# Vanna AI Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/vanna-ai
> Markdown URL: https://aitinkerers.org/technologies/vanna-ai.md
> Technology record last updated: 2026-03-10T16:30:36Z
> Generated: 2026-09-21T17:34:39Z

Vanna AI is the open-source Python RAG framework that translates natural language into accurate SQL queries, empowering users to 'chat' directly with their database.

Vanna AI is your production-ready, open-source Python framework for NL2SQL (Natural Language to SQL). It utilizes Retrieval-Augmented Generation (RAG) to connect Large Language Models (LLMs) to your database (e.g., Snowflake, PostgreSQL, BigQuery). The process is two-step: train the RAG model on your specific schema and SQL examples, then ask questions in plain English. This eliminates the SQL bottleneck, allowing business users to gain quick insights and enabling developers to build secure, user-scoped AI data agents. Vanna 2.0 features include role-based access control (RBAC) and embeddable UI components for seamless integration.

- Official technology site: https://vanna.ai
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Using evals to build robust chatbot assistants](https://dubai.aitinkerers.org/talks/rsvp_VES7t3DOtpk)

I'll be demonstrating a project I am working on where we are using evals to build robust LLM pipelines. Evals help us be more confident shipping LLM based apps to production. I am building a chatbot assistant that is functioning as a Natural Language to SQL agent, allowing users to interact with data in the database, and to get insights from the companies data. This is an actual live project for a business in the UAE The demo will be focusing on how we built evaluation sets to help write deterministic tests for the agent, to give us more confidence in its performance. We will discuss - how we break down the potential query space of the assistant into defined categories using dimensions and error analysis. This helps structure the set of queries we want our bot to work for, as oppose to having an infinite query space which is hard to design good products around. This gives us structure for designing a well performing assistant - we will show how we have written automated evaluation tests, where we pass queries to our bot, check the results it gets from the db, and we validate that against expected data. This is basically writing deterministic unit tests for our non-deterministic agent pipeline

- Event context: AI Tinkerers Dubai Meetup — August 2025 Demo Day — 2025-08-23 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_VES7t3DOtpk

### [AI SQL Agent](https://dubai.aitinkerers.org/talks/rsvp_FMQcpud78S0)

An AI-driven system that automates real-time executive briefings and business insights to enhance decision-making. Text to SQL generator that taken in Simple English analytical questions as input and outputs the answer via a SQL Generator.

- Event context: AI Tinkerers Dubai - April 2025 - Demos Night! — 2025-04-11 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_FMQcpud78S0

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Amazon Athena](https://aitinkerers.org/technologies/amazon-athena) ([Markdown](https://aitinkerers.org/technologies/amazon-athena.md)) — 1 public demo
- [Amazon EC2](https://aitinkerers.org/technologies/amazon-ec2) ([Markdown](https://aitinkerers.org/technologies/amazon-ec2.md)) — 7 public demos
- [Amazon RDS](https://aitinkerers.org/technologies/amazon-rds) ([Markdown](https://aitinkerers.org/technologies/amazon-rds.md)) — 3 public demos
- [Anthropic Bedrock](https://aitinkerers.org/technologies/anthropic-bedrock) ([Markdown](https://aitinkerers.org/technologies/anthropic-bedrock.md)) — 1 public demo
- [Flask](https://aitinkerers.org/technologies/flask) ([Markdown](https://aitinkerers.org/technologies/flask.md)) — 24 public demos
- [Pytest](https://aitinkerers.org/technologies/pytest) ([Markdown](https://aitinkerers.org/technologies/pytest.md)) — 6 public demos