Unlocking Insights: Semantic Search in Jupyter Notebooks

Li, Lan; Lv, Jinpeng

Permalink

https://hdl.handle.net/2142/122797 Copy

Description

Title

Unlocking Insights: Semantic Search in Jupyter Notebooks

Author(s)

• Li, Lan
• Lv, Jinpeng

Issue Date

2024-03-20

Keyword(s)

• semantic search
• large language model
• Jupyter Notebook

Abstract

Semantic search, a process aimed at delivering highly relevant search results by comprehending the searcher's intent and the contextual meaning of terms within a searchable dataspace, plays a pivotal role in information retrieval. In this paper, we investigate the application of large language models to enhance semantic search capabilities, specifically tailored for the domain of Jupyter Notebooks. Our objective is to retrieve generated outputs, such as figures or tables, associated functions and methods, and other pertinent information. In this study, we demonstrate a semantic search framework that achieves a comprehensive semantic understanding of the entire notebook's contents, enabling it to effectively handle various types of user queries. Key components of this framework include: 1). A data preprocessor is designed to handle diverse types of cells within Jupyter Notebooks, encompassing both markdown and code cells. 2). An innovative methodology is devised to address token size limitations that arise with code-type cells. We implement a finer-grained approach to data input, transitioning from the cell level to the function level, effectively resolving these issues.

Publisher

iSchools

Series/Report Name or Number

iConference 2024 Proceedings

Type of Resource

Other

Language

eng

Handle URL

https://hdl.handle.net/2142/122797

Copyright and License Information

Copyright 2024 is held by Lan Li and Jinpeng Lv. Copyright permissions, when appropriate, must be obtained directly from the authors.

Owning Collections