TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: How to use LLMs to generate accurate SQL for real-world data

21 点作者 zainhoda超过 1 年前
Hey HN,<p>We are Zain and Ashish, founders of Vanna AI. We recently embarked on an experiment to see if large language models (specifically LLMs) could help in generating SQL queries for real-world datasets. We initially started this project as a web app but realized that it was most useful and had broadest applicability as a Python package since you can then incorporate it into an existing workflow (Jupyter notebook, Slackbot, etc).<p>We&#x27;ve had some good success with customer datasets but we&#x27;ve generally heard a lot of skepticism so we decided to write a paper about the methodology we&#x27;re using and how various LLMs compare.<p>Let us know if you have any questions or requests. The underlying Python package is open source. There is a server component to store and retrieve metadata but by next week there will be a fully open-source and locally runnable version.<p>Cheers!

2 条评论

chuckhend超过 1 年前
This looks awesome, great work team! A few questions :)<p>How complex were the &#x27;static examples&#x27; that were used? Can you share the examples of the three that were used in the tests?<p>Were the &quot;contextually relevant sql&quot; ran in addition to or isolated from the &quot;static examples&quot;?
评论 #37166245 未加载
tamiral超过 1 年前
really interesting work ! looking forward to exploring this with some of my datasets. Keep up the great work!