The fastest way to get actionable insights from your database just by asking questions
TLDR: It all has to do with the training data you give it, which is what
helps with.The Vanna Python package and the various frontend integrations are all open-source. You can run Vanna on your own infrastructure.
Vanna’s capabilities are tied to the training data you give it. More training data means better accuracy for large and complex datasets.
Your database contents are never sent to the LLM unless you specifically enable features that require it. The metadata storage layer only sees schemas, documentation, and queries.
As you use Vanna more, your model continuously improves as we augment your training data.
We have out-of-the-box support Snowflake , BigQuery, Postgres, and many others. You can easily make a connector for any database.
Start in a Jupyter Notebook. Expose to business users via Slackbot, web app, Streamlit app, any other frontend. Even integrate in your web app for customers.
The core Vanna package is open-source and configurable.
We offer hosted components and enterprise services.
Many large enterprises need customization in deployment. Vanna is open-source so you can do this yourself. If you need help, contact us and we'll connect you with experienced developers.