Let Vanna.AI write your SQL for you
Vanna is an Open-Source Python-based AI SQL agent trained on your schema that writes complex SQL in seconds
import vanna as vn
vn.set_api_key(vn.get_api_key('my-email@example.com'))
vn.set_model('chinook')
vn.vn.connect_to_sqlite('https://vanna.ai/Chinook.sqlite')
vn.ask('What are the top 10 artists by sales?')
Whitepaper: How to get high SQL accuracy rates using AI
TLDR: It all has to do with the training data you give it, which is what helps with.
Sign up for our newsletter
Get the latest on Vanna & AI generated SQL
Why ?
High accuracy on complex datasets
Vanna’s capabilities are tied to the training data you give it. More training data means better accuracy for large and complex datasets.
Secure and private
Your database contents are never sent to Vanna’s servers. We only see the bare minimum - schemas & queries.
Isolated, custom model
You train a custom model specific to your database and your schema. Nobody else can use your model or view your model’s training data unless you choose to add members to your model or make it public. We use a combination of third-party foundational models (OpenAI, Google) and our own LLM.
Self learning
As you use Vanna more, your model continuously improves as we augment your training data.
Supports many databases
We have out-of-the-box support Snowflake, BigQuery, Postgres. You can easily make a connector for any database.
Pretrained models
If you’re a data provider you can publish your models for anyone to use. As part of our roadmap, we are in the process of pre-training models for common datasets (Google Ads, Facebook ads, etc).
Choose your front end
Start in a Jupyter Notebook. Expose to business users via Slackbot, web app, Streamlit app, or Excel plugin. Even integrate in your web app for customers.
Supports Your Database
If you can connect to it in Python, you can use it with Vanna
Vanna.AI
The fastest way to get insights from your database just by asking questions
Pricing
Open Source
Bring your own LLM
- Integrate with any LLM
- Local metadata storage using ChromaDB
- Customize however you like
Free Tier
Easiest to use
- Free use of LLM
- Free use of hosted metadata storage
- GPT 3.5 Foundational Model
Paid Tier
Best for companies
- Hosted Slack / MS Teams bot
- More Capable Foundational Models
- Customized VPC Deployments
"Data security and privacy is the number 1 reason that our codebase is open-source."
