Hey there HN!<p>We've just open-sourced Vanna – a Python package that allows you to transform questions into SQL. We've leveraged LLMs to enable you to "ask" databases what you need, bypassing the need to "write" complex SQL.<p>Quick Overview:<p>- "Train" using DDL statements, documentation, or known correct SQL statements.<p>- "Ask" 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://github.com/vanna-ai/vanna">https://github.com/vanna-ai/vanna</a>
Looks nice but I'm confused why it's advertised as if it's training anything. It's just doing retrieval from a vector db and generating a prompt with openai/LLM.
Just curious what kinds of models are used in your project?<p><a href="https://arxiv.org/abs/2306.08891" rel="nofollow noreferrer">https://arxiv.org/abs/2306.08891</a> One paper seems to suggest trained specialized model can outperform LLM in some tasks.