CodexDB: Generating Code for Processing SQL Queries using GPT-3 Codex

Trummer, Immanuel

doi:10.48550/arxiv.2204.08941

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…"Text-to-SQL" [22] is a sub-domain of automated code generation in natural language processing. Numerous studies have been conducted to evaluate the accuracy of LLMs and prior machine learning approaches [2,[23][24][25]. However, little is known about the performance of LLMs when generating code for geospatial SQL queries.…”

Section: Introductionmentioning

confidence: 99%

Is ChatGPT a Good Geospatial Data Analyst? Exploring the Integration of Natural Language into Structured Query Language within a Spatial Database

Jiang,

Yang

2024

IJGI

View full text Add to dashboard Cite

With recent advancements, large language models (LLMs) such as ChatGPT and Bard have shown the potential to disrupt many industries, from customer service to healthcare. Traditionally, humans interact with geospatial data through software (e.g., ArcGIS 10.3) and programming languages (e.g., Python). As a pioneer study, we explore the possibility of using an LLM as an interface to interact with geospatial datasets through natural language. To achieve this, we also propose a framework to (1) train an LLM to understand the datasets, (2) generate geospatial SQL queries based on a natural language question, (3) send the SQL query to the backend database, (4) parse the database response back to human language. As a proof of concept, a case study was conducted on real-world data to evaluate its performance on various queries. The results show that LLMs can be accurate in generating SQL code for most cases, including spatial joins, although there is still room for improvement. As all geospatial data can be stored in a spatial database, we hope that this framework can serve as a proxy to improve the efficiency of spatial data analyses and unlock the possibility of automated geospatial analytics.

show abstract

Section: Introductionmentioning

confidence: 99%