# Vanna Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/vanna
> Markdown URL: https://aitinkerers.org/technologies/vanna.md
> Technology record last updated: 2026-04-19T17:23:26Z
> Generated: 2026-09-22T19:41:42Z

Vanna is the open-source, Retrieval-Augmented Generation (RAG) framework that translates natural language questions into precise SQL for any database.

Vanna is your AI sidekick: an open-source Python framework that eliminates the data bottleneck. It uses a RAG architecture to connect Large Language Models (LLMs) directly to your database, generating accurate, context-aware SQL from plain English questions. This framework is highly flexible, supporting multiple LLMs (OpenAI, Gemini) and databases (Snowflake, PostgreSQL, SQLite, etc.). Vanna 2.0 (the latest version) includes features like user-scoped execution, robust Role-Based Access Control (RBAC), and self-learning capabilities, ensuring query accuracy improves over time as the agent learns your specific schema and business logic. Developers use Vanna to quickly embed secure, chat-to-data functionality directly into their applications, democratizing data access for all end-users.

- Official technology site: https://vanna.ai/
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Generating SQL using LLMs](https://nyc.aitinkerers.org/talks/rsvp_CHSwRRxJmQQ)

I can give a demo of using RAG to generate accurate SQL for your database. I'll be using the Vanna Python package for orchestration and I can even show it using fully open source components like using Ollama to run your LLM locally and Chroma running locally as a vector storage layer. We can discuss the prompting strategy, various approaches, and anything else that may be related.

- Event context: Live from Civic Hall! AI Tinkerers Meetup | NY#TechWeek — 2024-06-03 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_CHSwRRxJmQQ

## Related Technologies

- [Chroma](https://aitinkerers.org/technologies/chroma) ([Markdown](https://aitinkerers.org/technologies/chroma.md)) — 8 public demos
- [Jupyter notebook](https://aitinkerers.org/technologies/jupyter-notebook) ([Markdown](https://aitinkerers.org/technologies/jupyter-notebook.md)) — 13 public demos
- [Ollama](https://aitinkerers.org/technologies/ollama) ([Markdown](https://aitinkerers.org/technologies/ollama.md)) — 77 public demos
- [Streamlit](https://aitinkerers.org/technologies/streamlit) ([Markdown](https://aitinkerers.org/technologies/streamlit.md)) — 89 public demos