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: Vanna AI – Open-sourced text-to-SQL in Python

33 点作者 zainhoda超过 1 年前
Hey there HN!<p>We&#x27;ve just open-sourced Vanna – a Python package that allows you to transform questions into SQL. We&#x27;ve leveraged LLMs to enable you to &quot;ask&quot; databases what you need, bypassing the need to &quot;write&quot; complex SQL.<p>Quick Overview:<p>- &quot;Train&quot; using DDL statements, documentation, or known correct SQL statements.<p>- &quot;Ask&quot; questions in natural language and receive SQL, tables, and charts in return.<p>- Open Source Flexibility: Swap storage mechanisms, customize LLMs, and choose your databases.<p>- Local or Hosted: Operate everything locally or use our hosted version for free (including complimentary LLM calls).<p>- Use it wherever Python is applicable. We provide code examples for integration in Jupyter, Streamlit, Slack, and more.<p>We would greatly appreciate your feedback, insights on issues, and contributions:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;vanna-ai&#x2F;vanna">https:&#x2F;&#x2F;github.com&#x2F;vanna-ai&#x2F;vanna</a>

6 条评论

npace12超过 1 年前
Looks nice but I&#x27;m confused why it&#x27;s advertised as if it&#x27;s training anything. It&#x27;s just doing retrieval from a vector db and generating a prompt with openai&#x2F;LLM.
评论 #37435334 未加载
ban-lan-gen超过 1 年前
Just curious what kinds of models are used in your project?<p><a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2306.08891" rel="nofollow noreferrer">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2306.08891</a> One paper seems to suggest trained specialized model can outperform LLM in some tasks.
评论 #37435384 未加载
crazy_marksman超过 1 年前
Impressive! Quick question - is it possible to generate sql for a slight variant of sql? My project augments standard sql with a few new constructs.
评论 #37444833 未加载
jesuslop超过 1 年前
These results are impressive, guys. I&#x27;m saving a pointer to dig deeper to glean the details. Tip in the hat for making it open.
tzm超过 1 年前
Open source, but requires an API key?
评论 #37435361 未加载
ashishsingal超过 1 年前
oh how exciting :)