Mirror: A Natural Language Interface for Data Querying, Summarization, and Visualization

Canwen Xu, Julian McAuley, Penghan Wang
3/15/2023
cs.DBcs.AIcs.CL

No official code found. Best implementation: mirror-data/mirror (44 stars, Apache-2.0, last commit 2023-04-13).

Abstract

We present Mirror, an open-source platform for data exploration and analysis powered by large language models. Mirror offers an intuitive natural language interface for querying databases, and automatically generates executable SQL commands to retrieve relevant data and summarize it in natural language. In addition, users can preview and manually edit the generated SQL commands to ensure the accuracy of their queries. Mirror also generates visualizations to facilitate understanding of the data. Designed with flexibility and human input in mind, Mirror is suitable for both experienced data analysts and non-technical professionals looking to gain insights from their data.

View on arXivView PDF

Code Implementations(1)

mirror-data/mirrorCommunity100%
Apache-2.0

Mirror: Plug-and-Play Data Query, Summarization and Visualization with Natural Language Interface

444CSS, DockerfileOct 21, 20223 years agoApache-2.0

Similar Papers

Demonstration of InsightPilot: An LLM-Empowered Automated Data Exploration System

85% match2023

Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey

84% match2023

Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow

84% match1 repo1.5k2023

Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models

84% match1 repo20.2k2024

PyThaiNLP: Thai Natural Language Processing in Python

83% match1 repo1.1k2023

DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis

83% match2026

Cite this paper

@article{xu2023mirror,
  title  = {Mirror: A Natural Language Interface for Data Querying, Summarization, and Visualization},
  author = {Canwen Xu and Julian McAuley and Penghan Wang},
  year   = {2023},
  eprint = {2303.08697},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.08697v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.08697.svg)](https://codeofpaper.com/paper/2303.08697)

Discussion