoul. The primary objective of the agent is to increase awareness among visitors who are not familiar with Seoul, about the presence and precise locations of valuable cultural heritage sites. It aims to promote a basic understanding of Korea's rich and diverse cultural history. The agent is thoughtfully designed for accessibility in English and utilizes data generously provided by the Seoul Metropolitan Government. Despite the limited data volume, it consistently delivers reliable and accurate responses, seamlessly aligning with the available information. We have meticulously detailed the methodologies employed in creating this agent and provided a comprehensive overview of its underlying structure within the paper. Additionally, we delve into potential improvements to enhance this initial version of the system, with a primary emphasis on expanding the available data through our prompting. In conclusion, we provide an in-depth discussion of our expectations regarding the future impact of this agent in promoting and facilitating the sharing of historical sites.
Paper Structure (10 sections, 4 figures)

This paper contains 10 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Methods
  3. Langchain
  4. Streamlit
  5. OpenAI API
  6. Structure
  7. Discussion
  8. Conclusion
  9. Bibliographical References
  10. Language Resource References

Figures (4)

  • Figure 1: The overall structure of the conversational agent
  • Figure 2: A sample result of the conversation between the user and the agent
  • Figure 3: A result of conversation generation with "Make conversation with the dataset" prompt
  • Figure 4: A sample response with "Suggest further questions on Seoul's heritage." prompt