datasight [SWR-26-045]

RESOURCE

Abstract

This software is an AI-powered data exploration with natural language. datasight connects an AI agent to your database and provides a web UI where you can ask questions in natural language. The agent writes SQL, runs queries, and generates interactive Plotly visualizations. Supports DuckDB, PostgreSQL, SQLite, and Flight SQL databases. Also queries local CSV and Parquet files directly — no database setup required. Supports Anthropic Claude (default), GitHub Models (open source), and Ollama (local) as LLM backends.
Developers:
Thom, Daniel [1]
  1. National Laboratory of the Rockies (NLR), Golden, CO (United States)
Release Date:
2026-04-06
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Programming Languages:
Python
TypeScript
Mustache
CSS
HTML
Svelte
Licenses:
BSD 3-clause "New" or "Revised" License
Sponsoring Org.:
Code ID:
179639
Site Accession Number:
NLR SWR-26-045
Research Org.:
National Laboratory of the Rockies (NLR), Golden, CO (United States)
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Country of Origin:
United States

RESOURCE

Citation Formats

Thom, Daniel. datasight [SWR-26-045]. Computer Software. https://github.com/dsgrid/datasight. USDOE Office of Critical Minerals and Energy Innovation (CMEI), Office of Critical Minerals, Materials, and Manufacturing (CM3). Analysis and Strategy Office (ASO). 06 Apr. 2026. Web. doi:10.11578/dc.20260420.2.
Thom, Daniel. (2026, April 06). datasight [SWR-26-045]. [Computer software]. https://github.com/dsgrid/datasight. https://doi.org/10.11578/dc.20260420.2.
Thom, Daniel. "datasight [SWR-26-045]." Computer software. April 06, 2026. https://github.com/dsgrid/datasight. https://doi.org/10.11578/dc.20260420.2.
@misc{ doecode_179639,
title = {datasight [SWR-26-045]},
author = {Thom, Daniel},
abstractNote = {This software is an AI-powered data exploration with natural language. datasight connects an AI agent to your database and provides a web UI where you can ask questions in natural language. The agent writes SQL, runs queries, and generates interactive Plotly visualizations. Supports DuckDB, PostgreSQL, SQLite, and Flight SQL databases. Also queries local CSV and Parquet files directly — no database setup required. Supports Anthropic Claude (default), GitHub Models (open source), and Ollama (local) as LLM backends.},
doi = {10.11578/dc.20260420.2},
url = {https://doi.org/10.11578/dc.20260420.2},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20260420.2}},
year = {2026},
month = {apr}
}